@conference {13074, title = {A large-scale benchmark dataset for event recognition in surveillance video}, booktitle = {Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on}, year = {2011}, month = {2011/06//}, pages = {3153 - 3160}, abstract = {We introduce a new large-scale video dataset designed to assess the performance of diverse visual event recognition algorithms with a focus on continuous visual event recognition (CVER) in outdoor areas with wide coverage. Previous datasets for action recognition are unrealistic for real-world surveillance because they consist of short clips showing one action by one individual [15, 8]. Datasets have been developed for movies [11] and sports [12], but, these actions and scene conditions do not apply effectively to surveillance videos. Our dataset consists of many outdoor scenes with actions occurring naturally by non-actors in continuously captured videos of the real world. The dataset includes large numbers of instances for 23 event types distributed throughout 29 hours of video. This data is accompanied by detailed annotations which include both moving object tracks and event examples, which will provide solid basis for large-scale evaluation. Additionally, we propose different types of evaluation modes for visual recognition tasks and evaluation metrics along with our preliminary experimental results. We believe that this dataset will stimulate diverse aspects of computer vision research and help us to advance the CVER tasks in the years ahead.}, keywords = {algorithm;evaluation, CVER, databases;, databases;video, dataset;moving, event, metrics;large-scale, object, recognition, recognition;diverse, recognition;video, scenes;surveillance, surveillance;visual, tasks;computer, tracks;outdoor, video, video;computer, vision;continuous, vision;image, visual}, doi = {10.1109/CVPR.2011.5995586}, author = {Oh,Sangmin and Hoogs, A. and Perera,A. and Cuntoor, N. and Chen,Chia-Chih and Lee,Jong Taek and Mukherjee,S. and Aggarwal, JK and Lee,Hyungtae and Davis, Larry S. and Swears,E. and Wang,Xioyang and Ji,Qiang and Reddy,K. and Shah,M. and Vondrick,C. and Pirsiavash,H. and Ramanan,D. and Yuen,J. and Torralba,A. and Song,Bi and Fong,A. and Roy-Chowdhury, A. and Desai,M.} }