A
Amit K. Roy-Chowdhury
Researcher at University of California, Riverside
Publications - 311
Citations - 11469
Amit K. Roy-Chowdhury is an academic researcher from University of California, Riverside. The author has contributed to research in topics: Computer science & Activity recognition. The author has an hindex of 51, co-authored 288 publications receiving 9028 citations. Previous affiliations of Amit K. Roy-Chowdhury include University of Maryland, College Park & Bourns College of Engineering.
Papers
More filters
Proceedings ArticleDOI
Learning Temporal Regularity in Video Sequences
TL;DR: In this article, a generative model for regular motion patterns (termed as regularity) using multiple sources with very limited supervision is proposed, and two methods are built upon the autoencoders for their ability to work with little to no supervision.
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
Identification of humans using gait
Amit Kale,Aravind Sundaresan,A. N. Rajagopalan,Naresh P. Cuntoor,Amit K. Roy-Chowdhury,Volker Krüger,Rama Chellappa +6 more
TL;DR: A view-based approach to recognize humans from their gait by employing a hidden Markov model (HMM) and the statistical nature of the HMM lends overall robustness to representation and recognition.
Journal ArticleDOI
Matching shape sequences in video with applications in human movement analysis
TL;DR: This work suggests a modification of the dynamic time-warping algorithm to include the nature of the non-Euclidean space in which the shape deformations take place and shows the efficacy of this algorithm by its application to gait-based human recognition.
Posted Content
Learning Temporal Regularity in Video Sequences
TL;DR: This work proposes two methods that are built upon the autoencoders for their ability to work with little to no supervision, and builds a fully convolutional feed-forward autoencoder to learn both the local features and the classifiers as an end-to-end learning framework.