Selected Publications

Google scholar (6379 citations).

Journal

  1. Structured learning of binary codes with column generation for optimizing ranking measures.
    cdot G. Lin, F. Liu, C. Shen, J. Wu, H. Shen.
    cdot International Journal of Computer Vision (IJCV), 2017.
    cdot arXivbibtexsearchproject webpage

  2. Exploring context with deep structured models for semantic segmentation.
    cdot G. Lin, C. Shen, A. van den Hengel, I. Reid.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
    cdot arXivbibtexsearch

  3. Cross-convolutional-layer pooling for image recognition.
    cdot L. Liu, C. Shen, A. van den Hengel.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
    cdot arXivbibtexsearch

  4. Compositional model based Fisher vector coding for image classification.
    cdot L. Liu, P. Wang, C. Shen, L. Wang, A. van den Hengel, C. Wang, H. Shen.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
    cdot arXivbibtexsearch

  5. FVQA: fact-based visual question answering.
    cdot P. Wang, Q. Wu, C. Shen, A. Dick, A. van den Hengel.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
    cdot arXivbibtexsearch

  6. Image captioning and visual question answering based on attributes and external knowledge.
    cdot Q. Wu, C. Shen, P. Wang, A. Dick, A. van den Hengel.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
    cdot arXivbibtexsearch

  7. Mining mid-level visual patterns with deep CNN activations.
    cdot Y. Li, L. Liu, C. Shen, A. van den Hengel.
    cdot International Journal of Computer Vision (IJCV), 2016.
    cdot arXivlinkbibtexsearchproject webpage

  8. Efficient semidefinite branch-and-cut for MAP-MRF inference.
    cdot P. Wang, C. Shen, A. van den Hengel, P. Torr.
    cdot International Journal of Computer Vision (IJCV), 2016.
    cdot arXivlinkbibtexsearch

  9. Unsupervised feature learning for dense correspondences across scenes.
    cdot C. Zhang, C. Shen, T. Shen.
    cdot International Journal of Computer Vision (IJCV), 2016.
    cdot arXivbibtexsearchproject webpage

  10. Online metric-weighted linear representations for robust visual tracking.
    cdot X. Li, C. Shen, A. Dick, Z. Zhang, Y. Zhuang.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.
    cdot arXivbibtexsearch

  11. Learning depth from single monocular images using deep convolutional neural fields.
    cdot F. Liu, C. Shen, G. Lin, I. Reid.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.
    cdot arXivlinkbibtexsearchproject webpage

  12. A generalized probabilistic framework for compact codebook creation.
    cdot L. Liu, L. Wang, C. Shen.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.
    cdot arXivlinkbibtexsearch

  13. Pedestrian detection with spatially pooled features and structured ensemble learning.
    cdot S. Paisitkriangkrai, C. Shen, A. van den Hengel.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.
    cdot arXivlinkbibtexsearchproject webpage

  14. Large-scale binary quadratic optimization using semidefinite relaxation and applications.
    cdot P. Wang, C. Shen, A. van den Hengel, P. Torr.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.
    cdot arXivlinkbibtexsearch

  15. Extrinsic methods for coding and dictionary learning on Grassmann manifolds.
    cdot M. Harandi, R. Hartley, C. Shen, B. Lovell, C. Sanderson.
    cdot International Journal of Computer Vision (IJCV), 2015.
    cdot arXivbibtexsearchproject webpage

  16. Supervised hashing using graph cuts and boosted decision trees.
    cdot G. Lin, C. Shen, A. van den Hengel.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.
    cdot arXivlinkbibtexsearchproject webpage

  17. StructBoost: Boosting methods for predicting structured output variables.
    cdot C. Shen, G. Lin, A. van den Hengel.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014.
    cdot arXivlinkpdfbibtexsearch

  18. A hierarchical word-merging algorithm with class separability measure.
    cdot L. Wang, L. Zhou, C. Shen, L. Liu, H. Liu.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014.
    cdot pdfbibtexsearch

  19. Training effective node classifiers for cascade classification.
    cdot C. Shen, P. Wang, S. Paisitkriangkrai, A. van den Hengel.
    cdot International Journal of Computer Vision (IJCV), 2013.
    cdot arXivlinkbibtexsearch

  20. Incremental learning of 3D-DCT compact representations for robust visual tracking.
    cdot X. Li, A. Dick, C. Shen, A. van den Hengel, H. Wang.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2013.
    cdot arXivlinkpdfbibtexsearchproject webpage

  21. Positive semidefinite metric learning using boosting-like algorithms.
    cdot C. Shen, J. Kim, L. Wang, A. van den Hengel.
    cdot Journal of Machine Learning Research (JMLR), 2012.
    cdot arXivlinkbibtexsearchproject webpage

