@inproceedings{ICCV2017Haolu,
    author      = {Hao Lu and Lei Zhang and  Zhiguo Cao and Wei Wei and Ke Xian and Chunhua Shen and Anton {van den Hengel}},
    title       = {When Unsupervised Domain Adaptation Meets Tensor Representations},
    year        = {2017},
    month       = {},
    booktitle   = {International  Conference on Computer Vision (ICCV'17)},
    address     = {},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {},
    url         = {},
    project     = {},
}

@inproceedings{ICCV2017Zhuang,
    author      = {Bohan Zhuang  and  Lingqiao Liu  and Chunhua Shen  and Ian Reid},
    title       = {Towards Context-aware Interaction Recognition},
    year        = {2017},
    month       = {},
    booktitle   = {International  Conference on Computer Vision (ICCV'17)},
    address     = {},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1703.06246},
    url         = {},
    project     = {},
}



@inproceedings{ICCV2017Chen,
    author      = {Yu Chen  and  Chunhua Shen  and Xiu-Shen Wei  and Lingqiao Liu  and Jian Yang},
    title       = {Adversarial {PoseNet}: A Structure-aware Convolutional Network for Human Pose Estimation},
    year        = {2017},
    month       = {},
    booktitle   = {International  Conference on Computer Vision (ICCV'17)},
    address     = {},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1705.00389},
    url         = {},
    project     = {},
}



@inproceedings{ICCV2017WeiLiu,
    author      = {Wei Liu and Xiaogang Chen and Chuanhua Shen  and  Zhi Liu  and Jie Yang},
    title       = {Semi-Global Weighted Least Squares in Image Filtering},
    year        = {2017},
    month       = {},
    booktitle   = {International  Conference on Computer Vision (ICCV'17)},
    address     = {},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1705.01674},
    url         = {},
    project     = {},
}


@inproceedings{ICCV2017HuiLi,
    author      = {Hui Li and Peng Wang and Chunhua Shen},
    title       = {Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks},
    year        = {2017},
    month       = {},
    booktitle   = {International  Conference on Computer Vision (ICCV'17)},
    address     = {},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1707.03985},
    url         = {},
    project     = {},
}




@inproceedings{BMVC17Zeroshot,
    author      = {Ruizhi Qiao and Lingqiao Liu  and Chunhua Shen and Anton {van den Hengel}},
    title       = {Visually Aligned Word Embeddings for Improving Zero-shot Learning},
    year        = {2017},
    month       = {},
    booktitle   = {British  Machine  Vision Conference  (BMVC'17)},
    address     = {},
    venue       = {BMVC},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {},
    url         = {},
    project     = {},
}

@inproceedings{BMVC2017Tong,
          author      = {Tong Shen and Guosheng Lin  and Lingqiao Liu and Chunhua Shen  and  Ian Reid},
          title       = {Weakly supervised semantic segmentation based on co-segmentation},
          year        = {2017},
          month       = {},
          booktitle   = {British  Machine  Vision Conference  (BMVC'17)},
          address     = {},
          venue       = {BMVC},
          pages       = {},
          volume      = {},
          publisher   = {},
          eprint      = {1701.07122},
          url         = {},
          project     = {},
}

@inproceedings{IJCAI2017Tong,
          author      = {Tong Shen and Guosheng Lin  and  Chunhua Shen  and  Ian Reid},
          title       = {Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation},
          year        = {2017},
          month       = {},
          booktitle   = {International Joint Conference on Artificial Intelligence (IJCAI'17)},
          address     = {},
          venue       = {IJCAI},
          pages       = {},
          volume      = {},
          publisher   = {},
          eprint      = {1701.07122},
          url         = {},
          project     = {},
}

@inproceedings{IJCAI2017Wei,
          author      = {Xiu-Shen Wei  and  Chen-Lin Zhang  and  Yao Li  and Chen-Wei Xie  and  Jianxin Wu  and Chunhua Shen  and Zhi-Hua Zhou},
          title       = {Deep Descriptor Transforming for Image Co-Localization},
          year        = {2017},
          month       = {},
          booktitle   = {International Joint Conference on Artificial Intelligence (IJCAI'17)},
          address     = {},
          venue       = {IJCAI},
          pages       = {},
          volume      = {},
          publisher   = {},
          eprint      = {1705.02758},
          url         = {},
          project     = {},
}

@inproceedings{IJCAI2017Wang,
          author      = {Peng Wang  and  Qi Wu and  Chunhua Shen  and Anton {van den Hengel} and Anthony Dick},
          title       = {Explicit Knowledge-based Reasoning for Visual Question Answering},
          year        = {2017},
          month       = {},
          booktitle   = {International Joint Conference on Artificial Intelligence (IJCAI'17)},
          address     = {},
          venue       = {IJCAI},
          pages       = {},
          volume      = {},
          publisher   = {},
          eprint      = {1511.02570},
          url         = {},
          project     = {},
}

@article{Lin2017Semantic,
  author  = {Guosheng Lin  and  Chunhua Shen  and  Anton {van den Hengel} and  Ian Reid},
  title   = {Exploring Context with Deep Structured models for Semantic Segmentation},
  year    = 2017,
  venue   = {TPAMI},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  eprint  = {1603.03183},
}

@article{Wu2017External,
  author  = {Qi Wu  and   Chunhua Shen  and Anton {van den Hengel} and Peng Wang  and Anthony Dick},
  title   = {Image Captioning and Visual Question Answering Based on Attributes and External Knowledge},
  year    = 2017,
  venue   = {TPAMI},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  eprint  = {1603.02814},
}

@article{Li2017Removal,
  author ={Ying Li and Wenbo Li and Chunhua Shen},
  title  = {Removal of Optically Thick Clouds From High-resolution Satellite Imagery Using Dictionary Group
    Learning and Interdictionary Nonlocal Joint Sparse Coding},
  year   = 2017,
  venue  = {JSTAEORS},
  journal ={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
}

@article{SWP2017Hu,
    author = {Qichang Hu  and  Huibing Wang  and  Teng Li  and   Chunhua Shen},
    title  = {Deep {CNNs} with Spatially Weighted Pooling for Fine-grained Car Recognition},
    journal= {IEEE Transactions on Intelligent Transportation Systems},
    year   = {2017},
    eprint = {},
    venue  = {TITS},
}

@inproceedings{CVPR2017WangVQA,
          author      = {Peng Wang and Qi Wu and Chunhua Shen  and  Anton {van den Hengel}},
          title       = {The {VQA}-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions},
          year        = {2017},
          month       = {},
          booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17)},
          address     = {},
          venue       = {CVPR},
          pages       = {},
          volume      = {},
          publisher   = {},
          eprint      = {1612.05386},
          url         = {},
          project     = {},
}

@inproceedings{CVPR2017Lin,
  author      = {Guosheng Lin and  Anton Milan  and Chunhua Shen  and Ian Reid},
  title       = {{RefineNet}: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation},
  year        = {2017},
  month       = {},
  booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17)},
  address     = {},
  venue       = {CVPR},
  pages       = {},
  volume      = {},
  publisher   = {},
  eprint      = {1611.06612},
  url         = {},
  project     = {https://github.com/guosheng/refinenet},
}

@inproceedings{CVPR2017YaoLi,
  author      = {Yao Li  and  Guosheng Lin  and Bohan Zhuang  and Lingqiao Liu  and Chunhua Shen and Anton {van den Hengel}},
  title       = {Sequential Person Recognition in Photo Albums with a Recurrent Network},
  year        = {2017},
  month       = {},
  booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17)},
  address     = {},
  venue       = {CVPR},
  pages       = {},
  volume      = {},
  publisher   = {},
  eprint      = {1611.09967},
  url         = {},
  project     = {},
}



@inproceedings{CVPR2017Gong,
  author      = {Dong Gong  and  Jie Yang  and Lingqiao Liu  and Yanning Zhang  and Ian Reid  and Chunhua Shen and Anton {van den Hengel} and Qinfeng Shi},
  title       = {From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur},
  year        = {2017},
  month       = {},
  booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17)},
  address     = {},
  venue       = {CVPR},
  pages       = {},
  volume      = {},
  publisher   = {},
  eprint      = {1612.02583},
  url         = {},
  project     = {},
}



@inproceedings{CVPR2017Zhuang,
  author      = {Bohan Zhuang  and  Lingqiao Liu  and  Chunhua Shen  and Ian Reid},
  title       = {Attend in groups: a weakly-supervised deep learning framework for learning from web data},
  year        = {2017},
  month       = {},
  booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17)},
  address     = {},
  venue       = {CVPR},
  pages       = {},
  volume      = {},
  publisher   = {},
  eprint      = {1611.09960},
  url         = {},
  project     = {},
}



@inproceedings{CVPR2017WangAttend,
  author      = {Peng Wang  and Lingqiao Liu  and Chunhua Shen  and Zi Huang  and  Anton {van den Hengel} and Heng Tao Shen},
  title       = {Multi-attention Network for One Shot Learning},
  year        = {2017},
  month       = {},
  booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17)},
  address     = {},
  venue       = {CVPR},
  pages       = {},
  volume      = {},
  publisher   = {},
  eprint      = {},
  url         = {},
  project     = {},
}

@article{TNNLS2017Liu,
    author = {Fayao Liu and  Guosheng Lin and Ruizhi Qiao  and Chunhua Shen},
    title  = {Structured Learning of Tree Potentials in {CRF} for Image Segmentation},
    journal= {IEEE Transactions on Neural Networks and Learning Systems},
    year   = {2017},
    eprint = {1703.08764},
    venue  = {TNN},
}

@article{TIP2017Liu,
    author = {Fayao Liu and  Guosheng Lin and Chunhua Shen},
    title  = {Discriminative Training of Deep Fully-connected Continuous {CRF} with Task-specific Loss},
    journal= {IEEE Transactions on Image Processing},
    year   = {2017},
    eprint = {1601.07649},
    venue  = {TIP},
}


@article{IJCV2017Lin,
    author = {Guosheng Lin  and  Fayao Liu  and  Chunhua Shen  and Jianxin Wu  and Heng Tao Shen},
    title  = {Structured Learning of Binary Codes with Column Generation for Optimizing Ranking Measures},
    journal= {International Journal of Computer Vision},
    volume = {},
    number = {},
    year   = {2017},
    url    = {},
    eprint = {1602.06654},
    venue  = {IJCV},
    project= {https://bitbucket.org/guosheng/structhash},
    note   = {},
}


@article{PR2017Qiao,
    author = {Ruizhi Qiao   and   Lingqiao Liu  and  Chunhua Shen  and Anton {van den Hengel}},
    title  = {Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition},
    journal= {Pattern Recognition},
    volume = {},
    number = {},
    year   = {2017},
    url    = {},
    eprint = {1504.04923},
    venue  = {PR},
    project= {},
    note   = {},
}


@article{TCSVT2017Hu,
    author = {Qichang Hu and  Peng Wang  and Chunhua Shen  and Anton {van den Hengel} and Fatih Porikli},
    title  = {Pushing the Limits of Deep {CNNs} for Pedestrian Detection},
    journal= {IEEE Transactions on Circuits and Systems for Video Technology},
    volume = {},
    number = {},
    year   = {2017},
    url    = {},
    eprint = {1603.04525},
    venue  = {TCSVT},
    project= {},
    note   = {},
}



@article{Wu2017PR,
    author = {Lin Wu and Chunhua Shen and Anton {van den Hengel}},
    title  = {Deep Linear Discriminant Analysis on {F}isher Networks: A Hybrid Architecture for Person Re-identification},
    journal= {Pattern Recognition},
    volume = {},
    number = {},
    year   = {2017},
    url    = {},
    eprint = {},
    venue  = {PR},
    project= {},
    note   = {},
}





@article{TCSVT2017Sheng,
    author = {Biyun Sheng and Chunhua Shen and Guosheng Lin and Jun Li and Wankou Yang and Changyin Sun},
    title  = {Crowd Counting via Weighted {VLAD} on Dense Attribute Feature Maps},
    journal= {IEEE Transactions on Circuits and Systems for Video Technology},
    volume = {},
    number = {},
    year   = {2017},
    url    = {},
    eprint = {1604.08660},
    venue  = {TCSVT},
    project= {},
    note   = {},
}



@article{TPAMI2017Liu,
    author = {Lingqiao Liu  and Peng Wang  and  Chunhua Shen  and  Lei Wang  and  Anton {van den Hengel}  and  Chao Wang  and  Heng Tao Shen},
    title  = {Compositional Model based {F}isher Vector Coding for Image Classification},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {},
    number = {},
    year   = {2017},
    url    = {},
    eprint = {1601.04143},
    venue  = {TPAMI},
    project= {},
    note   = {},
}


@article{Cross2017Liu,
    author = {Lingqiao Liu  and Chunhua Shen  and  Anton {van den Hengel}},
    title  = {Cross-convolutional-layer Pooling for Image Recognition},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {},
    number = {},
    year   = {2017},
    url    = {},
    month  = {},
    pages  = {},
    eprint = {1510.00921},
    venue  = {TPAMI},
    project= {},
    note   = {},
}




@article{TIP2016Cao,
    author = {Yuanzhouhan Cao and  Chunhua Shen and Heng Tao Shen},
    title  = {Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation},
    journal= {IEEE Transactions on Image Processing},
    volume = {},
    number = {},
    year   = {2017},
    url    = {},
    month  = {},
    pages  = {},
    eprint = {1610.01706},
    venue  = {TIP},
    project= {},
    note   = {},
}




