spacer
School of Computer Science The University of Adelaide Australia
Computer Science Home
Staff Only
text zoom: S | M | L

School of Computer Science
Level 4
Ingkarni Wardli Building
THE UNIVERSITY OF ADELAIDE
SA 5005
AUSTRALIA
Email

Telephone: +61 8 8313 4729
Facsimile: +61 8 8313 4366


You are here: Computer Science > users > paulp> projects

Research Projects

Pedestrian detection

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 output learning. Our detector currently ranks second on the KITTI data set

FrameworkOur Approach

S. Paisitkriangkrai, C. Shen and A. van den Hengel. Efficient Pedestrian Detection by Directly Optimizing the Partial Area under the ROC Curve, arXiv preprint arXiv:1409.5209

S. Paisitkriangkrai, C. Shen and A. van den Hengel, "Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features", ECCV 2014 (Supp. material)

Semantic Labeling

We build CNN model from both RGB and DSM images.

Cell Classification

We build an ensemble of classifiers for bacteria classification. Our results rank third in the ICIP 2013 competition.

Binary-class classification

Optimizing the partial area under the ROC curve

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.

AdaBoostpAUCEns (ours)

S. Paisitkriangkrai, C. Shen and A. van den Hengel. Efficient Pedestrian Detection by Directly Optimizing the Partial Area under the ROC Curve, ICCV 2013, PDF Supplementary

Greedy Sparse Linear Discriminant Analysis (GSLDA)

We introduce Greedy Sparse Linear Discriminant Analysis (GSLDA) for its conceptual simplicity and computational efficiency to the task of face and pedestrian detection.

AdaBoostGSLDA (ours)

S. Paisitkriangkrai, C. Shen and J. Zhang. Sharing features in multi-class boosting via group sparsity, CVPR 2009, PDF Journal

Multi-class classification

Multi-class Boosting + Group sparsity = Feature sharing classifier

We present a novel formulation of fully corrective boosting for multi-class classification problems with the awareness of sharing features.

AdaBoost.ECCOur MultiBoost (group)

S. Paisitkriangkrai, C. Shen and A. van den Hengel. Sharing features in multi-class boosting via group sparsity, CVPR 2012, PDF Supplementary

Multi-class boosting with Crammer and Singer's formulation

We propose scalable and effective classification model for multi-class boosting classification. The approach directly maximizes the multi-class margin (similar to the multi-class SVM (MSVM) formulation of Crammer and Singer).

The technical paper and source code for MultiBoost (Stage-wise) can be downloaded here. PDF source code.

MultiBoost (Stage-wise)MultiBoost (Stage-wise)

Randomized boosting with matlab source code

The new model trains a single-vector parameterized classifier irrespective of the number of classes. The advantage of the new appraoch is that multi-class boosting can be trained at the same learning complexity of binary boosting.

The technical paper and source code for RandomBoost can be downloaded here. PDF source code.

Data distributionRandomBoost

Online learning

Large-scale multimedia framework

Clip-based Hierarchical Representation for Near-Duplicate Video Detection