  22. UBoost: Boosting with the Universum.
    cdot C. Shen, P. Wang, F. Shen, H. Wang.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2012.
    cdot pdfbibtexsearch

  23. On the dual formulation of boosting algorithms.
    cdot C. Shen, H. Li.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2010.
    cdot arXivlinkbibtexsearch

  24. Adaptive object tracking based on an effective appearance filter.
    cdot H. Wang, D. Suter, K. Schindler, C. Shen.
    cdot IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2007.
    cdot linkpdfbibtexsearch

    1. Featured article of September issue 2007.

Conference

  1. From motion blur to motion flow: a deep learning solution for removing heterogeneous motion blur.
    cdot D. Gong, J. Yang, L. Liu, Y. Zhang, I. Reid, C. Shen, A. van den Hengel, Q. Shi.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17), 2017.
    cdot arXivbibtexsearch

  2. Sequential person recognition in photo albums with a recurrent network.
    cdot Y. Li, G. Lin, B. Zhuang, L. Liu, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17), 2017.
    cdot arXivbibtexsearch

  3. RefineNet: multi-path refinement networks for high-resolution semantic segmentation.
    cdot G. Lin, A. Milan, C. Shen, I. Reid.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17), 2017.
    cdot arXivbibtexsearchproject webpage

  4. Multi-attention network for one shot learning.
    cdot P. Wang, L. Liu, C. Shen, Z. Huang, A. van den Hengel, H. Shen.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17), 2017.
    cdot pdfbibtexsearch

  5. The VQA-machine: learning how to use existing vision algorithms to answer new questions.
    cdot P. Wang, Q. Wu, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17), 2017.
    cdot arXivbibtexsearch

  6. Attend in groups: a weakly-supervised deep learning framework for learning from web data.
    cdot B. Zhuang, L. Liu, Y. Li, C. Shen, I. Reid.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17), 2017.
    cdot arXivbibtexsearch

  7. Adversarial PoseNet: a structure-aware convolutional network for human pose estimation.
    cdot Y. Chen, C. Shen, X. Wei, L. Liu, J. Yang.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’17), 2017.
    cdot arXivbibtexsearch

  8. Towards end-to-end text spotting with convolutional recurrent neural networks.
    cdot H. Li, P. Wang, C. Shen.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’17), 2017.
    cdot arXivbibtexsearch

  9. Semi-global weighted least squares in image filtering.
    cdot W. Liu, X. Chen, C. Shen, Z. Liu, J. Yang.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’17), 2017.
    cdot arXivbibtexsearch

  10. When unsupervised domain adaptation meets tensor representations.
    cdot H. Lu, L. Zhang, Z. Cao, W. Wei, K. Xian, C. Shen, A. van den Hengel.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’17), 2017.
    cdot bibtexsearch

  11. Towards context-aware interaction recognition.
    cdot B. Zhuang, L. Liu, C. Shen, I. Reid.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’17), 2017.
    cdot arXivbibtexsearch

  12. Efficient piecewise training of deep structured models for semantic segmentation.
    cdot G. Lin, C. Shen, A. van dan Hengel, I. Reid.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), 2016.
    cdot arXivbibtexsearch

  13. Less is more: zero-shot learning from online textual documents with noise suppression.
    cdot R. Qiao, L. Liu, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), 2016.
    cdot arXivbibtexsearch

  14. What's wrong with that object? identifying irregular object from images by modelling the detection score distribution.
    cdot P. Wang, L. Liu, C. Shen, Z. Huang, A. van den Hengel, H. Shen.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), 2016.
    cdot arXivbibtexsearch

  15. What value do explicit high level concepts have in vision to language problems.
    cdot Q. Wu, C. Shen, L. Liu, A. Dick, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), 2016.
    cdot arXivbibtexsearch

  16. Ask me anything: free-form visual question answering based on knowledge from external sources.
    cdot Q. Wu, P. Wang, C. Shen, A. Dick, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), 2016.
    cdot arXivbibtexsearch

  17. Fast training of triplet-based deep binary embedding networks.
    cdot B. Zhuang, G. Lin, C. Shen, I. Reid.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), 2016.
    cdot arXivbibtexsearchproject webpage

  18. Image co-localization by mimicking a good detector's confidence score distribution.
    cdot Y. Li, L. Liu, C. Shen, A. van den Hengel.
    cdot Proc. European Conference on Computer Vision (ECCV’16), 2016.
    cdot arXivbibtexsearch

  19. Cluster sparsity field for hyperspectral imagery denoising.
    cdot L. Zhang, W. Wei, Y. Zhang, C. Shen, A. van den Hengel, Q. Shi.
    cdot Proc. European Conference on Computer Vision (ECCV’16), 2016.
    cdot bibtexsearch