@article{CVIU2016,
    author = {Sakrapee Paisitkriangkrai and  Lin Wu  and  Chunhua Shen and Anton {van den Hengel}},
    title  = {Structured learning of metric ensembles with application to person re-identification},
    journal= {Computer Vision and Image Understanding},
    volume = {},
    number = {},
    year   = {2016},
    url    = {},
    month  = {},
    pages  = {},
    eprint = {1511.08531},
    venue  = {CVIU},
    project= {},
    note   = {},
}


@article{Yao2016IJCV,
    author = {Yao Li and Lingqiao Liu and Chunhua Shen and Anton {van den Hengel}},
    title  = {Mining Mid-level Visual Patterns with Deep {CNN} Activations},
    journal= {International Journal of Computer Vision},
    volume = {},
    number = {},
    year   = {2016},
    url    = {http://rdcu.be/j1mA},
    month  = {},
    pages  = {},
    eprint = {1506.06343},
    venue  = {IJCV},
    project= {https://github.com/yaoliUoA/MDPM},
    note   = {},
}


@article{Zhang2016TGSE,
    author = {Lei Zhang and Wei Wei and Yanning Zhang and Chunhua Shen and  Anton {van den Hengel} and Qinfeng Shi},
    title  = {Dictionary Learning for Promoting Structured Sparsity in Hyerpsectral Compressive Sensing},
    journal= {IEEE Transactions on Geoscience and Remote Sensing},
    volume = {54},
    number = {12},
    year   = {2016},
    url    = {},
    month  = {},
    pages  = {7223--7235},
    eprint = {},
    venue  = {TGRS},
    project= {},
    note   = {},
}


@inproceedings{NIPS2016,
    author      = {Xiao-Jiao Mao and Chunhua Shen  and  Yu-Bin Yang},
    title       = {Image Restoration Using Very Deep Fully Convolutional Encoder-Decoder Networks with Symmetric Skip Connections},
    year        = {2016},
    month       = {},
    booktitle   = {Advances in Neural Information Processing Systems (NIPS'16)},
    address     = {},
    venue       = {NIPS},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1603.09056},
    url         = {http://papers.nips.cc/paper/6172-image-restoration-using-very-deep-convolutional-encoder-decoder-networks-with-symmetric-skip-connections.pdf},
    project     = {https://bitbucket.org/chhshen/image-denoising/},
}



@inproceedings{ECCV16hyperspectral,
    author      = {Lei Zhang and Wei Wei and Yanning Zhang and Chunhua Shen  and Anton {van den Hengel}  and Qinfeng Shi},
    title       = {Cluster Sparsity Field for Hyperspectral Imagery Denoising},
    year        = {2016},
    month       = {},
    booktitle   = {European Conference on Computer Vision (ECCV'16)},
    address     = {},
    venue       = {ECCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {},
    url         = {},
    project     = {},
}


@inproceedings{ECCV16Li,
    author      = {Yao Li and Lingqiao Liu and Chunhua Shen and Anton {van den Hengel}},
    title       = {Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution},
    year        = {2016},
    month       = {},
    booktitle   = {European Conference on Computer Vision (ECCV'16)},
    address     = {},
    venue       = {ECCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1603.04619},
    url         = {},
    project     = {},
}


@article{Liu2016Tracking,
    author = {Fayao Liu and Chunhua Shen and Ian Reid and Anton {van den Hengel}},
    title  = {Online Unsupervised Feature Learning for Visual Tracking},
    journal= {Image and Vision Computing},
    volume = {},
    number = {},
    year   = {2016},
    url    = {},
    month  = {},
    pages  = {},
    eprint = {1310.1690},
    venue  = {IVC},
    project= {},
    note   = {},
}



@inproceedings{CVPR16AMA,
    author      = {Qi Wu and Peng Wang and Chunhua Shen and Anthony Dick  and Anton {van den Hengel} },
    title       = {Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources},
    year        = {2016},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1511.06973},
    url         = {},
    project     = {},
}


@inproceedings{CVPR16What,
    author      = {Qi Wu  and Chunhua Shen  and Lingqiao Liu and Anthony Dick and Anton {van den Hengel}},
    title       = {What Value Do Explicit High Level Concepts Have in Vision to Language Problems},
    year        = {2016},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1506.01144},
    url         = {},
    project     = {},
}


@inproceedings{CVPR16Irregular,
    author      = {Peng Wang  and Lingqiao Liu  and Chunhua Shen and Zi Huang and Anton {van den Hengel} and Heng Tao Shen},
    title       = {What's Wrong with that Object? Identifying Irregular Object
                   From Images by Modelling the Detection Score Distribution},
    year        = {2016},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1602.04422},
    url         = {},
    project     = {},
}


@inproceedings{CVPR16labelling,
    author      = {Guosheng Lin and Chunhua Shen  and Anton {van dan Hengel} and Ian Reid},
    title       = {Efficient piecewise training of deep structured models for semantic segmentation},
    year        = {2016},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1504.01013},
    url         = {},
    project     = {},
}


@inproceedings{CVPR16Binary,
    author      = {Bohan Zhuang and Guosheng Lin and Chunhua Shen and Ian Reid},
    title       = {Fast Training of Triplet-based Deep Binary Embedding Networks},
    year        = {2016},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1603.02844},
    url         = {},
    project     = {https://bitbucket.org/jingruixiaozhuang/fast-training-of-triplet-based-deep-binary-embedding-networks},
}



@inproceedings{CVPR16Zeroshot,
    author      = {Ruizhi Qiao and Lingqiao Liu  and Chunhua Shen and Anton {van den Hengel}},
    title       = {Less is More: Zero-shot Learning from Online Textual Documents with Noise Suppression},
    year        = {2016},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1604.01146},
    url         = {},
    project     = {},
}





@article{Pooling2016Wang,
    author = {Peng Wang and  Yuanzhouhan Cao and Chunhua Shen and Lingqiao Liu and Heng Tao Shen},
    title  = {Temporal Pyramid Pooling Based Convolutional Neural Network for Action Recognition},
    journal= {IEEE Transactions on Circuits and Systems for Video Technology},
    year   = {2016},
    eprint = {1503.01224},
    venue  = {TCSVT},
    project= {},
}

@article{Face2016Li,
    author = {Hanxi Li and Fumin Shen and Chunhua Shen  and Yang Yang and Yongsheng Gao},
    title  = {Face Recognition Using Linear Representation Ensembles},
    journal= {Pattern Recognition},
    volume = {},
    number = {},
    year   = {2016},
    url    = {http://dx.doi.org/10.1016/j.patcog.2015.12.011},
    month  = {},
    pages  = {},
    eprint = {1110.0264},
    venue  = {PR},
    project= {},
    note   = {},
}


@article{Canonical2016Wang,
    author = {Sheng Wang  and  Jianfeng Lu   and   Xingjian Gu  and Chunhua Shen  and  Rui Xia  and Jingyu Yang},
    title  = {Canonical principal angles correlation analysis for two-view data},
    journal= {Journal of Visual Communication and Image Representation},
    volume = {},
    number = {},
    year   = {2016},
    url    = {http://dx.doi.org/10.1016/j.jvcir.2015.12.001},
    month  = {},
    pages  = {},
    eprint = {},
    venue  = {JVCIR},
    project= {},
    note   = {},
}


@article{Part2016Yao,
    author = {Rui Yao  and Qinfeng Shi  and Chunhua Shen  and Yanning Zhang and Anton {van den Hengel}},
    title  = {Part-based robust tracking using online latent structured learning},
    journal= {IEEE Transactions on Circuits and Systems for Video Technology},
    volume = {},
    number = {},
    year   = {2016},
    url    = {http://dx.doi.org/10.1109/TCSVT.2016.2527358},
    month  = {},
    pages  = {},
    eprint = {},
    venue  = {TCSVT},
    project= {},
    note   = {},
}

@article{PRFace2016Shen,
    author = {Fumin Shen  and  Chunhua Shen  and  Xiang Zhou  and Yang Yang and Heng Tao Shen},
    title  = {Face Image Classification by Pooling Raw Features},
    journal= {Pattern Recognition},
    volume = {54},
    number = {},
    year   = {2016},
    url    = {},
    month  = {},
    pages  = {94--103},
    eprint = {1406.6811},
    venue  = {PR},
    project= {https://github.com/bd622/FacePooling},
    note   = {},
}


@article{BQP2015Wang,
    author = {Peng Wang and Chunhua Shen  and  Anton {van den Hengel} and Philip H. S. Torr},
    title  = {Large-scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {},
    number = {},
    year   = {2016},
    url    = {http://dx.doi.org/10.1109/TPAMI.2016.2541146},
    month  = {},
    pages  = {},
    eprint = {1411.7564},
    venue  = {TPAMI},
    project= {},
    note   = {},
}


@article{Depth2015Liu,
    author = {Fayao Liu and Chunhua Shen  and  Guosheng Lin and Ian Reid},
    title  = {Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {},
    number = {},
    year   = {2016},
    eprint = {1502.07411},
    month  = {},
    pages  = {},
    url    = {http://dx.doi.org/10.1109/TPAMI.2015.2505283},
    venue  = {TPAMI},
    project= {http://goo.gl/rAKWrS},
    note   = {},
}

@article{BnB2015Wang,
    author = {Peng Wang and Chunhua Shen  and Anton {van den Hengel} and Philip Torr},
    title  = {Efficient Semidefinite Branch-and-Cut for {MAP-MRF} Inference},
    journal= {International Journal of Computer Vision},
    volume = {117},
    number = {3},
    year   = {2016},
    url    = {http://doi.org/10.1007/s11263-015-0865-2},
    month  = {},
    pages  = {269--289},
    eprint = {1404.5009},
    venue  = {IJCV},
    project= {},
    note   = {},
}

@inproceedings{ICCV15Zhang,
    author      = {Lei Zhang and  Wei Wei  and  Yanning  Zhang and Fei Li  and Chunhua Shen and Qinfeng Shi},
    title       = {Hyperspectral Compressive Sensing Using Manifold-Structured Sparsity Prior},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE International Conference on Computer Vision (ICCV'15)},
    address     = {},
    venue       = {ICCV},
    pdf         = {http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zhang_Hyperspectral_Compressive_Sensing_ICCV_2015_paper.pdf},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {},
    url         = {},
    project     = {},
}

@inproceedings{NIPS15Lin,
    author      = {Guosheng Lin  and Chunhua Shen and Ian Reid and Anton {van den Hengel}},
    title       = {Deeply Learning the Messages in Message Passing Inference},
    year        = {2015},
    month       = {},
    booktitle   = {Advances in Neural Information Processing Systems (NIPS'15)},
    address     = {},
    venue       = {NIPS},
    pages       = {},
    volume      = {},
    publisher   = {},
    eprint      = {1506.02108},
    pdf         = {http://papers.nips.cc/paper/5791-deeply-learning-the-messages-in-message-passing-inference.pdf},
    project     = {},
}

@article{Hu2015TITS,
    author = {Qichang Hu and Sakrapee Paisitkriangkrai  and Chunhua Shen  and Anton {van den Hengel} and  Fatih Porikli},
    title  = {Fast Detection of Multiple Objects in Traffic Scenes with a Common Detection Framework},
    journal= {IEEE Transactions on Intelligent Transportation Systems},
    volume = {17},
    number = {4},
    year   = {2016},
    url    = {},
    month  = {},
    pages  = {1002--1014},
    venue  = {TITS},
    project= {},
    note   = {},
}


@article{Xi2015TPAMI,
    author = {Xi Li  and Chunhua Shen  and Anthony Dick and Zhongfei Zhang and  Yueting Zhuang},
    title  = {Online Metric-Weighted Linear Representations for Robust Visual Tracking},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {38},
    number = {5},
    year   = {2016},
    url    = {},
    month  = {},
    pages  = {931--950},
    eprint = {1507.05737},
    venue  = {TPAMI},
    project= {},
    note   = {},
}

@article{Paisitkriangkrai2015TPAMI,
    author = {Sakrapee Paisitkriangkrai  and Chunhua Shen  and Anton {van den Hengel}},
    title  = {Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {38},
    number = {6},
    year   = {2016},
    url    = {http://doi.org/10.1109/TPAMI.2015.2474388},
    month  = {},
    pages  = {1243--1257},
    eprint = {1409.5209},
    venue  = {TPAMI},
    project= {https://github.com/chhshen/pedestrian-detection},
    note   = {},
}

@inproceedings{CVPR15workshop,
    author      = {Michael Milford and Chunhua Shen and Stephanie Lowry and Niko Suenderhauf
                   and Sareh Shirazi and Guosheng Lin and Fayao Liu and Edward Pepperell and
                   Cesar Lerma and Ben Upcroft and Ian Reid},
    title       = {Sequence searching with Deep-Learnt Depth for Condition- and Viewpoint-Invariant Route-Based Place Recognition},
    year        = {2015},
    month       = {},
    booktitle   = {6th International Workshop on Computer Vision in Vehicle Technology, in conjunction with
                   IEEE Conference on Computer Vision and Pattern Recognition (CVVT'15)},
    address     = {},
    venue       = {workshop},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {Best paper award (Sponsored by NVIDIA)},
    eprint      = {},
    url         = {},
    pdf         = {http://www.cv-foundation.org/openaccess/content_cvpr_workshops_2015/W11/papers/Milford_Sequence_Searching_With_2015_CVPR_paper.pdf},
    project     = {},
}

