S
Santanu Chaudhury
Researcher at Indian Institute of Technology, Jodhpur
Publications - 389
Citations - 4361
Santanu Chaudhury is an academic researcher from Indian Institute of Technology, Jodhpur. The author has contributed to research in topics: Ontology (information science) & Deep learning. The author has an hindex of 28, co-authored 380 publications receiving 3691 citations. Previous affiliations of Santanu Chaudhury include Central Electronics Engineering Research Institute & Indian Institute of Technology Delhi.
Papers
More filters
Proceedings ArticleDOI
Dynamic texture synthesis for video compression
TL;DR: A dynamic texture based compression scheme is devised for videos for the analysis of motion patterns in a video on the basis of optic flow data and then clusters of different motion patterns are created.
Proceedings ArticleDOI
Search result diversification in Flickr
TL;DR: This paper demonstrates how existing image search result diversification method can be extended to incorporate social tag information and shows that incorporating social tag features in some of the popular diversification algorithms results in improvement over baseline numbers.
Book ChapterDOI
Unusual Activity Analysis in Video Sequences
TL;DR: A unique representation scheme for events in an area under surveillance is presented, which provides a mechanism to analyze videos from multiple perspectives for unusual activity analysis and proposes clustering in event component spaces and defines algebraic operations on these clusters to find co-occurrences of event components.
Proceedings ArticleDOI
Image Analogy Based Document Image Compression
TL;DR: An image analogy based super-resolution technique that can be used as an effective tool for document image compression and multi-resolution viewing of the document.
Proceedings ArticleDOI
A connectionist network for simultaneous perception of multiple categories
TL;DR: A connectionist network is presented for simultaneous perception of multiple categories that provide an adequate explanation of the input features originating from multiple classes.