 |
Timothée
Cour Research scientist NEC-Labs Silicon Valley timothee dot cour at gmail dot com |
|
I am currently a research scientist at NEC-Labs (Silicon Valley) in the media analytics department, working on Computer Vision and Machine Learning with Kai Yu. I finished my postdoc in the Willow group of INRIA / Ecole Normale Superieure, where worked with Jean Ponce and Francis Bach. I obtained my PhD in Computer Science under the supervision of Ben Taskar at the University of Pennsylvania, Philadelphia, where I also obtained my MS with Jianbo Shi. Before that I was an undergrad at the Ecole Polytechnique, France, in applied mathematics. Recent projects include: Learning with weak supervision,Video understanding from images/text/audio, image segmentation and recognition, approximate inference for Graph Matching and MRFs. Find out more in my research page.
Videos
unsupervised face recognition in videos
Fully automatic person identification in a video. Absolutely no manual labeling was done, instead our algorithm automatically learns a person model from a video and associated screenplay, from which we extract the set of characters appearing in a scene (bottom labels). For more details, see our CVPR 2009 paper.
Toolboxes
Convex Learning from Partial Labels Toolbox new
Graph matching toolbox new (02/06/2011): update to support latest matlab version
Multiscale NCut Image segmentation Toolbox
Normalized Cuts Segmentation Code new (01/22/2010): release of all c++ source mex files compatible with matlab R2009b.
Datasets
Annotated Faces on TV Dataset new
Recent Press
Machine Learning by Watching and Listening, 2009
Référencer une Vidéo par Reconnaissance des Dialogues, 2009
Dans une vidéo, les dialogues sont un mode de référencement comme un autre, 2009
Cool! Machine Learning by Watching and Listening, 2009
Publications
Learning from Partial Labels. Timothee Cour, Ben Sapp, Ben Taskar. Journal of Machine Learning Research (JMLR), 2011 (to appear).
[pdf][abstract][bib] new
Large-scale image classification: fast feature extraction and SVM training. Yuanqing Lin, Fengjun Lv, Shenghuo Zhu, Ming Yang, Timothee Cour, Kai Yu, Liangliang Cao, Thomas Huang. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2011 (to appear).
[pdf][abstract][bib] new
Talking Pictures: Temporal Grouping and Dialog-Supervised Person Recognition. Timothee Cour, Ben Sapp, Akash Nagle, Ben Taskar. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
[pdf][abstract][bib] [supplement]
Thesis: Weakly Supervised Learning from Multiple Modalities: Exploiting Video, Audio and Text for Video Understanding. University of Pennsylvania, PA, May 2009
[pdf][abstract][bib]
Learning from Ambiguously Labeled Images. Timothee Cour, Ben Sapp, Chris Jordan, Ben Taskar. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2009.
[pdf][abstract][bib] [tech report] [code] [dataset]
Movie/Script: Alignment and Parsing of Video and Text Transcription. Timothee Cour, Chris Jordan, Eleni Miltsakaki, Ben Taskar. Proceedings of the European Conference on Computer Vision (ECCV), 2008.
[pdf][abstract][bib][videos: retrieval of actions and character naming]
Video Deconstruction: Revealing narrative structure through image and text alignment. Timothee Cour, Ben Taskar. NIPS 2007 Workshop on the Grammar of Vision: Probabilistic Grammar-Based Models for Visual Scene Understanding and Object Categorization.
[pdf][abstract][bib]
Recognizing objects by piecing together the Segmentation Puzzle. Timothee Cour, Jianbo Shi. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2007.
[pdf][abstract][bib][poster] [supplement: results on entire horse dataset (328 images)]
Solving Markov Random Fields with Spectral Relaxation. Timothee Cour, Jianbo Shi. Artificial Intelligence and Statistics (AISTATS), 2007.
[pdf][abstract][bib]
Balanced
Graph
Matching.
Timothee
Cour,
Praveen Srinivasan, Jianbo Shi. Advances
in
Neural Information Processing Systems (NIPS), 2006
[pdf][abstract][bib]
[supplement:
Affinely Constrained Rayleigh Quotients] [code]
Spectral
Segmentation with Multiscale Graph Decomposition.
Timothee
Cour,
Florence Benezit, Jianbo Shi.
IEEE
International Conference on
Computer Vision and Pattern Recognition (CVPR), 2005.
[pdf][abstract][bib][code]
Learning spectral
graph segmentation.
Timothee
Cour,
Nicolas
Gogin, Jianbo Shi.
Artificial
Intelligence and Statistics (AISTATS),
2005.
[pdf][abstract][bib][Slides]
Technical
reports
Learning from Ambiguously Labeled Images. Timothee Cour, Ben Sapp, Chris Jordan, Ben Taskar. Technical Report MS-CIS-09-07, University of Pennsylvania, Philadelphia, May 2009.
[pdf][abstract]
Convex Relaxations for Markov Random Field MAP estimation. Timothee Cour. University of Pennsylvania, Philadelphia, September 2008.
[pdf]
A learnable spectral memory graph for recognition and segmentation. Timothee Cour, Jianbo Shi. Technical Report MS-CIS-04-12, University of Pennsylvania CIS Technical Reports, Philadelphia, PA, June 2004.
[pdf][abstract][bib]
Teaching
Fall 2006, Teaching Assistant: Automata, Computability, and Complexity, CSE 262 (w. Sudipto Guha)
Spring 2005, Teaching Assistant: Computer Vision, CSE 399 (w. Kostas Daniilidis)
Fall 2004, Teaching Assistant: Mathematical Foundations of Computer Science, CSE 260 (w. Sampath Kannan)
Last updated on Jan 2010