D
Dhruv Batra
Researcher at Georgia Institute of Technology
Publications - 272
Citations - 43803
Dhruv Batra is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Question answering & Dialog box. The author has an hindex of 69, co-authored 272 publications receiving 29938 citations. Previous affiliations of Dhruv Batra include Facebook & Toyota Technological Institute at Chicago.
Papers
More filters
Posted Content
Chasing Ghosts: Instruction Following as Bayesian State Tracking
TL;DR: This work forms an end-to-end differentiable Bayes filter and trains it to identify the goal by predicting the most likely trajectory through the map according to the instructions, constituting a new approach to instruction following that explicitly models a probability distribution over states.
Proceedings ArticleDOI
Learning the right model: Efficient max-margin learning in Laplacian CRFs
Dhruv Batra,Ashutosh Saxena +1 more
TL;DR: This paper shows that structured hinge-loss is non-convex for LCRFs and thus techniques used by previous works are not applicable, and presents the first approximate max-margin algorithm for L CRFs, and makes the learning algorithm scalable in the number of training images by using dual-decomposition techniques.
Posted Content
Dialog System Technology Challenge 7.
Koichiro Yoshino,Chiori Hori,Julien Perez,Luis Fernando D'Haro,Lazaros Polymenakos,R. Chulaka Gunasekara,Walter S. Lasecki,Jonathan K. Kummerfeld,Michel Galley,Chris Brockett,Jianfeng Gao,Bill Dolan,Xiang Gao,Huda Alamri,Tim K. Marks,Devi Parikh,Dhruv Batra +16 more
TL;DR: This paper summarizes the overall setup and results of DSTC7, including detailed descriptions of the different tracks and provided datasets, and describes overall trends in the submitted systems and the key results.
Posted Content
Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7.
Huda Alamri,Vincent Cartillier,Raphael Gontijo Lopes,Abhishek Das,Jue Wang,Irfan Essa,Dhruv Batra,Devi Parikh,Anoop Cherian,Tim K. Marks,Chiori Hori +10 more
TL;DR: The Audio Visual Scene Aware Dialog (AVSD) challenge and dataset is introduced, which is to build a system that generates responses in a dialog about an input video.
Proceedings ArticleDOI
The Promise of Premise: Harnessing Question Premises in Visual Question Answering
TL;DR: In this article, the authors make a simple observation that questions about images often contain premises, and that reasoning about premises can help VQA models respond more intelligently to irrelevant or previously unseen questions.