Bharat Singh

me

About Me

I am a PhD student in Computer Science department at University of Maryland, College Park. My advisor is Prof. Larry Davis . I received my Bachelor's and Master's degree in Computer Science from IIT Madras. My research interests are in Computer Vision and Machine Learning.



Multi-GPU Faster-RCNN/R-FCN training code for Caffe is available here

Publications:

Fast-AT: Fast Automatic Thumbnail Generation using Deep Neural Networks: Seyed A. Esmaeili, Bharat Singh, and Larry S. Davis, CVPR 2017 arXiv

VRFP: On-the-fly Video Retrieval using Web Images and Fast Fisher Vector Products: Xintong Han, Bharat Singh, Vlad I. Morariu and Larry S. Davis, IEEE Transactions on Multimedia, TMM 2017 pdf

Son of Zorn's Lemma: Targetted Style Transfer Using Instance-Aware Semantic Segmentation: Carlos Castillo, Soham De, Xintong Han, Bharat Singh, Abhay Kumar Yadav, and Tom Goldstein , ICASSP 2017 (oral) pdf

A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection: Bharat Singh, Michael Jones, Tim Marks, Oncel Tuzel and Ming Shao, CVPR 2016 pdf dataset+results ActivityNet Video

Training Neural Networks Without Gradients: A Scalable ADMM Approach: Gavin Taylor, Ryan Burmeister, Zheng Xu, Bharat Singh, Ankit Patel and Tom Goldstein, ICML 2016 pdf

Selecting Relevant Web Trained Concepts for Automated Event Retrieval: Bharat Singh, Xintong Han, Zhe Wu, Vlad I. Morariu and Larry S. Davis, ICCV 2015 pdf

Layer-Specific Adaptive Learning Rates for Deep Networks: Bharat Singh, Soham De, Yangmuzi Zhang, Tom Goldstein and Gavin Taylor, ICMLA 2015 pdf

Quasi Real-Time Sub-Space 3D Deformable Fusion: Bharat Singh, Stavros Alchatzidis and Nikos Paragios, ISBI 2015 (Oral) pdf

PSPGC: Part-Based Seeds for Parametric Graph-Cuts: Bharat Singh, Xintong Han, Zhe Wu and Larry S. Davis, ACCV 2014 pdf

Contact:

Bharat Singh,
3362, A. V. Williams Building,
University of Maryland,
College Park - 20742

Email: bharat [at] cs [dot] umd [dot] edu