@article{Zhang2015IJCV,
    author = {Chao Zhang and Chunhua Shen and Tingzhi Shen},
    title  = {Unsupervised Feature Learning for Dense Correspondences across Scenes},
    journal= {International Journal of Computer Vision},
    volume = {116},
    number = {1},
    year   = {2016},
    url    = {},
    month  = {},
    pages  = {90--107},
    eprint = {1501.00642},
    venue  = {IJCV},
    project= {https://bitbucket.org/chhshen/ufl},
    abstract={We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes.
              It is a challenging problem to estimate dense pixel correspondences between images depicting different scenes
              or instances of the same object category.
              While most such matching methods rely on hand-crafted features such as SIFT,
              we learn features from a large amount of unlabeled image patches using unsupervised learning.
              Pixel-layer features are obtained by encoding over the dictionary,
              followed by spatial pooling to obtain patch-layer features.
              The learned features are then seamlessly embedded into a multi-layer match-ing framework.
              We experimentally demonstrate that the learned features,
              together with our matching model, outperforms state-of-the-art methods such as the SIFT flow,
              coherency sensitive hashing and the recent deformable spatial pyramid matching methods both in terms of accuracy
              and computation efficiency. Furthermore, we evaluate the performance of a few different dictionary learning and feature
              encoding methods in the proposed pixel correspondences estimation framework,
              and analyse the impact of dictionary learning and feature encoding with respect to the final matching performance.
              },
    note   = {},
}

@article{Zhao2015TNN,
    author = {Xueyi Zhao and Xi Li and  Zhongfei Zhang and Chunhua Shen and Lixin Gao and Xuelong Li},
    title  = {Scalable Linear Visual Feature Learning via Online Parallel Nonnegative Matrix Factorization},
    journal= {IEEE Transactions on Neural Networks and Learning Systems},
    volume = {},
    number = {},
    year   = {2016},
    url    = {http://dx.doi.org/10.1109/TNNLS.2015.2499273},
    month  = {},
    pages  = {},
    eprint = {},
    venue  = {TNN},
    project= {},
    note   = {},
}

@article{Liu2015CRFPR,
    author = {Fayao Liu and Guosheng Lin and Chunhua Shen},
    title  = {{CRF} Learning with {CNN} Features for Image Segmentation},
    journal= {Pattern Recognition},
    volume = {48},
    number = {10},
    year   = {2015},
    url    = {},
    month  = {},
    pages  = {2983--2992},
    eprint = {1503.08263},
    venue  = {PR},
    project= {},
    note   = {},
}

@article{Liu2015TPAMI,
    author = {Lingqiao Liu and Lei Wang and Chunhua Shen},
    title  = {A Generalized Probabilistic Framework for Compact Codebook Creation},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {38},
    number = {2},
    year   = {2016},
    url    = {http://doi.org/10.1109/TPAMI.2015.2441069},
    month  = {},
    pages  = {224--237},
    eprint = {1401.7713},
    venue  = {TPAMI},
    project= {},
    note   = {},
}

@article{Harandi2015IJCV,
    author = {Mehrtash Harandi and Richard Hartley and Chunhua Shen and Brian Lovell and Conrad Sanderson},
    title  = {Extrinsic Methods for Coding and Dictionary Learning on {G}rassmann Manifolds},
    journal= {International Journal of Computer Vision},
    volume = {114},
    number = {2},
    year   = {2015},
    url    = {},
    month  = {},
    pages  = {113--136},
    eprint = {1401.8126},
    venue  = {IJCV},
    project= {https://github.com/chhshen/Grassmann/},
    note   = {},
}

@inproceedings{CVPR15a,
    author      = {Yao Li and Lingqiao Liu and Chunhua Shen and Anton  {van den Hengel}},
    title       = {Mid-level Deep Pattern Mining},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1411.6382},
    url         = {},
    pdf         = {},
    project     = {https://github.com/yaoliUoA/MDPM},
}

@inproceedings{CVPR15b,
    author      = {Fayao Liu and Chunhua Shen and Guosheng Lin},
    title       = {Deep Convolutional Neural Fields for Depth Estimation from a Single Image},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1411.6387},
    url         = {},
    pdf         = {},
    project     = {http://goo.gl/rAKWrS},
}

@inproceedings{CVPR15c,
    author      = {Fumin Shen and Chunhua Shen and Wei Liu and Heng Tao Shen},
    title       = {Supervised Discrete Hashing},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Shen_Supervised_Discrete_Hashing_2015_CVPR_paper.pdf},
    project     = {https://github.com/bd622/DiscretHashing/},
}

@inproceedings{CVPR15d,
    author      = {Lingqiao Liu and Chunhua Shen and Anton  {van den Hengel}},
    title       = {The Treasure beneath Convolutional Layers: Cross convolutional layer Pooling for Image Classification},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1411.7466},
    url         = {},
    pdf         = {},
    project     = {},
}

@inproceedings{CVPR15e,
    author      = {Peng Wang and Chunhua Shen and Anton  {van den Hengel}},
    title       = {Efficient {SDP} Inference for Fully-connected {CRFs} Based on Low-rank Decomposition},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1504.01492},
    url         = {},
    pdf         = {},
    project     = {},
}

@inproceedings{CVPR15f,
    author      = {Sakrapee Paisitkriangkrai and Chunhua Shen and Anton  {van den Hengel}},
    title       = {Learning to rank in person re-identification with metric ensembles},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1503.01543},
    url         = {},
    pdf         = {},
    project     = {},
}


@inproceedings{CVPR15g,
    author      = {Mingkui Tan  and Qinfeng Shi and Anton  {van den Hengel} and Chunhua Shen
                   and Junbin Gao and Fuyuan Hu
                   and Zhen Zhang},
    title       = {Learning Graph Structure for Multi-label Image Classification via Clique Generation},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Tan_Learning_Graph_Structure_2015_CVPR_paper.pdf},
    project     = {},
}



@inproceedings{CVPR15h,
    author      = {Bo Li and Chunhua Shen  and Yuchao Dai and Anton  {van den Hengel} and Mingyi He},
    title       = {Depth and Surface Normal Estimation from Monocular Images Using
                   Regression on Deep Features and Hierarchical {CRFs}},
    year        = {2015},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15)},
    address     = {},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Li_Depth_and_Surface_2015_CVPR_paper.pdf},
    project     = {},
}


@article{FastHash2015Lin,

    author = {Guosheng Lin and Chunhua Shen and Anton {van den Hengel}},
    title  = {Supervised Hashing Using Graph Cuts and Boosted Decision Trees},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {37},
    number = {11},
    year   = {2015},
    url    = {http://dx.doi.org/10.1109/TPAMI.2015.2404776},
    month  = {},
    pages  = {2317--2331},
    eprint = {1408.5574},
    venue  = {TPAMI},
    project= {https://bitbucket.org/chhshen/fasthash/},
    note   = {},
}

@article{Hashing2015Shen,
    author = {Fumin Shen and Chunhua Shen and Qinfeng Shi and Anton {van den Hengel} and Zhenmin Tang and Heng Tao Shen},
    title  = {Hashing on Nonlinear Manifolds},
    journal= {IEEE Transactions on Image Processing},
    volume = {24},
    number = {6},
    year   = {2015},
    url    = {},
    month  = {},
    pages  = {1839--1851},
    eprint = {1412.0826},
    venue  = {TIP},
    note   = {},
    project= {https://github.com/chhshen/Hashing-on-Nonlinear-Manifolds},
}



@article{SDP2015Li,
    author = {Hui Li and Chunhua Shen and Anton {van den Hengel} and Qinfeng Shi},
    title  = {Worst-Case Linear Discriminant Analysis as Scalable Semidefinite Feasibility Problems},
    journal= {IEEE Transactions on Image Processing},
    volume = {24},
    number = {8},
    year   = {2015},
    url    = {},
    month  = {},
    pages  = {2382--2392},
    eprint = {1411.7450},
    venue  = {TIP},
    note   = {},
    project= {https://github.com/chhshen/SDP-WLDA},
}


@inproceedings{Liu2014Fisher,
   author    = {Lingqiao Liu and Chunhua Shen and Lei Wang and Anton {van den Hengel} and Chao Wang},
   title     = {Encoding High Dimensional Local Features by Sparse Coding Based {F}isher Vectors},
   booktitle = {Advances in Neural Information Processing Systems (NIPS'14)},
   year      = {2014},
   pages     = {},
   volume    = {},
   editor    = {},
   address   = {Montreal, Canada},
   month     = {December},
   publisher = {MIT Press},
   pdf       = {},
   url       = {},
   eprint    = {1411.6406},
   note      = {},
   venue     = {NIPS},
}

@article{MKL2014,
    author = {Yanting Lu and Liantao Wang and Jianfeng Lu and Jingyu Yang and Chunhua Shen},
    title  = {Multiple kernel clustering based on centered kernel alignment},
    journal= {Pattern Recognition},
    volume = {47},
    number = {11},
    year   = {2014},
    url    = {},
    month  = {},
    pages  = {3656--3664},
    eprint = {},
    venue  = {PR},
    note   = {},
}

@article{Paul2014TIPb,
    author = {Sakrapee Paisitkriangkrai  and  Chunhua Shen  and Anton {van den Hengel}},
    title  = {Large-margin Learning of Compact Binary Image Encodings},
    journal= {IEEE Transactions on Image Processing},
    volume = {23},
    number = {9},
    year   = {2014},
    url    = {},
    month  = {},
    pages  = {4041--4054},
    eprint = {1402.6383},
    venue  = {TIP},
    note   = {},
}

@inproceedings{ECCV14Lin,
    author      = {Guosheng Lin and Chunhua Shen and Jianxin Wu},
    title       = {Optimizing Ranking Measures for Compact Binary Code Learning},
    year        = {2014},
    month       = {},
    booktitle   = {European Conference on Computer Vision (ECCV'14)},
    address     = {Zurich},
    venue       = {ECCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1407.1151},
    url         = {},
    pdf         = {},
    project     = {https://bitbucket.org/guosheng/structhash},
}

@inproceedings{ECCV14Paul,
    author      = {Sakrapee Paisitkriangkrai and Chunhua Shen and Anton {van den Hengel}},
    title       = {Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features},
    year        = {2014},
    month       = {},
    booktitle   = {European Conference on Computer Vision (ECCV'14)},
    address     = {Zurich},
    venue       = {ECCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1407.0786},
    url         = {},
    pdf         = {},
    project     = {https://github.com/chhshen/pedestrian-detection},
}

@article{Yan2014TIPa,
    author = {Yan Yan and Chunhua Shen and Hanzi Wang},
    title  = {Efficient Semidefinite Spectral Clustering via {L}agrange Duality},
    journal= {IEEE Transactions on Image Processing},
    volume = {23},
    number = {8},
    year   = {2014},
    url    = {},
    month  = {},
    pages  = {3522--3534},
    eprint = {1402.5497},
    venue  = {TIP},
    note   = {},
}

@inproceedings{CVPR14Lin,
    author      = {Guosheng Lin and Chunhua Shen and Qinfeng Shi and Anton {van den Hengel} and David Suter},
    title       = {Fast Supervised Hashing with Decision Trees for High-Dimensional Data},
    year        = {2014},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'14)},
    address     = {Columbus, Ohio, USA},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1404.1561},
    url         = {https://bitbucket.org/chhshen/fasthash/src},
    pdf         = {},
    project     = {https://bitbucket.org/chhshen/fasthash/},
    abstract    = {
            Supervised hashing aims to map the original features to compact
                binary codes that are able to preserve label based similarity
                in the Hamming space. Non-linear hash functions have
                demonstrated the advantage over linear ones due to their
                powerful generalization capability. In the literature, kernel
                functions are typically used to achieve non-linearity in
                hashing, which achieve encouraging retrieval perfor- mance at
                the price of slow evaluation and training time. Here we propose
                to use boosted decision trees for achieving non-linearity in
                hashing, which are fast to train and evaluate, hence more
                suitable for hashing with high dimensional data. In our
                approach, we first propose sub-modular formulations for the
                hashing binary code inference problem and an efficient GraphCut
                based block search method for solving large-scale inference.
                Then we learn hash func- tions by training boosted decision
                trees to fit the binary codes. Experiments demonstrate that our
                proposed method significantly outperforms most state-of-the-art
                methods in retrieval precision and training time. Especially
                for high- dimensional data, our method is orders of magnitude
                faster than many methods in terms of training time.
    },
}

@article{Shen2014Outlier,
    author = {Fumin Shen and Chunhua Shen  and Rhys Hill  and
                Anton {van den Hengel} and Zhenmin Tang},
    title  = {Fast approximate $L_\infty$ minimization: {S}peeding up robust regression},
    journal= {Computational Statistics and Data Analysis},
    volume = {77},
    number = {},
    year   = {2014},
    month  = {September},
    pages  = {25--37},
    eprint = {1304.1250},
    venue  = {CSDA},
    note   = {},
    abstract={
    Minimization of the $L_\infty$ norm, which can be viewed as approximately
    solving the non-convex least median estimation problem, is a powerful
    method for outlier removal and hence robust regression. However, current
    techniques for solving the problem at the heart of $L_\infty$  norm minimization are
    slow, and therefore cannot scale to large problems. A new method for the
    minimization of the $L_\infty$ norm is presented here, which provides a speedup of
    multiple orders of magnitude for data with high dimension. This method,
    termed Fast $L_\infty$  Minimization, allows robust regression to be applied to a class
    of problems which were previously inaccessible. It is shown how the $L_\infty$ norm
    minimization problem can be broken up into smaller sub-problems, which can
    then be solved extremely efficiently. Experimental results demonstrate the
    radical reduction in computation time, along with robustness against large
    numbers of outliers in a few model-fitting problems.
    },
}

