Dhruv Batra

Dhruv is a Research Scientist at Facebook AI Research, and a faculty member in the School of Interactive Computing at Georgia Tech. He received his Ph.D. from Carnegie Mellon University, and is the recipient of the Presidential Early Career Award for Scientists and Engineers 2019, as well as a number of career and best paper awards.

Dhruv's Publications

April 07, 2020

RESEARCH

COMPUTER VISION

Improving Generative Visual Dialog by Answering Diverse Questions

Prior work on training generative Visual Dialog models with reinforcement learning (Das et al., 2017b) has explored a Q-BOT-A-BOT image-guessing game and shown that this ‘self-talk’ approach can lead to improved performance at the downstream…

Vishvak Murahari, Prithvijit Chattopadhyay, Dhruv Batra, Devi Parikh, Abhishek Das,

April 07, 2020

April 07, 2020

RESEARCH

COMPUTER VISION

Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded

Many vision and language models suffer from poor visual grounding – often falling back on easy-to-learn language priors rather than basing their decisions on visual concepts in the image. In this work, we propose a generic approach called Human…

Ramprasaath R. Selvaraju, Stefan Lee, Yilin Shen, Hongxia Jin, Shalini Ghosh, Larry Heck, Dhruv Batra, Devi Parikh,

April 07, 2020

April 07, 2020

RESEARCH

COMPUTER VISION

NoCaps: Novel object captioning at scale

Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger variety of…

Harsh Agrawal, Karan Desai, Yufei Wang, Xinlei Chen, Rishabh Jain, Mark Johnson, Dhruv Batra, Devi Parikh, Stefan Lee, Peter Anderson,

April 07, 2020