Saptarshi Sinha's Photo

Saptarshi Sinha

I am currently a Ph.D. student working with Prof. Dima Damen at the School of Computer Science, University of Bristol. I am part of MaVi and ViLab. I was previously a computer vision researcher at Hitachi Research and Development, Japan. My research interest lies in computer vision, focusing primarily on long-term video understanding. I completed my Masters from IIT Bombay under the supervision of Prof. Subhasis Chaudhuri.


Activities


Publications

Every Shot Counts: Using Exemplars for Repetition Counting in Videos
Saptarshi Sinha, Alexandros Stergiou, Dima Damen
arXiv, 2024
[Webpage] [arXiv] [code]
MILA: memory-based instance-level adaptation for cross-domain object detection
Onkar Krishna, Hiroki Ohashi, Saptarshi Sinha
British Machine Vision Conference (BMVC), 2023
[arXiv] [code]
Use your head: Improving long-tail video recognition
Toby Perrett, Saptarshi Sinha, Tilo Burghardt, Majid Mirmehdi, Dima Damen
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[arXiv] [code] [page]
Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition
Saptarshi Sinha, Hiroki Ohashi
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
[arXiv] [code]
Class-difficulty based methods for long-tailed visual recognition
Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura
International Journal of Computer Vision (IJCV), 2022
[arXiv] [code]
Class-wise difficulty-balanced loss for solving class-imbalance
Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura
Asian Conference on Computer Vision (ACCV), 2020
[arXiv] [code]
NII Hitachi UIT at TRECVID 2019
Martin Klinkigt, Duy-Dinh Le, Atsushi Hiroike, Hung-Quoc Vo, Mohit Chabra, Vu-Minh-Hieu Dang, Quan Kong, Vinh-Tiep Nguyen, Tomokazu Murakami, Tien-Van Do 0002, Tomoaki Yoshinaga, Duy-Nhat Nguyen, Sinha Saptarshi, Thanh-Duc Ngo, Charles Limasanches, Tushar Agrawal, Jian Vora, Manikandan Ravikiran, Zheng Wang, Shin'ichi Satoh
TRECVID, 2019
[OpenReview]