8:30-8:45

Opening remarks by organizers
8:45-9:15

Invited Talk: "The Evolution of Stochastic Grammars for Representation and Recognition of Activities in Videos" by Rama Chellappa, University of Maryland, USA

Slides
9:15-10:00

Invited Talk: "Object Detection Grammars" by Pedro Felzenszwalb, Brown University, USA

Slides
10:00-10:15

Coffee break
10:15-11:00

Invited Talk: "Sum-Product Networks: A New Deep Architecture" by Pedro Domingos, University of Washington, USA

Slides
11:00-11:45

Invited Talk: "Stochastic Models for Semantic Parsing, Multi-Faceted Topic Discovery, and Causal Event Inference: Perspectives from Natural Language Processing" by Roxana Girju, University of Illinois at Urbana-Champaign, USA

Slides
11:45-12:00

Oral presentation of a peer reviewed paper: "Human Parsing using Stochastic And-Or Grammars and Rich Appearances" by Brandon Rothrock and Song-Chun Zhu, University of California Los Angeles, USA

Slides
12:00-12:15

Oral presentation of a peer reviewed paper: "Modeling Symmetries for Stochastic Structural Recognition" by R. Tylecek and R. Sara, Center for Machine Perception, Czech Technical University, Czech Republic

Slides
12:15-1:30

Lunch
1:30-2:30

Poster session

  1. "An Ontology for Generating Descriptions about Natural Outdoor Scenes" by I. Nwogu, Y. Zhou, and C. Brown, University of Rochester, USA
  2. "Modeling Symmetries for Stochastic Structural Recognition" by R. Tylecek and R. Sara, Center for Machine Perception, Czech Technical University, Czech Republic
  3. "Unsupervised Learning of Stochastic AND-OR Templates for Object Modeling" by Z. Si and S.C. Zhu, University of California Los Angeles, USA
  4. "Human Parsing using Stochastic And-Or Grammars and Rich Appearances" by B Rothrock and S.C. Zhu, University of California Los Angeles, USA
  5. "Towards Coherent Natural Language Description of Video Streams" by M. Khan, L. Zhang, Y. Gotoh, University of Sheffield, UK
  6. "Interactive Learning of Human Activities Using Active Video Composition" by M. Ryoo, Electronics and Telecommunications Research Institute, South Korea
  7. "PEL-CNF: Probabilistic Event Logic Conjunctive Normal Form for Video Interpretation" by J. Selman, M. Amer, A. Fern, and S. Todorovic, Oregon State University, USA
2:30-3:15

Invited Talk: "Learning and the Language of Thought" by Noah Goodman, Stanford University, USA

Slides
3:15-4:00

Invited Talk: "Information Theoretic Methods for Learning Generative Models for Relational Structures" by Edwin Hancock, University of York, UK

Slides
4:00-4:30

Coffee break
4:30-5:00

Panel