@article{Shen2014SBoosting,
    author = {Chunhua Shen  and  Guosheng Lin  and  Anton {van den Hengel}},
    title  = {{StructBoost}: {B}oosting Methods for Predicting Structured Output Variables},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {36},
    number = {10},
    year   = {2014},
    url    = {http://dx.doi.org/10.1109/TPAMI.2014.2315792},
    month  = {October},
    pages  = {2089--2103},
    eprint = {1302.3283},
    venue  = {TPAMI},
    note   = {},
    pdf    = {http://goo.gl/goCVLK},
    abstract={
Boosting is a method for learning a single accurate predictor by linearly
    combining a set of less accurate weak learners. Recently, structured
    learning has found many applications in computer vision. Thus far it has
    not been clear how one can train a boosting model that is directly
    optimized for predicting multivariate or structured outputs. To bridge this
    gap, inspired by structured support vector machines (SSVM), here we propose
    a boosting algorithm for structured output prediction, which we refer to as
    StructBoost. StructBoost supports nonlinear structured learning by
    combining a set of weak structured learners. As SSVM generalizes SVM, our
    StructBoost generalizes standard boosting approaches such as AdaBoost, or
    LPBoost to structured learning. The resulting optimization problem of
    StructBoost is more challenging than SSVM in the sense that it may involve
    exponentially many variables and constraints. In contrast, for SSVM one
    usually has an exponential number of constraints and a cutting-plane method
    is used. In order to efficiently solve StructBoost, we formulate an
    equivalent 1-slack formulation and solve it using a combination of cutting
    planes and column generation. We show the versatility and usefulness of
    StructBoost on a range of problems such as optimizing the tree loss for
    hierarchical multi-class classification, optimizing the Pascal overlap
    criterion for robust visual tracking and learning conditional random field
    parameters for image segmentation.
},
}

@article{Liu2014MKL,
    author = {Fayao Liu  and  Luping Zhou  and  Chunhua Shen  and  Jianping Yin},
    title  = {Multiple Kernel Learning in the Primal for Multi-modal {A}lzheimer's Disease Classification},
    journal= {IEEE Journal of Biomedical and Health Informatics},
    volume = {},
    number = {},
    year   = {2014},
    month  = {},
    pages  = {},
    eprint = {1310.0890},
    url    = {http://dx.doi.org/10.1109/JBHI.2013.2285378},
    venue  = {JBHI},
    note   = {Online published at IEEE: 10 October 2013},
    abstract={
         To achieve effective and efficient detection of Alzheimer's disease
             (AD), many machine learning methods have been introduced into this
             realm. However, the general case of limited training samples, as
             well as different feature representations typically makes this
             problem challenging. In this work, we propose a novel multiple
             kernel learning framework to combine multi-modal features for AD
             classification, which is scalable and easy to implement. Contrary
             to the usual way of solving the problem in the dual space, we look
             at the optimization from a new perspective. By conducting Fourier
             transform on the Gaussian kernel, we explicitly compute the
             mapping function, which leads to a more straightforward solution
             of the problem in the primal space. Furthermore, we impose the
             mixed $L_{21}$ norm constraint on the kernel weights, known as the
             group lasso regularization, to enforce group sparsity among
             different feature modalities. This actually acts as a role of
             feature modality selection, while at the same time exploiting
             complementary information among different kernels. Therefore it is
             able to extract the most discriminative features for
             classification. Experiments on the ADNI data set demonstrate the
             effectiveness of the proposed method.
    },
}

@article{Li2014TIP,
    author = {Yao Li and Wenjing Jia and  Chunhua Shen and Anton {van den Hengel}},
    title  = {Characterness: {A}n Indicator of Text in the Wild},
    journal= {IEEE Transactions on Image Processing},
    volume = {23},
    number = {4},
    year   = {2014},
    month  = {},
    pages  = {1666--1677},
    eprint = {1309.6691},
    venue  = {TIP},
    url    = {http://dx.doi.org/10.1109/TIP.2014.2302896},
    project= {https://github.com/yaoliUoA/characterness},
    abstract={
            Text in an image provides vital information for interpreting its
            contents, and text in a scene can aide with a variety of tasks from
            navigation, to obstacle avoidance, and odometry. Despite its value,
            however, identifying general text in images remains a challenging
            research problem. Motivated by the need to consider the widely
            varying forms of natural text, we propose a bottom-up approach to
            the problem which reflects the 'characterness' of an image
            region.  In this sense our approach mirrors the move from saliency
            detection methods to measures of `objectness'. In order to measure
            the characterness we develop three novel cues that are tailored for
            character detection, and a Bayesian method for their integration.
            Because text is made up of sets of characters, we then design a
            Markov random field (MRF) model so as to exploit the inherent
            dependencies between characters.  We experimentally demonstrate the
            effectiveness of our characterness cues as well as the advantage of
            Bayesian multi-cue integration. The proposed text detector
            outperforms state-of-the-art methods on a few benchmark scene text
            detection datasets. We also show that our measurement of
            'characterness' is superior than state-of-the-art saliency
            detection models when applied to the same task.
            },
}

@inproceedings{ICCV13Lin,
    author      = {Guosheng Lin and Chunhua Shen and David Suter and Anton {van den Hengel}},
    title       = {A General Two-step Approach to Learning-Based Hashing},
    year        = {2013},
    month       = {December},
    booktitle   = {IEEE International Conference on Computer Vision (ICCV'13)},
    address     = {Sydney, Australia},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1309.1853},
    url         = {},
    pdf         = {},
    project     = {https://bitbucket.org/guosheng/two-step-hashing/},
    abstract    = {
            Most existing approaches to hashing apply a single form of
            hash function, and an optimization process which is typically deeply
            coupled to this specific form. This tight coupling restricts the
            flexibility of the method to respond to the data, and can result in
            complex optimization problems that are difficult to solve. Here we
            propose a flexible yet simple framework that is able to accommodate
            different types of loss functions and hash functions. This
            framework allows a number of existing approaches to hashing to be
            placed in context, and simplifies the development of new
            problem-specific hashing methods. Our framework decomposes hashing
            learning problem into two steps: hash bit learning and hash
            function learning based on the learned bits. The first step can
            typically be formulated as binary quadratic problems, and the
            second step can be accomplished by training standard binary
            classifiers. Both problems have been extensively studied in the
            literature.
    },
}

@inproceedings{ICCV13Pai,
    author      = {Sakrapee Paisitkriangkrai and Chunhua Shen and Anton {van den Hengel}},
    title       = {Efficient pedestrian detection by directly optimizing the partial area under the {ROC} curve},
    year        = {2013},
    month       = {December},
    booktitle   = {IEEE International  Conference on Computer Vision (ICCV'13)},
    address     = {Sydney, Australia},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1310.0900},
    url         = {},
    pdf         = {http://hdl.handle.net/2440/83158},
    project     = {},
    abstract    = {Many typical applications of object detection operate
 within a prescribed false-positive range. In this situation
 the performance of a detector should be assessed on the basis
 of the area under the ROC curve over that range, rather
 than over the full curve, as the performance outside the
 range is irrelevant. This measure is labelled as the partial
 area under the ROC curve (pAUC). Effective cascade-based
 classification, for example, depends on training node classifiers
 that achieve the maximal detection rate at a moderate
 false positive rate, e.g., around 40% to 50%. We propose
 a novel ensemble learning method which achieves a maximal
 detection rate at a user-defined range of false positive
 rates by directly optimizing the partial AUC using structured
 learning. By optimizing for different ranges of false
 positive rates, the proposed method can be used to train
 either a single strong classifier or a node classifier forming
 part of a cascade classifier. Experimental results on both
 synthetic and real-world data sets demonstrate the effectiveness
 of our approach, and we show that it is possible
 to train state-of-the-art pedestrian detectors using the
 proposed structured ensemble learning method.},
}

@inproceedings{ICCV13Li,
    author      = {Xi Li and Yao Li and Chunhua Shen and Anthony Dick and Anton {van den Hengel}},
    title       = {Contextual Hypergraph Modeling for Salient Object Detection},
    year        = {2013},
    month       = {December},
    booktitle   = {IEEE International  Conference on Computer Vision (ICCV'13)},
    address     = {Sydney, Australia},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1310.5767},
    url         = {},
    pdf         = {},
    project     = {https://bitbucket.org/chhshen/saliency-detection},
    abstract    = {Salient object detection aims to locate objects that
        capture human attention within images.
    Previous approaches often pose this as a problem of image contrast analysis.
    In this work, we model an image as a hypergraph that
    utilizes a set of hyperedges to capture the contextual
    properties of image pixels or regions. As a result,
    the problem of salient object detection becomes one of finding salient
    vertices and hyperedges in the hypergraph.
    The main advantage of hypergraph modeling is that it takes into
    account each pixel's (or region's) affinity with its neighborhood
    as well as its separation from image background.
    Furthermore, we propose an alternative approach based on
    center-versus-surround contextual contrast analysis,
    which performs salient object detection by optimizing a cost-sensitive
    support vector machine (SVM) objective function.
    Experimental results on four challenging datasets demonstrate the
    effectiveness of the proposed approaches against the state-of-the-art
    approaches to salient object detection.},
}

@inproceedings{ICCV2013Harandi,
    author      = {Mehrtash {Harandi} and Conrad {Sanderson} and Chunhua Shen and Brian Lovell},
    title       = {Dictionary Learning and Sparse Coding on {G}rassmann Manifolds: An Extrinsic Solution},
    year        = {2013},
    month       = {December},
    booktitle   = {IEEE International  Conference on Computer Vision (ICCV'13)},
    address     = {Sydney, Australia},
    venue       = {ICCV},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1310.4891},
    url         = {},
    pdf         = {},
    project     = {https://github.com/chhshen/Grassmann/},
    abstract    = {
 Recent advances in computer vision and machine learning
 suggest that a wide range of problems can be addressed
 more appropriately by considering non-Euclidean geometry.
 In this paper we explore sparse dictionary learning
 over the space of linear subspaces, which form Riemannian
 structures known as Grassmann manifolds. To this end, we
 propose to embed Grassmann manifolds into the space of
 symmetric matrices by an isometric mapping, which enables
 us to devise a closed-form solution for updating a
 Grassmann dictionary, atom by atom. Furthermore, to handle
 non-linearity in data, we propose a kernelised version
 of the dictionary learning algorithm.}
}

@article{Shen2014Metric,
    author = {Chunhua Shen and Junae Kim and Fayao Liu and Lei Wang and Anton {van den Hengel}},
    title  = {Efficient Dual Approach to Distance Metric Learning},
    journal= {IEEE Transactions on Neural Networks and Learning Systems},
    volume = {25},
    number = {2},
    year   = {2014},
    month  = {},
    pages  = {394--406},
    eprint = {1302.3219},
    venue  = {TNN},
    note   = {},
    abstract= {
    Distance metric learning is of fundamental interest in machine learning
        because the distance metric employed can significantly affect the
        performance of many learning methods. Quadratic Mahalanobis metric
        learning is a popular approach to the problem, but typically requires
        solving a semidefinite programming (SDP) problem, which is
        computationally expensive. Standard interior-point SDP solvers
        typically have a complexity of O(D^6.5) (with D the dimension of input
                data), and can thus only practically solve problems exhibiting
        less than a few thousand variables. Since the number of variables is
        D(D+1)/2, this implies a limit upon the size of problem that can
        practically be solved of around a few hundred dimensions. The
        complexity of the popular quadratic Mahalanobis metric learning
        approach thus limits the size of problem to which metric learning can
        be applied. Here we propose a significantly more efficient approach to
        the metric learning problem based on the Lagrange dual formulation of
        the problem. The proposed formulation is much simpler to implement, and
        therefore allows much larger Mahalanobis metric learning problems to be
        solved. The time complexity of the proposed method is O(D^3), which is
        significantly lower than that of the SDP approach. Experiments on a
        variety of datasets demonstrate that the proposed method achieves an
        accuracy comparable to the state-of-the-art, but is applicable to
        significantly larger problems. We also show that the proposed method
        can be applied to solve more general Frobenius-norm regularized SDP
        problems approximately.
    },
}

@article{Wang2014PAMI,
    author = {Lei Wang and Luping Zhou and Chunhua Shen and Lingqiao Liu and Huan Liu},
    title  = {A Hierarchical Word-merging Algorithm with Class Separability Measure},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {36},
    number = {3},
    year   = {2014},
    month  = {March},
    pdf    = {https://bitbucket.org/chhshen/chhshen.bitbucket.org/src/be12d4ef8deb6207ec97f0fdac6efbe2df151b59/_download/TPAMI14Wang.pdf},
    pages  = {417--435},
    eprint = {},
    venue  = {TPAMI},
    note   = {},
    abstract = {In image recognition with the bag-of-features model, a small-sized visual
    codebook is usually preferred to obtain a low- dimensional histogram
    representation and high computational efficiency. Such a visual codebook
    has to be discriminative enough to achieve excellent recognition
    performance. To create a compact and discriminative codebook, in this paper
    we propose to merge the visual words in a large-sized initial codebook by
    maximally preserving class separability. We first show that this results in
    a difficult optimization problem. To deal with this situation, we devise a
    suboptimal but very efficient hierarchical word-merging algorithm, which
    optimally merges two words at each level of the hierarchy. By exploiting
    the characteristics of the class separability measure and designing a novel
    indexing structure, the proposed algorithm can hierarchically merge 10,000
    visual words down to two words in merely 90 seconds. Also, to show the
    properties of the proposed algorithm and reveal its advantages, we conduct
    detailed theoretical analysis to compare it with another hierarchical
    word-merging algorithm that maximally preserves mutual information,
obtaining interesting findings. Experimental studies are conducted to verify
    the effectiveness of the proposed algorithm on multiple benchmark data
    sets. As shown, it can efficiently produce more compact and discriminative
    codebooks than the state-of-the-art hierarchical word- merging algorithms,
especially when the size of the codebook is significantly reduced.
    },
}

