Tian Lan (MSc), Weilong Yang (PhD), and Yang Wang had a paper accepted to Neural Information Processing Systems (NIPS) 2010. Context relating the actions of individuals and groups of people is modelled for human action recognition. The paper develops a latent variable framework that adapts the latent connections between actions of individuals to model an image.
Yang Wang had a paper accepted to Neural Information Processing Systems (NIPS) 2010. The paper develops a method for annotating images with tags describing the objects present. The model explicitly captures the matching of object tags to image regions in a discriminative framework.
Tian Lan successfully defended his M.Sc. thesis Beyond Actions: Discriminative Models For Contextual Group Activities. Congratulations Tian!
Bahman Yari Saeed Khanloo successfully defended his M.Sc. thesis Combining Simple Trackers Using Structural SVMs For Offline Single Object Tracking. Congratulations Bahman!
Tian Lan (MSc) and Yang Wang had a paper on action recognition accepted in the International Workshop on Sign, Gesture, Action, 2010. A contextual feature representation that considers the actions of nearby people when recognizing the action of an individual is presented. For example, one can recognize that a nursing home resident has fallen based on the fact that other people in the scene are coming to help.
Yang Wang had a paper on object recognition accepted in the European Conference on Computer Vision (ECCV), 2010. Object categories (e.g. bird, apple, chair) and attributes (e.g. red, shiny, edible) are treated together in a unified learning framework.
Mani Ranjbar (PhD) and Yang Wang had a paper on object segmentation accepted in the European Conference on Computer Vision (ECCV), 2010. A learning framework for choosing segmentation algorithm parameters against a class of complex loss measures is developed.
Weilong Yang successfully defended his M.Sc. thesis Learning Transferable Distance Functions For Human Action Recognition And Detection. Congratulations Weilong!
Zhi Feng Huang (MSc) won an NSERC Alexander Graham Bell Canada Graduate Scholarship (CGS). Congratulations!
Weilong Yang (MSc) and Yang Wang had a paper on action recognition in still images accepted in the IEEE Computer Vision and Pattern Recognition (CVPR), 2010. Body pose is treated as a latent variable in a model focused on action recognition.
Bahman Yari Saeed Khanloo (MSc), Ferdinand Stefanus (MSc), and Mani Ranjbar (PhD) had a paper on tracking accepted in the Seventh Canadian Conference on Computer and Robot Vision (CRV), 2010. A max-margin criterion is used to learn weights for parameters of a tracking algorithm with multiple features.
Alex Couture-Beil (MSc) developed an algorithm for selecting individual robots using face detection and commanding them using gesture recognition. A video of the system appeared at the IEEE International Conference on Human-Robot Interaction (Video Session) (HRI), 2010. A full paper describing the work will appear at the Seventh Canadian Conference on Computer and Robot Vision (CRV), 2010.
Mohammad Norouzi successfully defended his M.Sc. thesis Convolutional Restricted Boltzmann Machines for Feature Learning. Congratulations Mohammad!
Yang Wang had a paper on semi-supervised learning for structured prediction problems accepted to Advances in Neural Information Processing Systems (NIPS), 2009. A novel information theoretic approach to mutual information-based regularization is developed.
Dr. Yang Wang successfully defended his Ph.D. thesis Learning Structured Models For Human Actions And Poses. Congratulations Yang!
Weilong Yang (MSc) and Yang Wang (PhD) had papers on transfer learning for human action recognition accepted to the Asian Conference on Computer Vision (ACCV) and 2nd International Workshop on Machine Learning for Vision-based Motion Analysis (MLVMA at ICCV), 2009. Video clips are compared with a distance function built from patches. The weights of these patches are determined via transfer learning (MLVMA), and used in an efficient action detection framework (ACCV).
William Ma successfully defended his M.Sc. thesis Motion Estimation For Functional Medical Imaging Studies Using A Stereo Video Head Pose Tracking System. Congratulations William!
Yang Wang (PhD) had a paper on human action recognition accepted to IEEE Computer Vision and Pattern Recognition (CVPR), 2009. A hidden conditional random field model is learned using a max-margin criterion.
Mohammad Norouzi (MSc) and Mani Ranjbar (PhD) had a paper on feature learning accepted to IEEE Computer Vision and Pattern Recognition (CVPR), 2009. A hierarchical convolutional variant of the restricted Boltzmann machine model is developed in which parameters are tied to learn filters which are used as features for object detection.
Mark Bayazit (BSc) and Alex Couture-Beil (MSc) had a paper on human gesture recognition accepted to IAPR Conference on Machine Vision Applications (MVA), 2009. An efficient algorithm using the GPU was developed.
Yang Wang (PhD) had a paper on human action recognition accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2009. A novel bag-of-words sequence model is developed, based on latent Dirichlet allocation (LDA).
Yang Wang (PhD) had a paper on human action recognition accepted to Advances in Neural Information Processing Systems (NIPS), 2008. A hidden conditional random field model incorporating large-scale global features and local patch features is used in this work.
Yang Wang (PhD) had a paper on estimating human pose. Multiple tree-structured models are combined to handle occlusion and avoid "double-counting" of image evidence. This work appeared at the European Conference on Computer Vision (ECCV), 2008.
Bo Chen (BSc) and William Ma (MSc) had a paper on energy efficient scheduling for window-scanning algorithms at the Workshop on the Interaction between Operating Systems and Computer Architecture (WIOSCA), 2008.
Yang Wang (PhD) had a paper on boosting with incomplete information. For example, in object recognition bounding box information may be provided on some training data. This work appeared at the International Conference on Machine Learning (ICML), 2008.



Back to Greg Mori's page