From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems Export

@proceedings{citeulike:4446647, abstract = {Clustering video sequences in order to infer and extract activities from a single video stream is an extremely important problem and has significant potential in video indexing, surveillance, activity discovery and event recognition. Clustering a video sequence into activities requires one to simultaneously recognize activity boundaries (activity consistent subsequences) and cluster these activity subsequences. In order to do this, we build a generative model for activities (in video) using a cascade of dynamical systems and show that this model is able to capture and represent a diverse class of activities. We then derive algorithms to learn the model parameters from a video stream and also show how a single video sequence may be clustered into different clusters where each cluster represents an activity. We also propose a novel technique to build affine, view, rate invariance of the activity into the distance metric for clustering. Experiments show that the clusters found by the algorithm correspond to semantically meaningful activities.}, author = {Turaga, P. K. and Veeraraghavan, A. and Chellappa, R.}, booktitle = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, citeulike-article-id = {4446647}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/CVPR.2007.383170}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270195}, day = {22}, doi = {10.1109/CVPR.2007.383170}, journal = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, keywords = {activities, activity-recognition, augmenting, clustering, dynamics, mining, segmenting, sequences, signal-processing, streaming, streams, verbalizing, verbs, video, videos}, month = {June}, pages = {1--8}, posted-at = {2009-07-22 12:07:28}, priority = {2}, title = {From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems}, url = {http://dx.doi.org/10.1109/CVPR.2007.383170}, year = {2007} }

TY - CONF ID - citeulike:4446647 L3 - citeulike-article-id:4446647 N2 - Clustering video sequences in order to infer and extract activities from a single video stream is an extremely important problem and has significant potential in video indexing, surveillance, activity discovery and event recognition. Clustering a video sequence into activities requires one to simultaneously recognize activity boundaries (activity consistent subsequences) and cluster these activity subsequences. In order to do this, we build a generative model for activities (in video) using a cascade of dynamical systems and show that this model is able to capture and represent a diverse class of activities. We then derive algorithms to learn the model parameters from a video stream and also show how a single video sequence may be clustered into different clusters where each cluster represents an activity. We also propose a novel technique to build affine, view, rate invariance of the activity into the distance metric for clustering. Experiments show that the clusters found by the algorithm correspond to semantically meaningful activities. JF - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on EP - 8 TI - From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on SP - 1 KW - activities KW - activity-recognition KW - augmenting KW - clustering KW - dynamics KW - mining KW - segmenting KW - sequences KW - signal-processing KW - streaming KW - streams KW - verbalizing KW - verbs KW - video KW - videos AU - Turaga, PK AU - Veeraraghavan, A AU - Chellappa, R PY - 2007/06/22/ UR - http://dx.doi.org/10.1109/CVPR.2007.383170 ER -