TY - CONF T1 - Learning multi-modal densities on Discriminative Temporal Interaction Manifold for group activity recognition T2 - Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on Y1 - 2009 A1 - Ruonan Li A1 - Chellapa, Rama A1 - Zhou,S. K KW - a KW - activities;parametric KW - activity KW - analysis;belief KW - analysis;pattern KW - Bayesian KW - classification;image KW - classifier;multimodal KW - complex KW - constraints;data-driven KW - density KW - equipment;video KW - function;multiobject KW - interaction KW - manifold;discriminative KW - matrix;football KW - MOTION KW - network;video-based KW - networks;image KW - play KW - posteriori KW - processing; KW - recognition KW - recognition;group KW - recognition;maximum KW - signal KW - spatial KW - strategy;discriminative KW - temporal AB - While video-based activity analysis and recognition has received much attention, existing body of work mostly deals with single object/person case. Coordinated multi-object activities, or group activities, present in a variety of applications such as surveillance, sports, and biological monitoring records, etc., are the main focus of this paper. Unlike earlier attempts which model the complex spatial temporal constraints among multiple objects with a parametric Bayesian network, we propose a Discriminative Temporal Interaction Manifold (DTIM) framework as a data-driven strategy to characterize the group motion pattern without employing specific domain knowledge. In particular, we establish probability densities on the DTIM, whose element, the discriminative temporal interaction matrix, compactly describes the coordination and interaction among multiple objects in a group activity. For each class of group activity we learn a multi-modal density function on the DTIM. A Maximum a Posteriori (MAP) classifier on the manifold is then designed for recognizing new activities. Experiments on football play recognition demonstrate the effectiveness of the approach. JA - Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on M3 - 10.1109/CVPR.2009.5206676 ER -