Program

09:15-09:20Welcome
09:20-10:00Invited talk: Jamie Shotton (Microsoft Research): "One-shot human pose estimation by inferring dense correspondences to the Vitruvian Manifold"
10:00-10:40Invited talk: Aude Oliva (MIT): "Human representation of object and space affordance"
10:40-11:00Coffee break
11:00-11:40Invited talk: David Forsyth (UIUC): "But what are they doing with their hands?"
11:40-12:20Invited talk: Abhinav Gupta (CMU): "Humans, actions, and objects"
12:20-12:30Poster spotlights
  • Shigeyuki Odashima (Univ. of Tokyo), Masamichi Shimosaka (Univ. of Tokyo), Takuhiro Kaneko (Univ. of Tokyo), Rui Fukui (Univ. of Tokyo), and Tomomasa Sato (Univ. of Tokyo). "Collective activity localization with contextual spatial pyramid"
  • Takuhiro Kaneko (Univ. of Tokyo), Masamichi Shimosaka (Univ. of Tokyo), Shigeyuki Odashima (Univ. of Tokyo), Rui Fukui (Univ. of Tokyo), and Tomomasa Sato (Univ. of Tokyo). "Viewpoint invariant collective activity recognition with relative action context"
  • Fadime Sener (Bilkent Univ.), Cagdas Bas (Hacettepe Univ.), and Nazli Ikizler-Cinbis (Hacettepe Univ.). "On recognizing actions in still images via multiple features"
12:30-13:30Lunch break
13:30-14:30Poster session
14:30-15:10Invited talk: Deva Ramanan (UC Irvine): "Multi-body and multi-object pose estimation"
15:10-15:50Invited talk: Jitendra Malik (UC Berkeley): "The future of action recognition"
15:50The end