@article{Paul2013Fastboosting,
    author = {Sakrapee Paisitkriangkrai and Chunhua Shen and Anton {van den Hengel}},
    title  = {A scalable stage-wise approach to large-margin multi-class loss based boosting},
    journal= {IEEE Transactions on Neural Networks and Learning Systems},
    volume = {25},
    number = {5},
    year   = {2014},
    month  = {},
    pages  = {1002--1013},
    eprint = {1307.5497},
    venue  = {TNN},
    pdf    = {https://bytebucket.org/chhshen/data/raw/7e2f958b104603e54e9d8376a8e1672363f742a3/papers/Paisitkriangkrai2014TNNLS.pdf},
    url    = {http://dx.doi.org/10.1109/TNNLS.2013.2282369},
    note   = {}
}


@article{Paul2013TMM,
    author = {Sakrapee Paisitkriangkrai and Chunhua Shen and Anton {van den Hengel}},
    title  = {Asymmetric pruning for learning cascade detectors},
    journal= {IEEE Transactions on Multimedia},
    volume = {16},
    number = {5},
    year   = {2014},
    month  = {},
    pages  = {1254--1267},
    url    = {http://dx.doi.org/10.1109/TMM.2014.2308723},
    eprint = {1303.6066},
    venue  = {TMM},
}

@article{Li2013Hyper,
    author = {Xi Li and Weiming Hu and  Chunhua Shen and Anthony Dick and Zhongfei Zhang},
    title  = {Context-aware hypergraph construction for robust spectral clustering},
    journal= {IEEE Transactions on Knowledge and Data Engineering},
    volume = {26},
    number = {10},
    year   = {2014},
    month  = {},
    pages  = {2588--2597},
    eprint = {1401.0764},
    pdf    = {},
    url    = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2013.126},
    note   = {},
    venue  = {TKDE},
    project = {},
}


@article{Paisitkriangkrai2013RandomBoost,
    author = {Sakrapee Paisitkriangkrai and  Chunhua Shen and Qinfeng Shi and Anton {van den Hengel}},
    title  = {{RandomBoost}: {S}implified Multi-class Boosting through Randomization},
    journal= {IEEE Transactions on Neural Networks and Learning Systems},
    volume = {25},
    number = {4},
    year   = {2014},
    month  = {},
    pages  = {764--779},
    eprint = {1302.0963},
    pdf    = {},
    url    = {http://dx.doi.org/10.1109/TNNLS.2013.2281214},
    note   = {},
    venue  = {TNN},
    project = {},
}




@inproceedings{ICIP13aShen,
    author      = {Guosheng Lin and Chunhua Shen and  Anton {van den Hengel}},
    title       = {Approximate constraint generation for efficient structured boosting},
    year        = {2013},
    month       = {},
    booktitle   = {IEEE Conference on Image Processing (ICIP'13)},
    address     = {Melbourne, Australia},
    venue       = {ICIP},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {},
    project     = {}
}

@inproceedings{ICIP13bShen,
    author      = {Yao Li and Chunhua Shen and Wenjing Jia and Anton {van den Hengel}},
    title       = {Leveraging surrounding context for scene text detection},
    year        = {2013},
    month       = {},
    booktitle   = {IEEE Conference on Image Processing (ICIP'13)},
    address     = {Melbourne, Australia},
    venue       = {ICIP},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {},
    project     = {}
}

@inproceedings{ICIP13cShen,
    author      = {Chao Zhang and John Bastian and Chunhua Shen and
        Anton {van den Hengel} and Tingzhi Shen},
    title       = {Extended depth-of-field via focus stacking and graph cuts},
    year        = {2013},
    month       = {},
    booktitle   = {IEEE Conference on Image Processing (ICIP'13)},
    address     = {Melbourne, Australia},
    venue       = {ICIP},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {https://sites.google.com/site/chhshen/Home/ICIP2013.pdf},
    project     = {}
}


@inproceedings{CVPR13aShen,
    author      = {Fumin Shen and Chunhua Shen and Qinfeng Shi and Anton {van den Hengel} and Zhenmin Tang},
    title       = {Inductive Hashing on Manifolds},
    year        = {2013},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13)},
    address     = {Oregon, USA},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1303.7043},
    url         = {},
    pdf         = {},
    project     = {https://github.com/chhshen/Hashing-on-Nonlinear-Manifolds},
}


@inproceedings{CVPR13bLi,
    author      = {Xi Li and Chunhua Shen and Anthony Dick and Anton {van den Hengel}},
    title       = {Learning Compact Binary Codes for Visual Tracking},
    year        = {2013},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13)},
    address     = {Oregon, USA},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {http://hdl.handle.net/2440/77412},
    pdf         = {http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Li_Learning_Compact_Binary_2013_CVPR_paper.pdf},
}

@inproceedings{CVPR13cWang,
    author      = {Zhenhua Wang and Qinfeng Shi and Chunhua Shen  and Anton {van den Hengel}},
    title       = {Bilinear Programming for Human Activity Recognition with unknown {MRF} graphs},
    year        = {2013},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13)},
    address     = {Oregon, USA},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {http://hdl.handle.net/2440/77411},
    pdf         = {http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Wang_Bilinear_Programming_for_2013_CVPR_paper.pdf},
}

@inproceedings{CVPR13dWang,
    author      = {Peng Wang and Chunhua Shen  and Anton {van den Hengel}},
    title       = {A Fast Semidefinite Approach to Solving Binary Quadratic Problems},
    year        = {2013},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13)},
    address     = {Oregon, USA},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {Oral presentation, 60 out of 1870 submissions.},
    eprint      = {1304.0840},
    url         = {},
    pdf         = {},
    project     = {./projects/BQP/}
}

@inproceedings{CVPR13eYao,
    author      = {Rui Yao and  Qinfeng Shi and Chunhua Shen  and Yanning Zhang and Anton {van den Hengel} },
    title       = {Part-based Visual Tracking with Online Latent Structural Learning},
    year        = {2013},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13)},
    address     = {Oregon, USA},
    venue       = {CVPR},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    project     = {https://github.com/chhshen/PartTracking},
    url         = {http://hdl.handle.net/2440/77413},
    pdf         = {http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Yao_Part-Based_Visual_Tracking_2013_CVPR_paper.pdf},
}


@article{Shen2013NN,
    author = {Chunhua Shen and Hanxi Li and Anton {van den Hengel}},
    title  = {Fully Corrective Boosting with Arbitrary Loss and Regularization},
    journal= {Neural Networks},
    volume = {48},
    number = {},
    year   = {2013},
    month  = {December},
    pages  = {44--58},
    eprint = {},
    pdf    = {http://hdl.handle.net/2440/78929},
    venue  = {NN},
    note   = {},
}

@article{Xi2013Survey,
    author = {Xi Li and Weiming Hu and Chunhua Shen and Zhongfei Zhang and Anthony Dick and Anton {van den Hengel}},
    title  = {A Survey of Appearance Models in Visual Object Tracking},
    journal= {ACM Transactions on Intelligent Systems and Technology},
    volume = {4},
    number = {4},
    year   = {2013},
    month  = {},
    pages  = {},
    eprint = {1303.4803},
    url    = {},
    venue  = {TIST},
}

@article{Xi2013TIP,
    author = {Xi Li and Anthony Dick and Chunhua Shen and Zhongfei
        Zhang and Anton {van den Hengel} and Hanzi Wang},
    title  = {Visual Tracking with Spatio-Temporal {Dempster-Shafer} Information Fusion},
    journal= {IEEE Transactions on Image Processing},
    volume = {22},
    number = {8},
    year   = {2013},
    month  = {},
    pages  = {3028--3040},
    eprint = {},
    pdf    = {http://hdl.handle.net/2440/77448},
    venue  = {TIP},
    note   = {},
}

@inproceedings{ICML13a,
    author      = {Xi Li and Guosheng Lin and Chunhua Shen and Anton
        {van den Hengel} and Anthony Dick},
    title       = {Learning Hash Functions Using Column Generation},
    year        = {2013},
    month       = {},
    booktitle   = {International Conference on Machine Learning (ICML'13)},
    address     = {Atlanta, USA},
    venue       = {ICML},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {Oral presentation},
    eprint      = {1303.0339},
    url         = {},
    project     = {https://bitbucket.org/guosheng/column-generation-hashing/},
    pdf         = {http://jmlr.csail.mit.edu/proceedings/papers/v28/li13a.pdf}
}

@article{FisherBoost2013IJCV,
    author = {Chunhua Shen and Peng Wang and  Sakrapee Paisitkriangkrai  and Anton {van den Hengel}},
    title  = {Training Effective Node Classifiers for Cascade Classification},
    journal= {International Journal of Computer Vision},
    volume = {103},
    number = {3},
    year   = {2013},
    month  = {July},
    pages  = {326--347},
    eprint = {1301.2032},
    pdf    = {https://sites.google.com/site/chhshen/publication/IJCV2013.pdf},
    url    = {http://link.springer.com/article/10.1007%2Fs11263-013-0608-1},
    venue  = {IJCV},
    project= {./projects/fisherboost/},
    note   = {},
}

@article{LMS2013TIP,
    author = {Fumin Shen and Chunhua Shen  and Anton {van den Hengel} and Zhenmin Tang},
    title  = {Approximate Least Trimmed Sum of Squares Fitting and Applications in Image Analysis},
    journal= {IEEE Transactions on Image Processing},
    volume = {22},
    number = {5},
    year   = {2013},
    month  = {May},
    pages  = {1836--1847},
    eprint = {},
    pdf    = {http://hdl.handle.net/2440/79428},
    url    = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6408142},
    venue  = {TIP},
    note   = {},
}

@article{TMM2013Shape,
    author = {Lei Luo and Chunhua Shen and Chunyuan Zhang  and Anton {van den Hengel}},
    title  = {Shape Similarity Analysis by Self-Tuning Locally Constrained Mixed-Diffusion},
    journal= {IEEE Transactions on Multimedia},
    volume = {15},
    number = {5},
    year   = {2013},
    month  = {August},
    pages  = {1174--1183},
    eprint = {},
    pdf    = {http://hdl.handle.net/2440/73304},
    venue  = {TMM},
    note   = {},
}

@article{TIP2014Shortcut,
    author = {Lei Luo and Chunhua Shen and  Xinwang Liu and  Chunyuan Zhang},
    title  = {A Computational Model of the Short-Cut Rule for {2D} Shape Decomposition},
    journal= {IEEE Transactions on Image Processing},
    volume = {24},
    number = {1},
    year   = {2015},
    month  = {},
    pages  = {},
    eprint = {1409.2104},
    pdf    = {},
    venue  = {TIP},
    note   = {},
}

@article{TPAMI2013Xi,
    author = {Xi Li and Anthony Dick and Chunhua Shen and Anton {van den Hengel} and Hanzi Wang},
    title  = {Incremental Learning of {3D-DCT} Compact Representations for Robust Visual Tracking},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {35},
    number = {4},
    year   = {2013},
    month  = {April},
    pages  = {863--881},
    eprint = {1207.3389},
    pdf    = {https://sites.google.com/site/chhshen/publication/tpami12xi.pdf?attredirects=1},
    url    = {http://dx.doi.org/10.1109/TPAMI.2012.166},
    venue  = {TPAMI},
    project = {https://github.com/chhshen/DCT-Tracking/},
}


@inproceedings{ACCV12,
    author      = {Guosheng Lin and Chunhua Shen and  Anton {van den Hengel} and David Suter},
    title       = {Fast Training of Effective Multi-class Boosting Using Coordinate Descent Optimization},
    year        = {2012},
    month       = {},
    booktitle   = {Asian Conference on Computer Vision (ACCV'12)},
    address     = {},
    venue       = {ACCV},
    pages       = {782--795},
    volume      = {7725},
    publisher   = {LNCS, Springer},
    note        = {},
    eprint      = {1311.5947},
    url         = {},
    pdf         = {}
}

@inproceedings{ECCV12,
    author      = {Rui Yao and Qinfeng Shi and Chunhua Shen and Yanning Zhang and Anton {van den Hengel} },
    title       = {Robust Tracking with Weighted Online Structured Learning},
    year        = {2012},
    month       = {},
    booktitle   = {European Conference on Computer Vision (ECCV'12)},
    address     = {},
    venue       = {ECCV},
    pages       = {158--172},
    volume      = {7574},
    publisher   = {LNCS, Springer},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {https://sites.google.com/site/chhshen/publication/weighted_tracking_eccv12.pdf?attredirects=1}
}

