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
Proceedings Article
SubmodBoxes: near-optimal search for a set of diverse object proposals
Qing Sun,Dhruv Batra +1 more
TL;DR: This paper formulates the search for a set of bounding boxes as a monotone submodular maximization problem over the space of all possible bounded boxes in an image as a Branch-and-Bound scheme and shows that this approach leads to a state-of-art performance on object proposal generation via a novel diversity measure.
Proceedings Article
Auxiliary Tasks and Exploration Enable ObjectGoal Navigation
Posted Content
End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features
Chiori Hori,Huda Alamri,Jue Wang,Gordon Wichern,Takaaki Hori,Anoop Cherian,Tim K. Marks,Vincent Cartillier,Raphael Gontijo Lopes,Abhishek Das,Irfan Essa,Dhruv Batra,Devi Parikh +12 more
TL;DR: In this article, an end-to-end conversation model was trained to generate responses in a dialog about a video, where the dialog is a typed conversation that consists of a sequence of 10 question-and-answer (QA) pairs between two Amazon Mechanical Turk workers.
Posted Content
Habitat 2.0: Training Home Assistants to Rearrange their Habitat
Andrew Szot,Alexander Clegg,Eric Undersander,Erik Wijmans,Yili Zhao,John Turner,Noah Maestre,Mustafa Mukadam,Devendra Singh Chaplot,Oleksandr Maksymets,Aaron Gokaslan,Vladimir Vondrus,Sameer Dharur,Franziska Meier,Wojciech Galuba,Angel X. Chang,Zsolt Kira,Vladlen Koltun,Jitendra Malik,Manolis Savva,Dhruv Batra +20 more
TL;DR: H2.0 as discussed by the authors is a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios, which includes a suite of common tasks for assistive robots (tidy the house, prepare groceries, set the table).
Journal ArticleDOI
Putting the User in the Loop for Image-Based Modeling
TL;DR: The task of recovering the 3D structure as a discrete optimization problem solved via energy minimization is formulated and an algorithm where the user guides the process of image-based modeling to find and model the object of interest by manually interacting with the nodes of the graph is introduced.