img-logoTexmex

The talks (MP4 - Downloading files)

Jiri Matas ; Patrick Perez ; Andrew Zisserman ; Albert Gordo ; Yannis Avrithis ; Philippe-Henri Gosselin

img-Jirimatas-workshopComputerscience2oct2014 Jiri Matas, Czech Technical University Prague

Short-term Model-Free Causal Tracking - the VOT Challenge 2013, 2014 [time: 47:37mn]

Abstract:
The Visual Object Tracking Challenge is a benchmarking activity for a certain class of trackers. The talk will introduce the challenge, its semi-automatic selection and annotation of test data and the performance metrics. We will review the results for 2013 and 2014, summarize the lessons learned and discuss changes considered for 2015.

img-minilogoPDF The slides

img-HautPage

img-PatrickPerezWorkshopComputerVision2oct2014 Patrick Perez, Technicolor, Rennes

Face2Face: Learning Metrics to Compare Faces [time: 53:03mn]

img-minilogoPDF The slides

img-HautPage

Andrew Zisserman, University of Oxford

Time is on my side

Abstract:

The talk will cover two aspects of encoding time in video: first, to discern the temporal direction of the video, and second, to discriminate human actions in video. For the second aspect we employ a deep Convolutional Network trained on multi-frame dense optical flow, and evaluate on the standard video human actions benchmarks of UCF-101 and HMDB-51.
Work with William Freeman, Zheng Pan, Lyndsey Pickup, Bernhard Scholkopf, YiChang Shih, Karen Simonyan, Donglai Wei, Changshui Zhang .

The slides

img-HautPage

img-AlbertGordo-workshopComputerScience2oct2014 Albert Gordo, Xerox Research Center Europe

Towards Text Understanding: Word Image Representation, Matching and Recognition [time: 32:48 mn]

img-minilogoPDF The slides

img-HautPage

img-YannisAvrithis-workshopComputerVision2oct2014 Yannis Avrithis, National Technical University of Athens

Image Retrieval, Vector Quantization and Nearest Neighbor Search [timing: 29:53 mn]

img-minilogoPDF The slides

img-HautPage

img-PHGosselin-workshopComputervision2oct2014 Philippe-Henri Gosselin, ENSEA - Cergy

Scalable Learning and Indexing for Retrieval in Large Image Databases [timing: 21:59 mn]

img-minilogoPDF The slides

img-HautPage

Sponsors

img-logoANR img-logoFire img-logoInria img-logoImagesreseaux img-logoirisa

img-visuelVideothequeInria Index-Videotheque Inria-Rennes

img-flechehaut-Videotheque