We are organizing our second tutorial on large-scale holistic video understanding with MIT, ETH Zurich, KU Leuven, KIT, Uni. Bonn, Stanford University, Google Research and Facebook AI Research. The tutorial will take place on October 16th virtually.
Learning features for various tasks in videos is an ongoing research endeavour to tackle large scale video understanding. We are organizing the workshop for holistic video understanding at CVPR'21. The agenda of this workshop is to facilitate the learning of generic video feature representation for vision tasks.
Live streaming link: Zoom Link
Organizers: Vivek Sharma (MIT, Harvard), Ali Diba (KU Leuven), Mohsen Fayyaz (Uni. Bonn), Shyamal Buch (Stanford University), Juergen Gall (Uni. Bonn), Rainer Stiefelhagen (KIT), Luc Van Gool (ETH Zurich/ KU Leuven), Manohar Paluri (Facebook AI Research), Ehsan Adeli (Stanford University), David Ross (Google Research)