  20. Image restoration using very deep fully convolutional encoder-decoder networks with symmetric skip connections.
    cdot X. Mao, C. Shen, Y. Yang.
    cdot Proc. Advances in Neural Information Processing Systems (NIPS’16), 2016.
    cdot arXivlinkbibtexsearchproject webpage

  21. Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs.
    cdot B. Li, C. Shen, Y. Dai, A. van den Hengel, M. He.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 2015.
    cdot pdfbibtexsearch

  22. Mid-level deep pattern mining.
    cdot Y. Li, L. Liu, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 2015.
    cdot arXivbibtexsearchproject webpage

  23. Deep convolutional neural fields for depth estimation from a single image.
    cdot F. Liu, C. Shen, G. Lin.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 2015.
    cdot arXivbibtexsearchproject webpage

  24. The treasure beneath convolutional layers: cross convolutional layer pooling for image classification.
    cdot L. Liu, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 2015.
    cdot arXivbibtexsearch

  25. Learning to rank in person re-identification with metric ensembles.
    cdot S. Paisitkriangkrai, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 2015.
    cdot arXivbibtexsearch

  26. Supervised discrete hashing.
    cdot F. Shen, C. Shen, W. Liu, H. Shen.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 2015.
    cdot pdfbibtexsearchproject webpage

  27. Learning graph structure for multi-label image classification via clique generation.
    cdot M. Tan, Q. Shi, A. van den Hengel, C. Shen, J. Gao, F. Hu, Z. Zhang.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 2015.
    cdot pdfbibtexsearch

  28. Efficient SDP inference for fully-connected CRFs based on low-rank decomposition.
    cdot P. Wang, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), 2015.
    cdot arXivbibtexsearch

  29. Hyperspectral compressive sensing using manifold-structured sparsity prior.
    cdot L. Zhang, W. Wei, Y. Zhang, F. Li, C. Shen, Q. Shi.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’15), 2015.
    cdot pdfbibtexsearch

  30. Deeply learning the messages in message passing inference.
    cdot G. Lin, C. Shen, I. Reid, A. van den Hengel.
    cdot Proc. Advances in Neural Information Processing Systems (NIPS’15), 2015.
    cdot arXivpdfbibtexsearch

  31. Fast supervised hashing with decision trees for high-dimensional data.
    cdot G. Lin, C. Shen, Q. Shi, A. van den Hengel, D. Suter.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14), 2014.
    cdot arXivlinkbibtexsearchproject webpage

  32. Optimizing ranking measures for compact binary code learning.
    cdot G. Lin, C. Shen, J. Wu.
    cdot Proc. European Conference on Computer Vision (ECCV’14), 2014.
    cdot arXivbibtexsearchproject webpage

  33. Strengthening the effectiveness of pedestrian detection with spatially pooled features.
    cdot S. Paisitkriangkrai, C. Shen, A. van den Hengel.
    cdot Proc. European Conference on Computer Vision (ECCV’14), 2014.
    cdot arXivbibtexsearchproject webpage

  34. Encoding high dimensional local features by sparse coding based Fisher vectors.
    cdot L. Liu, C. Shen, L. Wang, A. van den Hengel, C. Wang.
    cdot Proc. Advances in Neural Information Processing Systems (NIPS’14), 2014.
    cdot arXivbibtexsearch

  35. Learning compact binary codes for visual tracking.
    cdot X. Li, C. Shen, A. Dick, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’13), 2013.
    cdot linkpdfbibtexsearch

  36. Inductive hashing on manifolds.
    cdot F. Shen, C. Shen, Q. Shi, A. van den Hengel, Z. Tang.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’13), 2013.
    cdot arXivbibtexsearchproject webpage

  37. A fast semidefinite approach to solving binary quadratic problems.
    cdot P. Wang, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’13), 2013.
    cdot arXivbibtexsearchproject webpage

    1. Oral presentation, 60 out of 1870 submissions.

  38. Bilinear programming for human activity recognition with unknown MRF graphs.
    cdot Z. Wang, Q. Shi, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’13), 2013.
    cdot linkpdfbibtexsearch

  39. Part-based visual tracking with online latent structural learning.
    cdot R. Yao, Q. Shi, C. Shen, Y. Zhang, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’13), 2013.
    cdot linkpdfbibtexsearchproject webpage

  40. Contextual hypergraph modeling for salient object detection.
    cdot X. Li, Y. Li, C. Shen, A. Dick, A. van den Hengel.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’13), 2013.
    cdot arXivbibtexsearchproject webpage

  41. A general two-step approach to learning-based hashing.
    cdot G. Lin, C. Shen, D. Suter, A. van den Hengel.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’13), 2013.
    cdot arXivbibtexsearchproject webpage

