A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video

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 type...

• Type: Journal
• Year: 2011
• Where: CVPR
• Authors: Sangmin Oh, Anthony Hoogs, A.G.Amitha Perera, Chia-Chih Chen, Jong Taek Lee, Jake Aggarwal, Hyungtae Lee, Larry Davis, Xiaoyang Wang, Eran Swears, Qiang Ji, Kishore Reddy, Mubarak Shah, Carl Vondrick, Hamed Pirsiavash, Deva Ramanan, Jenny Yuen, Antonio Torralba, Bi Song, Anesco Fong, Amit Roy-Chowdhury, Mita Desai
• Keywords: Computer Vision, CVPR 2011, Dataset, Diverse Visual Event, Visual Event Recognition