B
Bi Song
Researcher at University of California, Riverside
Publications - 34
Citations - 2100
Bi Song is an academic researcher from University of California, Riverside. The author has contributed to research in topics: Video tracking & Activity recognition. The author has an hindex of 18, co-authored 34 publications receiving 1897 citations. Previous affiliations of Bi Song include University of Science and Technology of China & University of California.
Papers
More filters
Proceedings ArticleDOI
A large-scale benchmark dataset for event recognition in surveillance video
Sangmin Oh,Anthony Hoogs,A. G. Amitha Perera,Naresh P. Cuntoor,Chia-Chih Chen,Jong Taek Lee,Saurajit Mukherjee,Jake K. Aggarwal,Hyungtae Lee,Larry S. Davis,Eran Swears,Xioyang Wang,Qiang Ji,Kishore K. Reddy,Mubarak Shah,Carl Vondrick,Hamed Pirsiavash,Deva Ramanan,Jenny Yuen,Antonio Torralba,Bi Song,Anesco Fong,Amit K. Roy-Chowdhury,Mita Desai +23 more
TL;DR: A new large-scale video dataset designed to assess the performance of diverseVisual event recognition algorithms with a focus on continuous visual event recognition (CVER) in outdoor areas with wide coverage is introduced.
Journal ArticleDOI
Tracking and Activity Recognition Through Consensus in Distributed Camera Networks
TL;DR: This paper investigates distributed scene analysis algorithms by leveraging upon concepts of consensus that have been studied in the context of multiagent systems, but have had little applications in video analysis.
Proceedings ArticleDOI
A “string of feature graphs” model for recognition of complex activities in natural videos
TL;DR: A new feature model based on a string representation of the video which respects the spatio-temporal ordering is proposed, which is able to identify the region of interest in a cluttered scene, and gives reasonable performance with even a single query example.
Journal ArticleDOI
Collaborative Sensing in a Distributed PTZ Camera Network
TL;DR: This paper proposes an integrated analysis and control framework for a pan, tilt, zoom (PTZ) camera network in order to maximize various scene understanding performance criteria through dynamic camera-to-target assignment and efficient feature acquisition.
Book ChapterDOI
A stochastic graph evolution framework for robust multi-target tracking
TL;DR: This paper considers the problem of long-term tracking in video in application domains where context information is not available a priori, nor can it be learned online, and builds the solution on the hypothesis that most existing trackers can obtain reasonable short-term tracks.