  42. Efficient pedestrian detection by directly optimizing the partial area under the ROC curve.
    cdot S. Paisitkriangkrai, C. Shen, A. van den Hengel.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’13), 2013.
    cdot arXivpdfbibtexsearch

  43. Dictionary learning and sparse coding on Grassmann manifolds: an extrinsic solution.
    cdot M. Harandi, C. Sanderson, C. Shen, B. Lovell.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’13), 2013.
    cdot arXivbibtexsearchproject webpage

  44. Learning hash functions using column generation.
    cdot X. Li, G. Lin, C. Shen, A. van den Hengel, A. Dick.
    cdot Proc. International Conference on Machine Learning (ICML’13), 2013.
    cdot arXivpdfbibtexsearchproject webpage

    1. Oral presentation.

  45. Non-sparse linear representations for visual tracking with online reservoir metric learning.
    cdot X. Li, C. Shen, Q. Shi, A. Dick, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’12), 2012.
    cdot arXivpdfbibtexsearch

  46. Sharing features in multi-class boosting via group sparsity.
    cdot S. Paisitkriangkrai, C. Shen, A. van den Hengel.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’12), 2012.
    cdot pdfbibtexsearch

  47. Robust tracking with weighted online structured learning.
    cdot R. Yao, Q. Shi, C. Shen, Y. Zhang, A. van den Hengel.
    cdot Proc. European Conference on Computer Vision (ECCV’12), 2012.
    cdot pdfbibtexsearch

  48. Is margin preserved after random projection?.
    cdot Q. Shi, C. Shen, R. Hill, A. van den Hengel.
    cdot Proc. International Conference on Machine Learning (ICML’12), 2012.
    cdot arXivlinkbibtexsearch

    1. 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.

  49. Real-time visual tracking using compressive sensing.
    cdot H. Li, C. Shen, Q. Shi.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’11), 2011.
    cdot pdfbibtexsearch

  50. A generalized probabilistic framework for compact codebook creation.
    cdot L. Liu, L. Wang, C. Shen.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’11), 2011.
    cdot pdfbibtexsearch

  51. A direct formulation for totally-corrective multi-class boosting.
    cdot C. Shen, Z. Hao.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’11), 2011.
    cdot pdfbibtexsearch

  52. A scalable dual approach to semidefinite metric learning.
    cdot C. Shen, J. Kim, L. Wang.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’11), 2011.
    cdot pdfbibtexsearch

  53. Is face recognition really a compressive sensing problem?.
    cdot Q. Shi, A. Eriksson, A. van den Hengel, C. Shen.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’11), 2011.
    cdot pdfbibtexsearch

  54. Graph mode-based contextual kernels for robust SVM tracking.
    cdot X. Li, A. Dick, H. Wang, C. Shen, A. van den Hengel.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’11), 2011.
    cdot pdfbibtexsearch

  55. Rapid face recognition using hashing.
    cdot Q. Shi, H. Li, C. Shen.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’10), 2010.
    cdot pdfbibtexsearch

  56. LACBoost and FisherBoost: optimally building cascade classifiers.
    cdot C. Shen, P. Wang, H. Li.
    cdot Proc. European Conference on Computer Vision (ECCV’10), 2010.
    cdot arXivlinkbibtexsearch

  57. Efficiently training a better visual detector with sparse eigenvectors.
    cdot S. Paisitkriangkrai, C. Shen, J. Zhang.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’09), 2009.
    cdot arXivlinkbibtexsearch

  58. Positive semidefinite metric learning with boosting.
    cdot C. Shen, J. Kim, L. Wang, A. van den Hengel.
    cdot Proc. Advances in Neural Information Processing Systems (NIPS’09), 2009.
    cdot arXivpdfbibtexsearchproject webpage

  59. A fast algorithm for creating a compact and discriminative visual codebook.
    cdot L. Wang, L. Zhou, C. Shen.
    cdot Proc. European Conference on Computer Vision (ECCV’08), 2008.
    cdot linkpdfbibtexsearch

  60. PSDBoost: matrix-generation linear programming for positive semidefinite matrices learning.
    cdot C. Shen, A. Welsh, L. Wang.
    cdot Proc. Advances in Neural Information Processing Systems (NIPS’08), 2008.
    cdot pdfbibtexsearch

  61. Kernel-based tracking from a probabilistic viewpoint.
    cdot Q. Nguyen, A. Robles-Kelly, C. Shen.
    cdot Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR’07), 2007.
    cdot linkpdfbibtexsearch

  62. Fast global kernel density mode seeking with application to localisation and tracking.
    cdot C. Shen, M. Brooks, A. van den Hengel.
    cdot Proc. IEEE International Conference on Computer Vision (ICCV’05), 2005.
    cdot linkpdfbibtexsearch

    1. Oral presentation, 45 out of 1200 submissions.