What’s Different between Visual Question Answering for Machine “Understanding” Versus for Accessibility?
Open Access
- 1 January 2022
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 1025-1034
Abstract
Yang Trista Cao, Kyle Seelman, Kyungjun Lee, Hal Daumé III. Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2022.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Vision Skills Needed to Answer Visual QuestionsProceedings of the ACM on Human-Computer Interaction, 2020
- Design Lessons From AI’s Two Grand Goals: Human Emulation and Useful ApplicationsIEEE Transactions on Technology and Society, 2020
- Commonsense Reasoning for Natural Language Processing2020
- Beyond Bilinear: Generalized Multimodal Factorized High-Order Pooling for Visual Question AnsweringIEEE Transactions on Neural Networks and Learning Systems, 2018
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding2018
- VQA: Visual Question AnsweringInternational Journal of Computer Vision, 2016
- Visual challenges in the everyday lives of blind people2013
- The symbol grounding problemPhysica D: Nonlinear Phenomena, 1990