@inproceedings{ICML12,
    author      = {Qinfeng Shi and  Chunhua Shen and Rhys Hill and Anton van den Hengel},
    title       = {Is margin preserved after random projection?},
    year        = {2012},
    month       = {},
    booktitle   = {International  Conference on Machine Learning (ICML'12)},
    address     = {},
    venue       = {ICML},
    pages       = {},
    volume      = {},
    publisher   = {},
    note        = {This work provides an analysis of margin distortion
                   under random projections, the conditions under which margins
                   are preserved, and presents bounds on the margin
                   distortion.},
    eprint      = {1206.4651},
    url         = {http://hdl.handle.net/2440/71063},
}

@inproceedings{CVPR12a,
    author      = {Xi Li and  Chunhua Shen and Qinfeng Shi and Anthony Dick and Anton {van den Hengel}},
    title       = {Non-sparse Linear Representations for Visual Tracking with Online Reservoir Metric Learning},
    year        = {2012},
    month       = {},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'12)},
    address     = {},
    venue       = {CVPR},
    pages       = {1760--1767},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {1204.2912},
    pdf         = {http://hdl.handle.net/2440/70244},
}

@inproceedings{CVPR12b,
    author      = {Sakrapee Paisitkriangkrai and Chunhua Shen  and Anton {van den Hengel}},
    title       = {Sharing Features in Multi-class Boosting via Group Sparsity},
    year        = {2012},
    month       = {},
    booktitle   = {IEEE  Conference on Computer Vision and Pattern Recognition (CVPR'12)},
    address     = {},
    venue       = {CVPR},
    pages       = {2128--2135},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    pdf         = {http://hdl.handle.net/2440/69851},
}



@article{JMLR2012Shen,
    author = {Chunhua Shen and Junae Kim and Lei Wang and Anton {van den Hengel}},
    title  = {Positive Semidefinite Metric Learning Using Boosting-like Algorithms},
    journal= {Journal of Machine Learning Research},
    volume = {13},
    number = {},
    year   = {2012},
    month  = {},
    pages  = {1007--1036},
    eprint = {1104.4704},
    url    = {http://jmlr.csail.mit.edu/papers/v13/shen12a.html},
    venue  = {JMLR},
    project= {https://bitbucket.org/chhshen/data/raw/45d101372013763d18f0a7ed191c86569532ed96/code/BoostMetric-NIPS09-codes-V0.1.tar.bz2},
    note    = {Code is available at http://code.google.com/p/boosting/},
}



@article{UBoost2011Shen,
    author = {Chunhua Shen and Peng Wang and Fumin Shen and Hanzi Wang},
    title  = {{UBoost}: {B}oosting with the {U}niversum},
    journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume = {34},
    number = {4},
    year   = {2012},
    month  = {April},
    pages  = {825--832},
    eprint = {},
    pdf    = {http://hdl.handle.net/2440/67027},
    venue  = {TPAMI},
    abstract = {
    It has been shown that the Universum data, which do not belong to either
      class of the classification problem of interest, may contain useful prior
      domain knowledge for training a classifier. In this work, we
      design a novel boosting algorithm that takes advantage of the available
      Universum data, hence the name UBoost. UBoost is a boosting
      implementation of Vapnik’s alternative capacity concept to the large
      margin approach. In addition to the standard regularization term, UBoost
      also controls the learned model’s capacity by maximizing the number of
      observed contradictions. Our experiments demonstrate that UBoost can
      deliver improved classification accuracy over standard boosting
      algorithms that use labeled data alone.
    },
}


@inproceedings{DICTA2011b,
    author      = {Lei Wang and Chunhua Shen and Richard Hartley},
    title       = {On The Optimality of Sequential Forward Feature Selection Using Class Separability Measure},
    year        = {2011},
    month       = {December},
    booktitle   = {International Conference on Digital Image Computing: Techniques and Applications (DICTA'11)},
    address     = {Queensland, Australia},
    venue       = {DICTA},
    pages       = {203--208},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
}


@inproceedings{DICTA2011a,
    author      = {Tao Wang and Xuming He and Chunhua Shen and Nick Barnes},
    title       = {Laplacian margin distribution boosting for learning from sparsely labeled data},
    year        = {2011},
    month       = {December},
    booktitle   = {International Conference on Digital Image Computing: Techniques and Applications (DICTA'11)},
    address     = {Queensland, Australia},
    venue       = {DICTA},
    pages       = {209--216},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
}

@article{AsymBoost2011Wang,
    author = {Peng Wang and Chunhua Shen and Nick Barnes and Hong Zheng},
    title  = {Fast and Robust Object Detection Using Asymmetric Totally-corrective Boosting},
    journal= {IEEE Transactions on Neural Networks and Learning Systems},
    volume = {23},
    number = {1},
    year   = {2012},
    month  = {January},
    pages  = {33--46},
    eprint = {},
    pdf    = {http://hdl.handle.net/2440/66763},
    venue  = {TNN},
    note   = {},
}

@inproceedings{ICCV2011,
    author      = {Xi Li and Anthony Dick and Hanzi Wang and Chunhua Shen and Anton van den Hengel},
    title       = {Graph mode-based contextual kernels for robust {SVM} tracking},
    year        = {2011},
    month       = {},
    booktitle   = {IEEE International Conference on Computer Vision (ICCV'11)},
    address     = {},
    venue       = {ICCV},
    pages       = {1156--1163},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    pdf         = {http://goo.gl/GzpBVb},
}

@inproceedings{AAAI2011,
    author      = {Kyoungup Park and  Chunhua Shen and  Zhihui Hao and Junae Kim},
    title       = {Efficiently learning a distance metric for large margin nearest neighbor classification},
    year        = {2011},
    month       = {August},
    booktitle   = {National Conference on Artificial Intelligence (AAAI'11)},
    address     = {San Francisco, USA},
    venue       = {AAAI},
    pages       = {453--458},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
}

@inproceedings{Shen2011CVPRa,
    author      = {Chunhua Shen and Zhihui Hao},
    title       = {A direct formulation for totally-corrective multi-class boosting},
    year        = {2011},
    month       = {June},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11)},
    address     = {Colorado Springs, USA},
    venue       = {CVPR},
    pages       = {2585--2592},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    pdf         = {http://hdl.handle.net/2440/62919},
}

@inproceedings{Liu2011CVPR,
    author      = {Lingqiao Liu and Lei Wang and Chunhua Shen},
    title       = {A generalized probabilistic framework for compact codebook creation},
    year        = {2011},
    month       = {June},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11)},
    address     = {Colorado Springs, USA},
    venue       = {CVPR},
    pages       = {1537--1544},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    pdf         = {http://hdl.handle.net/2440/63014},
}

@inproceedings{Shi2011CVPR,
    author      = {Qinfeng Shi and Anders Eriksson and Anton van den Hengel and Chunhua Shen},
    title       = {Is face recognition really a Compressive Sensing problem?},
    year        = {2011},
    month       = {June},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11)},
    address     = {Colorado Springs, USA},
    venue       = {CVPR},
    pages       = {553--560},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    pdf         = {http://hdl.handle.net/2440/67036},
}


@inproceedings{Li2011CVPR,
    author      = {Hanxi Li and Chunhua Shen and Qinfeng Shi},
    title       = {Real-time visual tracking Using compressive sensing},
    year        = {2011},
    month       = {June},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11)},
    address     = {Colorado Springs, USA},
    venue       = {CVPR},
    pages       = {1305--1312},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {http://goo.gl/dsjsoM}
}

@inproceedings{Shen2011CVPRb,
    author      = {Chunhua Shen and Junae Kim and Lei Wang},
    title       = {A Scalable Dual Approach to Semidefinite Metric Learning},
    year        = {2011},
    month       = {June},
    booktitle   = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11)},
    address     = {Colorado Springs, USA},
    venue       = {CVPR},
    pages       = {2601--2608},
    volume      = {},
    publisher   = {},
    note        = {},
    eprint      = {},
    url         = {},
    pdf         = {http://goo.gl/UyVdEc},
}


@BOOK{DICTA2010,
    author    = {Jian Zhang and Chunhua Shen and Glen Geers and Qiang Wu},
    title     = {Proceedings of International Conference on Digital Image Computing: Techniques and Applications},
    publisher = {Editors, IEEE},
    year      = {2010},
    otherinfo = {Sydney, Australia},
    venue     = {book},
}


@BOOK{SDP2012,
    author      = {Chunhua Shen and Anton {van den Hengel}},
    title       = {Semidefinite programming (Book chapter in: Encyclopedia of Computer Vision, Springer)},
    year        = {2012},
    venue       = {book},
    note        = {},
}




@article{GSLDA2010Shen,
    author = {Chunhua Shen and Sakrapee Paisitkriangkrai and Jian Zhang},
    title  = {Efficiently Learning a Detection Cascade with Sparse Eigenvectors},
    journal= {IEEE Transactions on Image Processing},
    volume = {20},
    number = {1},
    year   = {2011},
    month  = {},
    pages  = {22--35},
    eprint = {0903.3103},
    url    = {http://dx.doi.org/10.1109/TIP.2010.2055880},
    venue  = {TIP},
    note   = {},
}


@article{Incremental2010Shen,
   author   = {Sakrapee Paisitkriangkrai and Chunhua Shen  and Jian Zhang},
   title    = {Incremental Training of a Detector Using Online Sparse Eigen-decomposition},
   journal  = {IEEE Transactions on Image Processing},
   volume   = {20},
   number   = {1},
   year     = {2011},
   month    = {},
   pages    = {213--226},
   publisher= {},
   eprint   = {1005.4118},
   venue    = {TIP},
   url      = {http://dx.doi.org/10.1109/TIP.2010.2053548},
}

@article{Scalable2010Shen,
   author   = {Chunhua Shen and Junae Kim and Lei Wang},
   title    = {Scalable Large-Margin {M}ahalanobis Distance Metric Learning},
   journal  = {IEEE Transactions on Neural Networks},
   volume   = {21},
   number   = {9},
   year     = {2010},
   month    = {September},
   pages    = {1524--1530},
   publisher= {},
   url      = {http://dx.doi.org/10.1109/TNN.2010.2052630},
   eprint   = {1003.0487},
   venue    = {TNN},
}


@inproceedings{Shen2010ECCV,
    author      = {Chunhua Shen and Peng Wang and Hanxi Li},
    title       = {{LACBoost} and {FisherBoost}: Optimally Building Cascade Classifiers},
    year        = {2010},
    month       = {September},
    booktitle   = {European Conference on Computer Vision (ECCV'10)},
    address     = {Crete Island, Greece},
    venue       = {ECCV},
    pages       = {608--621},
    volume      = {2},
    publisher   = {Lecture Notes in Computer Science (LNCS) 6312, Springer-Verlag},
    eprint      = {1005.4103},
    url         = {http://dx.doi.org/10.1007/978-3-642-15552-9_44},
}


@inproceedings{Shi2010CVPR,
   author    = {Qinfeng Shi and Hanxi Li and Chunhua Shen},
   title     = {Rapid face recognition using hashing},
   booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10)},
   year      = {2010},
   pages     = {2753--2760},
   volume    = {},
   address   = {San Francisco, CA},
   month     = {June},
   publisher = {IEEE Computer Society},
   pdf       = {http://sites.google.com/site/chhshen/publication/cvpr10.pdf?attredirects=1},
   eprint    = {},
   venue     = {CVPR},
}


@inproceedings{Shen2009PSD,
   author    = {Chunhua Shen and Junae Kim and Lei Wang and Anton {van den Hengel}},
   title     = {Positive semidefinite metric learning with Boosting},
   booktitle = {Advances in Neural Information Processing Systems (NIPS'09)},
   year      = {2009},
   pages     = {1651--1659},
   volume    = {},
   editor    = {Y. Bengio and D. Schuurmans and J. Lafferty and C. Williams and A. Culotta},
   address   = {Vancouver, B.C., Canada},
   month     = {December},
   publisher = {MIT Press},
   pdf       = {http://papers.nips.cc/paper/3658-positive-semidefinite-metric-learning-with-boosting.pdf},
   url       = {},
   eprint    = {0910.2279},
   project   = {https://bitbucket.org/chhshen/data/raw/45d101372013763d18f0a7ed191c86569532ed96/code/BoostMetric-NIPS09-codes-V0.1.tar.bz2},
   note      = {Code is available at http://code.google.com/p/boosting/},
   venue     = {NIPS},
}


@inproceedings{Paisitkriangkrai2009CVPR,
   author    = {Sakrapee Paisitkriangkrai and Chunhua Shen and Jian Zhang},
   title     = {Efficiently Training a Better Visual Detector with Sparse Eigenvectors},
   booktitle = {IEEE Conference on Computer Vision and Pattern
      Recognition (CVPR'09)},
   year      = {2009},
   pages     = {1129--1136},
   volume    = {},
   address   = {Miami, Florida},
   month     = {June},
   publisher = {IEEE Computer Society},
   eprint    = {0903.3103},
   url       = {http://sites.google.com/site/chhshen/publication/CVPR2009GSLDA.pdf?attredirects=1},
   venue     = {CVPR},
}


