Vijay Kumar
I am currently a computer vision engineer at Meta Reality Labs, Zurich. Previously, I worked as a senior data scientist at Walmart Labs Bangalore where I worked on recommendation systems for online e-commerce applications. Before that, I completed my post-doctoral researcher in the Willow team at INRIA Paris where I worked with Ivan Laptev. I obtained my PhD at IIIT Hyderabad under the guidance of Prof. C V Jawahar and Prof. Anoop Namboodiri.
I am interested in computer vision and machine learning specifically on human understanding in images and videos.
Email  / 
CV  / 
LinkedIn  / 
Google Scholar  / 
Github
|
|
Selected publications
|
Semi-Supervised Visual Representation Learning for Fashion Compatability
Ambareesh R,
Vijay Kumar,
Deepthi Sharma
ACM Recommender Systems (RecSys), 2021
|
Long term spatio-temporal modeling for action detection
Makarand Tapaswi*,
Vijay Kumar*,
Ivan Laptev
* indicate equal contribution
Computer Vision and Image Understanding Journal, 2021
|
Region Pooling with Adaptive Feature Fusion for End-to-End Person Recognition
Vijay Kumar,
Anoop Namboodiri,
C V Jawahar
Winter Conference on Applications of Computer Vision (WACV), 2020
|
Semi-supervised annotation of faces in image collection
Vijay Kumar,
Anoop Namboodiri,
C V Jawahar
Signal, Image and Video Processing Journal (SIVP), 2018
|
Pose-aware Person Recognition
Vijay Kumar,
Anoop Namboodiri,
Manohar Paluri,
C V Jawahar
IEEE Computer Vision and Pattern Recognition (CVPR), 2017
|
Visual phrases for exemplar face detection
Vijay Kumar,
Anoop Namboodiri,
C V Jawahar
IEEE International Conference on Computer Vision (ICCV) , 2015
|
|