Dhruv Mahajan
Dhruv Mahajan is a research scientist on the Computer Vision team, which is part of Applied Machine Learning. Dhruv joined Facebook Research in January 2017. Prior to joining Facebook, he worked at Microsoft, MSR India and Yahoo! Research. Dhruv's research interests lie in computer vision and large scale and distributed machine learning. In computer vision, he is interested in extreme classification and ranking problems with huge scale both in terms of number of data points and labels and video understanding. Dhruv is also interested in new and efficient distributed optimization algorithms respecting system constraints like communication and machine failures.
Dhruv's Publications
June 18, 2020
RESEARCH
COMPUTER VISION
Scaling and Benchmarking Self-Supervised Visual Representation Learning
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning – the ability to scale to large amount of data because self-supervision requires…
Priya Goyal, Dhruv Mahajan, Abhinav Gupta, Ishan Misra
June 18, 2020
June 18, 2020
RESEARCH
SPEECH & AUDIO
Large-scale weakly-supervised pre-training for video action recognition
Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of using…
Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Hen Wang, Dhruv Mahajan
June 18, 2020
June 18, 2020
RESEARCH
COMPUTER VISION
What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
The ability to capture temporal information has been critical to the development of video understanding models. While there have been numerous attempts at modeling motion in videos, an explicit analysis of the effect of temporal information for video…
De-An Huang, Vignesh Ramanathan, Dhruv Mahajan, Lorenzo Torresani, Manohar Paluri, Li Fei-Fei, Juan Carlos Niebles
June 18, 2020