@inproceedings{Shen2008PSD,
   author    = {Chunhua Shen and Alan Welsh and Lei Wang},
   title     = {{PSDB}oost: Matrix-generation linear programming for positive semidefinite matrices learning},
   booktitle = {Advances in Neural Information Processing Systems (NIPS'08)},
   year      = {2008},
   pages     = {1473--1480},
   volume    = {},
   editor    = {D. Koller and D. Schuurmans and Y. Bengio and L. Bottou},
   address   = {Vancouver, B.C., Canada},
   month     = {December},
   publisher = {MIT Press},
   url       = {},
   pdf       = {http://papers.nips.cc/paper/3611-psdboost-matrix-generation-linear-programming-for-positive-semidefinite-matrices-learning.pdf},
   venue     = {NIPS}
}


@inproceedings{Fast2008Wang,
   author    = {Lei Wang and Luping Zhou and Chunhua Shen},
   title     = {A Fast Algorithm for Creating a Compact and Discriminative Visual Codebook},
   booktitle = {European Conference on Computer Vision (ECCV'08)},
   year      = {2008},
   pages     = {719--732},
   volume    = {4},
   address   = {Marseille, France},
   month     = {October},
   publisher = {Lecture Notes in Computer Science (LNCS) 5305, Springer-Verlag},
   url       = {http://dx.doi.org/10.1007/978-3-540-88693-8_53},
   venue     = {ECCV},
   pdf       = {http://sites.google.com/site/chhshen/publication/ECCV2008Wang.pdf?attredirects=1},
}


@inproceedings{Kernel2007Quang,
   author    = {Quang Nguyen and Antonio Robles-Kelly and Chunhua Shen},
   title     = {Kernel-based tracking from a probabilistic viewpoint},
   booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'07)},
   year      = {2007},
   pages     = {},
   volume    = {},
   address   = {Minneapolis, US},
   month     = {June},
   publisher = {IEEE Computer Society},
   pdf       = {http://goo.gl/1QNmaq},
   url       = {http://dx.doi.org/10.1109/CVPR.2007.383240},
   venue     = {CVPR},
}


@inproceedings{Shen2005Fast,
   author    = {Chunhua Shen and Michael J. Brooks and Anton {van den Hengel}},
   title     = {Fast global kernel density mode seeking with application to localisation and tracking},
   booktitle = {IEEE International Conference on Computer Vision (ICCV'05)},
   year      = {2005},
   pages     = {1516--1523},
   volume    = {2},
   address   = {Beijing, China},
   month     = {October},
   publisher = {IEEE Computer Society},
   pdf       = {http://goo.gl/UHzjWW},
   url       = {http://dx.doi.org/10.1109/ICCV.2005.94},
   venue     = {ICCV},
   note      = {Oral presentation, 45 out of 1200 submissions.},
}


@inproceedings{Zhou2010MICCAI,
   author    = {Luping Zhou and Lei Wang and Chunhua Shen and Nick Barnes},
   title     = {Hippocampal shape classification using redundancy constrained feature selection},
   booktitle = {International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'10)},
   year      = {2010},
   pages     = {266--273},
   volume    = {6362},
   address   = {Beijing, China},
   month     = {September},
   publisher = {LNCS, Springer},
   url       = {},
   eprint    = {},
   pdf       = {},
   note      = {},
   venue     = {MICCAI},
}


@inproceedings{Wang2010ACCV,
    author      = {Peng Wang and Chunhua Shen and Nick Barnes and Hong Zheng and Zhang Ren},
    title       = {Asymmetric Totally-corrective Boosting for Real-time Object Detection},
    year        = {2010},
    month       = {November},
    booktitle   = {Asian Conference on Computer Vision (ACCV'10)},
    address     = {New Zealand},
    venue       = {ACCV},
    pages       = {176--188},
    volume      = {6492},
    publisher   = {Lecture Notes in Computer Science (LNCS), Springer-Verlag},
    note        = {Oral presentation.},
    eprint      = {},
    url         = {},
}


@inproceedings{Zheng2010ACCV,
    author      = {Yongbin Zheng and Chunhua Shen and Richard Hartley and Xinsheng Huang},
    title       = {Pyramid Center-symmetric Local Binary, Trinary Patterns for Effective Pedestrian Detection},
    year        = {2010},
    month       = {November},
    booktitle   = {Asian Conference on Computer Vision (ACCV'10)},
    address     = {New Zealand},
    venue       = {ACCV},
    pages       = {281--292},
    volume      = {6495},
    publisher   = {Lecture Notes in Computer Science (LNCS), Springer-Verlag},
    note        = {},
    eprint      = {},
    pdf         = {http://goo.gl/5Cthse},
}



@inproceedings{Hao2010ACCV,
    author      = {Zhihui Hao and Chunhua Shen and Nick Barnes and Bo Wang},
    title       = {Totally-corrective Multi-class Boosting},
    year        = {2010},
    month       = {November},
    booktitle   = {Asian Conference on Computer Vision (ACCV'10)},
    address     = {New Zealand},
    venue       = {ACCV},
    pages       = {269-280},
    volume      = {6495},
    publisher   = {Lecture Notes in Computer Science (LNCS), Springer-Verlag},
    note        = {},
    eprint      = {},
    url         = {},
}

@inproceedings{Paul2010ACCV,
    author      = {Sakrapee Paisitkriangkrai and Chunhua Shen and Jian Zhang},
    title       = {Face Detection with Effective Feature Extraction},
    year        = {2010},
    month       = {November},
    booktitle   = {Asian Conference on Computer Vision (ACCV'10)},
    address     = {New Zealand},
    venue       = {ACCV},
    pages       = {460--470},
    volume      = {6494},
    publisher   = {Lecture Notes in Computer Science (LNCS), Springer-Verlag},
    note        = {},
    eprint      = {},
    url         = {},
}


@inproceedings{Face2010Li,
   author    = {Hanxi Li and Peng Wang and Chunhua Shen},
   title     = {Robust Face Recognition via Accurate Face Alignment and Sparse Representation},
   booktitle = {International Conference on on Digital Image Computing: Techniques and Applications (DICTA'10)},
   year      = {2010},
   pages     = {262--269},
   volume    = {},
   address   = {Sydney, Australia},
   month     = {December},
   publisher = {IEEE Press},
   url       = {},
   pdf       = {},
   venue     = {DICTA}
}


@inproceedings{Human2010,
   author    = {Weihong Wang and Jian Zhang and Chunhua Shen},
   title     = {Improved Human Detection and Classification in Thermal Images},
   booktitle = {IEEE International Conference on Image Processing (ICIP'10)},
   year      = {2010},
   pages     = {2313--2316},
   volume    = {},
   address   = {Hong Kong},
   month     = {October},
   publisher = {IEEE Press},
   url       = {},
   pdf       = {},
   venue     = {ICIP}
}



@inproceedings{Multiexit2010Wang,
   author    = {Peng Wang and Chunhua Shen and Hong Zheng and Zhang Ren},
   title     = {Training a multi-exit cascade with linear asymmetric classification for efficient object detection},
   booktitle = {IEEE International Conference on Image Processing (ICIP'10)},
   year      = {2010},
   pages     = {61--64},
   volume    = {},
   address   = {Hong Kong},
   month     = {October},
   publisher = {IEEE Press},
   url       = {},
   pdf       = {},
   venue     = {ICIP}
}


@article{Zhou2010FS,
    author  = {Luping Zhou  and Lei Wang and Chunhua Shen},
    title   = {Feature Selection With Redundancy-Constrained Class Separability},
    journal = {IEEE Transactions on Neural Networks},
    volume  = {21},
    year    = {2010},
    number  = {5},
    pages   = {853--858},
    pdf     = {},
    url     = {http://dx.doi.org/10.1109/TNN.2010.2044189},
    venue   = {TNN},
}

@article{MDBoost2010Shen,
   author   = {Chunhua Shen and Hanxi Li},
   title    = {Boosting through optimization of margin distributions},
   journal  = {IEEE Transactions on Neural Networks},
   volume   = {21},
   number   = {4},
   year     = {2010},
   month    = {April},
   pages    = {659--666},
   publisher= {},
   url      = {http://dx.doi.org/10.1109/TNN.2010.2040484},
   pdf      = {},
   eprint   = {0904.2037},
   venue    = {TNN},
   project  = {},
   note     = {},
}


@article{Dual2010Shen,
   author   = {Chunhua Shen and Hanxi Li},
   title    = {On the dual formulation of boosting algorithms},
   journal  = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
   volume   = {32},
   number   = {12},
   year     = {2010},
   month    = {},
   pages    = {2216--2231},
   publisher= {},
   url      = {http://dx.doi.org/10.1109/TPAMI.2010.47},
   eprint   = {0901.3590},
   venue    = {TPAMI},
}



@inproceedings{Dai2009DICTA,
   author    = {Yuchao Dai and Hongdong Li and Mingyi He and Chunhua Shen},
   title     = {Smooth Approximation of $L_\infty$-Norm for Multi-view Geometry},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'09)},
   year      = {2009},
   pages     = {339--346},
   volume    = {},
   address   = {Melbourne, Australia},
   month     = {December},
   publisher = {IEEE Press},
   url       = {},
   eprint    = {},
   pdf       = {},
   venue     = {DICTA},
   note      = {},
}


@inproceedings{Wang2009DICTA,
   author    = {Weihong Wang and Chunhua Shen and Jian Zhang and Sakrapee Paisitkriangkrai},
   title     = {A Two-Layer Night-time Vehicle Detector},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'09)},
   year      = {2009},
   pages     = {162--167},
   volume    = {},
   address   = {Melbourne, Australia},
   month     = {December},
   publisher = {IEEE Press},
   url       = {},
   eprint    = {},
   pdf       = {},
   venue     = {DICTA},
   note      = {},
}


@inproceedings{Wang2009ACCV,
   author    = {Peng Wang and Chunhua Shen and Hong Zheng and Zhang Ren},
   title     = {A Variant of the Trace Quotient Formulation for Dimensionality Reduction},
   booktitle = {9th Asian Conference on Computer Vision (ACCV'09)},
   year      = {2009},
   pages     = {277--286},
   volume    = {5996},
   address   = {Xi'an, China},
   month     = {September},
   publisher = {LNCS, Springer-Verlag},
   url       = {},
   eprint    = {},
   pdf       = {},
   venue     = {ACCV},
   note      = {},
}


@inproceedings{Kim2009ACCV,
   author    = {Junae Kim and Chunhua Shen and Lei Wang},
   title     = {A Scalable Algorithm for Learning a {M}ahalanobis Distance Metric},
   booktitle = {9th Asian Conference on Computer Vision (ACCV'09)},
   year      = {2009},
   pages     = {299--310},
   volume    = {5996},
   address   = {Xi'an, China},
   month     = {September},
   publisher = {LNCS, Springer-Verlag},
   url       = {},
   eprint     = {},
   pdf       = {},
   venue     = {ACCV},
   note      = {},
}



@article{Generalized2010Shen,
   author   = {Chunhua Shen and Junae Kim and Hanzi Wang},
   title    = {Generalized Kernel-based Visual Tracking},
   journal  = {IEEE Transactions on Circuits and Systems for Video Technology},
   volume   = {20},
   number   = {1},
   year     = {2010},
   month    = {January},
   pages    = {119--130},
   publisher= {},
   url      = {http://dx.doi.org/10.1109/TCSVT.2009.2031393},
   pdf      = {http://sites.google.com/site/chhshen/publication/TCSVT2010.pdf},
   eprint    = {0905.2463},
   venue    = {TCSVT},
   project  = {https://github.com/chhshen/KernelTracking},
}




@article{Li2010Interactive,
   author   = {Hongdong Li and Chunhua Shen},
   title    = {Interactive Color Image Segmentation with Linear Programming},
   journal  = {Machine Vision and Applications},
   volume   = {21},
   year     = {2010},
   month    = {June},
   number   = {4},
   pages    = {403--412},
   publisher= {Springer},
   url      = {http://www.springerlink.com/content/b254775776114226},
   pdf      = {http://sites.google.com/site/chhshen/publication/MVA2010LP.pdf},
   venue    = {MVA},
}





@inproceedings{Lu2008Human,
   author    = {Yifan Lu and Lei Wang and Richard Hartley and Hongdong Li and Chunhua Shen},
   title     = {Multi-view Human Motion Capture with An Improved Deformation Skin Model},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'08)},
   year      = {2008},
   pages     = {420--427},
   volume    = {},
   address   = {Canberra, Australia},
   month     = {December},
   publisher = {IEEE Computer Society},
   url       = {},
   venue     = {DICTA}
}


@inproceedings{Junae2008SVM,
   author    = {Junae Kim and Chunhua Shen and Lei Wang},
   title     = {Learning Cascaded Reduced-set {SVM}s Using Linear Programming},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'08)},
   year      = {2008},
   pages     = {619--626},
   volume    = {},
   address   = {Canberra, Australia},
   month     = {December},
   publisher = {IEEE Press},
   url       = {},
   pdf       = {},
   venue     = {DICTA},
}

@inproceedings{Li2008Boosting,
   author    = {Hanxi Li and Chunhua Shen},
   title     = {Boosting the minimum margin: {LPBoost} vs. {AdaBoost}},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'08)},
   year      = {2008},
   pages     = {533--539},
   volume    = {},
   address   = {Canberra, Australia},
   month     = {December},
   publisher = {IEEE Press},
   url       = {},
   pdf       = {},
   venue     = {DICTA}
}

@inproceedings{Shen2008Self,
   author    = {Chunhua Shen and Hongdong Li and Michael J. Brooks},
   title     = {Self-Calibrating Cameras Using Semidefinite Programming},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'08)},
   year      = {2008},
   pages     = {436--441},
   volume    = {},
   address   = {Canberra, Australia},
   month     = {December},
   publisher = {IEEE Press},
   url       = {http://dx.doi.org/10.1109/DICTA.2008.46},
   pdf       = {},
   venue     = {DICTA},
}


