S
Sujoy Kumar Biswas
Researcher at IBM
Publications - 24
Citations - 423
Sujoy Kumar Biswas is an academic researcher from IBM. The author has contributed to research in topics: Centrality & Deep learning. The author has an hindex of 9, co-authored 23 publications receiving 312 citations. Previous affiliations of Sujoy Kumar Biswas include University of California, San Francisco & Indian Statistical Institute.
Papers
More filters
Journal ArticleDOI
Linear Support Tensor Machine With LSK Channels: Pedestrian Detection in Thermal Infrared Images
TL;DR: This work proposes a mid-level attribute in the form of the multidimensional template, or tensor, using local steering kernel (LSK) as low-level descriptors for detecting pedestrians in far infrared images, facilitating very fast and efficient pedestrian localization.
Journal ArticleDOI
Quanti.us: a tool for rapid, flexible, crowd-based annotation of images.
Alex J. Hughes,Joseph D Mornin,Sujoy Kumar Biswas,Lauren E. Beck,David P. Bauer,Arjun Raj,Simone Bianco,Simone Bianco,Zev J. Gartner +8 more
TL;DR: This paper describes and characterizes a tool that allows researchers to crowdsource image-annotation tasks and shows equivalent deep learning performance for Quanti.us-derived and expert-derived annotations, which should allow scalable integration with tailored machine learning algorithms.
Journal ArticleDOI
Linear Support Tensor Machine: Pedestrian Detection in Thermal Infrared Images.
TL;DR: In this paper, a multidimensional template, or tensor, using Local Steering Kernel (LSK) as low-level descriptors for detecting pedestrians in far infrared images is proposed.
Journal ArticleDOI
Recognizing Human Action at a Distance in Video by Key Poses
TL;DR: A graph theoretic technique for recognizing human actions at a distance in a video by modeling the visual senses associated with poses and introduces a “meaningful” threshold on centrality measure that selects key poses for each action type.
Journal ArticleDOI
Recognizing Architectural Distortion in Mammogram: A Multiscale Texture Modeling Approach with GMM
TL;DR: The results obtained on two publicly available datasets, namely Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM), demonstrate the efficacy of the proposed approach.