Y
Yash Goyal
Researcher at Virginia Tech
Publications - 25
Citations - 2934
Yash Goyal is an academic researcher from Virginia Tech. The author has contributed to research in topics: Question answering & Active listening. The author has an hindex of 14, co-authored 22 publications receiving 1962 citations. Previous affiliations of Yash Goyal include Indian Institute of Technology Gandhinagar & Georgia Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
TL;DR: The authors balance the VQA dataset by collecting complementary images such that every question in the balanced dataset is associated with not just a single image, but rather a pair of similar images that result in two different answers to the same question.
Proceedings Article
Counterfactual Visual Explanations
TL;DR: In this article, a technique to produce counterfactual visual explanations was developed for fine-grained bird classification, where a visual explanation identifies how a query image could change such that the system would output a different specified class.
Proceedings ArticleDOI
Yin and Yang: Balancing and Answering Binary Visual Questions
TL;DR: In this article, the authors address binary visual question answering (VQA) on abstract scenes by converting the question to a tuple that concisely summarizes the visual concept to be detected in the image.
Posted Content
Explaining Classifiers with Causal Concept Effect (CaCE).
TL;DR: This work defines the Causal Concept Effect (CaCE) as the causal effect of a human-interpretable concept on a deep neural net's predictions, and shows that the CaCE measure can avoid errors stemming from confounding.
Journal ArticleDOI
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
Yash Goyal,Tejas Khot,Aishwarya Agrawal,Douglas Summers-Stay,Dhruv Batra,Dhruv Batra,Devi Parikh,Devi Parikh +7 more
TL;DR: This work balances the popular VQA dataset by collecting complementary images such that every question in the authors' balanced dataset is associated with not just a single image, but rather a pair of similar images that result in two different answers to the question.