@article{Performance2008Paul,
   author   = {Sakrapee Paisitkriangkrai and Chunhua Shen and Jian Zhang},
   title    = {Performance Evaluation of Local Features in Human Classification and Detection},
   journal  = {IET Computer Vision},
   volume   = {2},
   number   = {4},
   year     = {2008},
   month    = {December},
   pages    = {236--246},
   publisher= {IET},
   url      = {http://dx.doi.org/10.1049/iet-cvi:20080026},
   pdf      = {http://sites.google.com/site/chhshen/publication/Huam2009IET.pdf},
   venue    = {IETCV},
   note     = {Invited submission, special issue of DICTA2007.}
}

@inproceedings{Realtime2008Paisitkriangkrai,
   author    = {Sakrapee Paisitkriangkrai and Chunhua Shen and Jian Zhang},
   title     = {Real-time Pedestrian Detection Using a Boosted Multi-layer Classifier},
   booktitle = {8th IEEE International Workshop on Visual
      Surveillance, in conjunction with European Conference on Computer Vision (ECCVW'08)},
   year      = {2008},
   pages     = {},
   volume    = {},
   address   = {Marseille, France},
   month     = {October},
   url       = {},
   pdf       = {},
   venue     = {workshop},
}




@article{Human2008Paul,
   author   = {Sakrapee Paisitkriangkrai and Chunhua Shen and Jian Zhang},
   title    = {Fast Pedestrian Detection Using a Cascade of Boosted Covariance Features},
   journal  = {IEEE Transactions on Circuits and Systems for Video Technology},
   volume   = {18},
   number   = {8},
   year     = {2008},
   month    = {August},
   pages    = {1140--1151},
   publisher= {},
   url      = {http://dx.doi.org/10.1109/TCSVT.2008.928213},
   pdf      = {http://goo.gl/lgpDJB},
   venue    = {TCSVT},
}


@inproceedings{Face2008Shen,
   author    = {Chunhua Shen and Sakrapee Paisitkriangkrai and Jian Zhang},
   title     = {Face Detection From Few Training Examples},
   booktitle = {IEEE International Conference on Image Processing (ICIP'08)},
   year      = {2008},
   pages     = {2764--2767},
   volume    = {},
   address   = {San Diego, California, USA},
   month     = {October},
   publisher = {IEEE Press},
   url       = {http://dx.doi.org/10.1109/ICIP.2008.4712367},
   pdf       = {},
   venue     = {ICIP}
}

@article{SDP2008Shen,
   author   = {Chunhua Shen and Hongdong Li and Michael J. Brooks},
   title    = {Supervised Dimensionality Reduction via Sequential
               Semidefinite Programming},
   journal  = {Pattern Recognition},
   volume   = {41},
   number   = {12},
   year     = {2008},
   month    = {December},
   pages    = {3644--3652},
   publisher= {Elsevier},
   url      = {http://dx.doi.org/10.1016/j.patcog.2008.06.015},
   pdf      = {http://sites.google.com/site/chhshen/publication/PR1.pdf},
   venue    = {PR},
}


@inproceedings{Color2007Li,
   author    = {Hongdong Li and Chunhua Shen and Zhiying Wen},
   title     = {Color image labelling using linear programming},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'07)},
   year      = {2007},
   pages     = {239--244},
   volume    = {},
   address   = {Adelaide, Australia},
   month     = {December},
   publisher = {IEEE Press},
   url       = {http://dx.doi.org/10.1109/DICTA.2007.4426802},
   pdf       = {},
   venue     = {DICTA}
}

@inproceedings{Experimental2007Paul,
   author    = {Sakrapee Paisitkriangkrai and Chunhua Shen and Jian Zhang},
   title     = {An Experimental Evaluation of Local Features for Pedestrian Classification},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'07)},
   year      = {2007},
   pages     = {53--60},
   volume    = {},
   address   = {Adelaide, Australia},
   month     = {December},
   publisher = {IEEE Press},
   postscript= {},
   pdf       = {},
   url       = {http://dx.doi.org/10.1109/DICTA.2007.4426775},
   note      = {Best Paper Award.},
   venue     = {DICTA},
}


@inproceedings{Feature2007Shen,
   author    = {Chunhua Shen and Hongdong Li and Michael J. Brooks},
   title     = {Feature extraction using sequential semidefinite programming},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'07)},
   year      = {2007},
   pages     = {430--437},
   volume    = {},
   address   = {Adelaide, Australia},
   month     = {December},
   pdf       = {},
   publisher = {IEEE Press},
   url       = {http://dx.doi.org/10.1109/DICTA.2007.4426829},
   venue     = {DICTA},
}


@inproceedings{Convex2007Shen,
   author    = {Chunhua Shen and Hongdong Li and Michael J. Brooks},
   title     = {A convex programming approach to the trace quotient problem},
   booktitle = {8th Asian Conference on Computer Vision (ACCV'07)},
   year      = {2007},
   pages     = {227--235},
   volume    = {2},
   address   = {Tokyo, Japan},
   month     = {November},
   publisher = {Lecture Notes in Computer Science (LNCS) 4844, Springer-Verlag},
   url       = {http://dx.doi.org/10.1007/978-3-540-76390-1_23},
   pdf       = {},
   venue     = {ACCV},
}

@inproceedings{Object2007Li,
   author    = {Hongdong Li and Chunhua Shen},
   title     = {Object-respecting colour image segmentation: An {LP} approach},
   booktitle = {IEEE International Conference on Image Processing (ICIP'07)},
   year      = {2007},
   pages     = {257--260},
   volume    = {2},
   address   = {San Antonio, Texas},
   month     = {September},
   publisher = {IEEE Press},
   pdf       = {},
   url       = {http://dx.doi.org/10.1109/ICIP.2007.4379141},
   venue     = {ICIP},
}

@article{Adaptive2007Wang,
   title   = {Adaptive object tracking based on an effective appearance filter},
   author  = {Hanzi Wang and David Suter and Konrad Schindler and Chunhua Shen},
   journal = {IEEE Transactions on Pattern Analysis and Machine
      Intelligence},
   volume  = {29},
   number  = {9},
   pages   = {1661--1667},
   year    = {2007},
   month   = {September},
   pdf     = {http://goo.gl/6rQTA1},
   url     = {http://dx.doi.org/10.1109/TPAMI.2007.1112},
   venue   = {TPAMI},
   note    = {Featured article of September issue 2007.},
}

@article{Fast2007Shen,
   author    = {Chunhua Shen and Michael J. Brooks and Anton {van den Hengel}},
   title     = {Fast global kernel density mode seeking: applications to localization and tracking},
   journal   = {IEEE Transactions on Image Processing},
   volume    = {16},
   number    = {5},
   year      = {2007},
   month     = {May},
   pages     = {1457--1469},
   pdf       = {http://sites.google.com/site/chhshen/publication/TIP2007Shen.pdf},
   url       = {http://dx.doi.org/10.1109/TIP.2007.894233},
   venue     = {TIP},
}

@inproceedings{Classification2006Shen,
   author    = {Chunhua Shen and Hongdong Li and Michael J. Brooks},
   title     = {Classification-based likelihood functions for {B}ayesian tracking},
   booktitle = {IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS'06)},
   year      = {2006},
   pages     = {33--38},
   volume    = {},
   address   = {Sydney, Australia},
   publisher = {IEEE Computer Society},
   month     = {November},
   url       = {http://dx.doi.org/10.1109/AVSS.2006.33},
   pdf       = {},
   venue     = {AVSS},
}

@inproceedings{LMI2006Li,
   author    = {Hongdong Li and Chunhua Shen},
   title     = {An {LMI} approach for reliable {PTZ} camera self-calibration},
   booktitle = {IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS'06)},
   year      = {2006},
   pages     = {79--84},
   volume    = {},
   address   = {Sydney, Australia},
   month     = {November},
   publisher = {IEEE Computer Society},
   url       = {http://dx.doi.org/10.1109/AVSS.2006.21},
   pdf       = {},
   venue     = {AVSS},
}

@inproceedings{Enhanced2006Nguyen,
   author    = {Quang Nguyen and Antonio Robles-Kelly and Chunhua Shen},
   title     = {Enhanced kernel-based tracking for monochromatic and thermographic video},
   booktitle = {IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS'06)},
   year      = {2006},
   pages     = {28--33},
   volume    = {},
   address   = {Sydney, Australia},
   publisher = {IEEE Computer Society},
   month     = {November},
   url       = {http://dx.doi.org/10.1109/AVSS.2006.47},
   pdf       = {},
   venue     = {AVSS},
}

@inproceedings{Shen2005Adaptive,
   author    = {Chunhua Shen and Michael J. Brooks},
   title     = {Adaptive over-relaxed mean shift},
   booktitle = {8th International Symposium on Signal Processing and Its Applications (ISSPA'05)},
   year      = {2005},
   pages     = {575--578},
   volume    = {2},
   address   = {Sydney, Australia},
   month     = {August},
   publisher = {IEEE Press},
   url       = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1581003},
   note      = {Errata: in figure 3 square marker and circle
                marker should be swapped.},
   pdf       = {},
   venue     = {ISSPA}
}


@inproceedings{Shen2005Visual,
   author    = {Chunhua Shen and Anton {van den Hengel} and Michael J. Brooks},
   title     = {Visual tracking via efficient kernel discriminant subspace learning},
   booktitle = {IEEE International Conference on Image Processing (ICIP'05)},
   year      = {2005},
   pages     = {590--593},
   volume    = {2},
   address   = {Genoa, Italy},
   publisher = {IEEE Press},
   month     = {September},
   url       = {http://dx.doi.org/10.1109/ICIP.2005.1530124},
   venue     = {ICIP},
}


@inproceedings{Shen2005Augmented,
   author    = {Chunhua Shen and Michael J. Brooks and Anton {van den Hengel}},
   title     = {Augmented particle filtering for efficient visual tracking},
   booktitle = {IEEE International Conference on Image Processing (ICIP'05)},
   year      = {2005},
   pages     = {856--859},
   volume    = {3},
   publisher = {IEEE Press},
   address   = {Genoa, Italy},
   month     = {September},
   url       = {http://dx.doi.org/10.1109/ICIP.2005.1530527},
   venue     = {ICIP},
}


@article{Lin2004Active,
   author    = {Zhibin Lin and Jing Lu and Chunhua Shen and Xiaojun Qiu and Boling Xu},
   title     = {Active control of radiation from a piston set in a rigid sphere},
   journal   = {Journal of  Acoustical Society of America},
   volume    = {115},
   number    = {6},
   year      = {2004},
   month     = {June},
   pages     = {2954--2963},
   pdf       = {http://goo.gl/nc4SjU},
   url       = {http://dx.doi.org/10.1121/1.1736654},
   venue     = {JASA},
}


@inproceedings{Shen2004Articulated,
   author    = {Chunhua Shen and Anton {van den Hengel} and Anthony Dick and Michael J. Brooks},
   title     = {{2D} articulated tracking with dynamic {B}ayesian networks},
   booktitle = {International Conference on Computer and Information Technology (CIT'04)},
   year      = {2004},
   pages     = {130--136},
   volume    = {},
   address   = {Wuhan, China},
   month     = {September},
   publisher = {IEEE Computer Society},
   url       = {http://dx.doi.org/10.1109/CIT.2004.1357185},
   venue     = {CIT},
}


@inproceedings{Shen2004Enhanced,
   author    = {Chunhua Shen and Anton {van den Hengel} and Anthony Dick and Michael J. Brooks},
   title     = {Enhanced importance sampling: unscented auxiliary particle filtering for visual tracking},
   booktitle = {Australian Joint Conference on Artificial Intelligence (AI'04)},
   year      = {2004},
   pages     = {180--191},
   volume    = {},
   address   = {Cairns, Australia},
   month     = {December},
   publisher = {Lecture Notes in Artificial Intelligence (LNAI) 3339, Springer-Verlag},
   url       = {http://digital.library.adelaide.edu.au/dspace/handle/2440/29538},
   venue     = {AI},
}


@article{Lu2003Lattice,
   author    = {Jing Lu and Chunhua Shen and Xiaojun Qiu and Boling Xu},
   title     = {Lattice form adaptive infinite impulse response filtering algorithm for active noise control},
   journal   = {Journal of Acoustical Society of America},
   volume    = {113},
   number    = {1},
   year      = {2003},
   month     = {January},
   pages     = {327--335},
   pdf       = {http://sites.google.com/site/chhshen/publication/Lattice2003JASA.pdf?attredirects=1},
   url       = {http://dx.doi.org/10.1121/1.1529665},
   venue     = {JASA},
}


@inproceedings{Shen2003Probabilistic,
   author    = {Chunhua Shen and Anton {van den Hengel} and Anthony Dick},
   title     = {Probabilistic multiple cue integration for particle filter based tracking},
   booktitle = {International Conference on Digital Image Computing - Techniques and Applications (DICTA'03)},
   year      = {2003},
   pages     = {309--408},
   volume    = {},
   address   = {Sydney, Australia},
   month     = {December},
   note      = {Nominated for Best Student Paper Award.},
   publisher = {CSIRO Publishing},
   pdf       = {http://sites.google.com/site/chhshen/publication/DICTA2003.pdf?attredirects=1},
   venue     = {DICTA}
}