%0 Conference Paper %B Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on %D 2011 %T Multi-agent event recognition in structured scenarios %A Morariu,V.I. %A Davis, Larry S. %K Allen %K analysis;Markov %K descriptions;video %K event %K grounding %K inference;semantic %K interval %K Logic %K logic;interval-based %K logic;Markov %K logic;multi-agent %K logical %K networks;bottom-up %K processes;formal %K processing; %K reasoning;multiagent %K reasoning;video %K recognition;probabilistic %K recognition;temporal %K scheme;first-order %K signal %K spatio-temporal %K systems;object %K temporal %X We present a framework for the automatic recognition of complex multi-agent events in settings where structure is imposed by rules that agents must follow while performing activities. Given semantic spatio-temporal descriptions of what generally happens (i.e., rules, event descriptions, physical constraints), and based on video analysis, we determine the events that occurred. Knowledge about spatio-temporal structure is encoded using first-order logic using an approach based on Allen's Interval Logic, and robustness to low-level observation uncertainty is provided by Markov Logic Networks (MLN). Our main contribution is that we integrate interval-based temporal reasoning with probabilistic logical inference, relying on an efficient bottom-up grounding scheme to avoid combinatorial explosion. Applied to one-on-one basketball, our framework detects and tracks players, their hands and feet, and the ball, generates event observations from the resulting trajectories, and performs probabilistic logical inference to determine the most consistent sequence of events. We demonstrate our approach on 1hr (100,000 frames) of outdoor videos. %B Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on %P 3289 - 3296 %8 2011/06// %G eng %R 10.1109/CVPR.2011.5995386