CMU Computer Vision Group
Home | People | Vision Courses | Misc-reading Group | VASC Seminar | Related Links


Activity Forecasting (ECCV 2012)
Kris Kitani, Brian Ziebart, Drew Bagnell, and Martial Hebert
Activity Forecasting (ECCV 2012)

We address the task of inferring the future actions of people from noisy visual input. We denote this task activity forecasting. To achieve accurate activity forecasting, our approach models the effect of the physical environment on the choice of human actions. This is accomplished by the use of state-of-the-art semantic scene understanding combined with ideas from optimal control theory. Our unified model also integrates several other key elements of activity analysis, namely, destination forecasting, sequence smoothing and transfer learning. As proof-of-concept, we focus on the domain of trajectory-based activity analysis from visual input. Experimental results demonstrate that our model accurately predicts distributions over future actions of individuals. We show how the same techniques
can improve the results of tracking algorithms by leveraging information about likely goals and trajectories.

Project Page:

Our CVPR 2013 Papers!

Congratulations to the authors!

Representing Videos using Mid-level Discriminative Patches
Arpit Jain, Abhinav Gupta, Mikel Rodriguez and Larry S. Davis

Pixel-level Hand Detection in Ego-Centric Videos
Cheng Li and Kris Kitani.

Jointly Aligning and Segmenting Multiple Web Photo Streams for the Inference of Collective Photo Storylines
Gunhee Kim and Eric Xing

Poselet Key-framing: A Model for Human Activity Recognition
Michalis Raptis and Leonid Sigal

Deformable Graph Matching
Feng Zhou and Fernando De la Torre

Selective Transfer Machine for Personalized Facial Action Unit Detection
Wen-Sheng Chu, Fernando DelaTorre, Jeffery Cohn

Supervised Descent Method and its Applications to Face Alignment
Xuehan Xiong, Fernando De la Torre

Representing and Discovering Adversarial Team Behaviors using Player Roles
Patrick Lucey, Alina Bialkowski, Peter Carr, Iain Matthews, Yaser Sheikh

Tracking Human Pose by Tracking Symmetric Parts
Varun Ramakrishna, Yaser Sheikh, Takeo Kanade

Tracking Sports Players with Context-Conditioned Motion Models
Jingchen Liu, Peter Carr, Robert Collins, Yanxi Liu


Last Updated April 22, 2013