Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos
2009 IEEE Conference on Computer Vision and Pattern Recognition (2009)
Miami, FL, USA
June 20, 2009 to June 25, 2009
A. Gupta , Univ. of Maryland, College Park, MD, USA
L.S. Davis , Univ. of Maryland, College Park, MD, USA
Analyzing videos of human activities involves not only recognizing actions (typically based on their appearances), but also determining the story/plot of the video. The storyline of a video describes causal relationships between actions. Beyond recognition of individual actions, discovering causal relationships helps to better understand the semantic meaning of the activities. We present an approach to learn a visually grounded storyline model of videos directly from weakly labeled data. The storyline model is represented as an AND-OR graph, a structure that can compactly encode storyline variation across videos. The edges in the AND-OR graph correspond to causal relationships which are represented in terms of spatio-temporal constraints. We formulate an Integer Programming framework for action recognition and storyline extraction using the storyline model and visual groundings learned from training data.
video annotation, human activity analysis, plots learning construction, visually grounded storyline model extraction, video understanding, human action recognition, semantic meaning, AND-OR graph, encoding, spatio-temporal constraint, integer programming framework
L. Davis, A. Gupta, Jianbo Shi and P. Srinivasan, "Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos," 2009 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Miami, FL, USA, 2009, pp. 2012-2019.