A
Abhishek Das
Researcher at Facebook
Publications - 61
Citations - 15366
Abhishek Das is an academic researcher from Facebook. The author has contributed to research in topics: Dialog box & Computer science. The author has an hindex of 27, co-authored 52 publications receiving 9447 citations. Previous affiliations of Abhishek Das include Georgia Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions?
TL;DR: In this article, the VQA-HAT (Human ATtention) dataset was introduced to evaluate attention maps generated by state-of-the-art VQAs against human attention.
Neural Modular Control for Embodied Question Answering.
TL;DR: This work uses imitation learning to warm-start policies at each level of the hierarchy, dramatically increasing sample efficiency, followed by reinforcement learning, for learning policies for navigation over long planning horizons from language input.
Posted Content
TarMAC: Targeted Multi-Agent Communication
Abhishek Das,Théophile Gervet,Joshua Romoff,Dhruv Batra,Devi Parikh,Michael G. Rabbat,Joelle Pineau +6 more
TL;DR: The authors proposed a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments.
Book ChapterDOI
Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline
TL;DR: This article adapt the ViLBERT model for multi-turn visually-grounded conversations, which is pretrained on Conceptual Captions and Visual Question Answering datasets, and finetuned on VisDial.
Posted Content
Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline
TL;DR: This work adapts the recently proposed ViLBERT model for multi-turn visually-grounded conversations and finds that additional finetuning using "dense" annotations in VisDial leads to even higher NDCG but hurts MRR, highlighting a trade-off between the two primary metrics.