lear.inrialpes.fr
THOTH
http://lear.inrialpes.fr/index.php
Modeling visual knowledge from large-scale data. The Thoth team started in January 2016. It is a follow up to the LEAR team (2003-2015). For more information see our research description page. And annual reports of 2015. Julien Mairal was awarded one of the ERC starting grants 2016. We organized a Symposium on Computer Vision and Deep Learning. On June 9th. Check the program and register. Mandatory, but free). Our new associate team GAYA. In collaboration with the Robotics Institute, CMU has started.
lear.inrialpes.fr
THOTH - Jobs
http://lear.inrialpes.fr/jobs
Have some background in Computer Vision and/or Statistical Learning. Excellent academic records are required for PhD students, and strong publications in internationally recognised conferences or journals are required for postdoctoral positions. For engineers, first class scientific programming skills and previous experience with computer vision or image processing are essential. Applications should include a curriculum vitae, a list of publications and three letters of reference (referees mi...Superviso...
lear.inrialpes.fr
THOTH - Software
http://lear.inrialpes.fr/software
The code for Patch-CKN. Along with the dataset introduced in the paper, is available here. The code for EpicFlow. CVPR'15) is available here. The detection code for "Learning to Detection Motion Boundaries". CVPR'15) is available here. Spatio-temporal object detection proposals. The code for Spatio-temporal object detection proposals. ECCV'14) and the refined spatio-temporal annotations of UCF Sport are available here. The code for our NIPS'14 paper. The code for "Category-specific video summarization".
lear.inrialpes.fr
THOTH - Team
http://lear.inrialpes.fr/team
Hervé Jégou.
lear.inrialpes.fr
Jakob Verbeek
http://lear.inrialpes.fr/~verbeek
Researcher in Computer Vision and Machine Learning. Internship of 6 months for PhD students on learning image representations in collaboration with Xerox Research Centre Europe. Publications HAL de verbeek de cordelia,schmid;jakob,verbeek;matthijs,douze;zaid,harchaoui;thomas,mensink;remi,ronfard;laurent,zwald;frederic,jurie;roger,mohr du labo/EPI 2398;44942. Machine learning solutions to visual recognition problems. Accès au texte intégral et bibtex. Accès au texte intégral et bibtex. Dec 2015, Santiago,...
lear.inrialpes.fr
THOTH - Data Sets and Images
http://lear.inrialpes.fr/data
Data Sets and Images. The dataset for spatio-temporal action detection, introduced in "Towards Weakly-Supervised Action Localization". ArXiv), is available here. The dataset introduced in the Patch-CKN paper. A dataset, introduced in the arXiv paper Beat-Event Detection in Action Movie Franchises. The datasets with temporally aligned video clips of a Climbing session and a Madonna concert, introduced in the arXiv paper Circulant temporal encoding for video retrieval and temporal alignment. For the datase...