Modular Visual Question Answering via Code Generation
Sanjay Subramanian, Medhini Narasimhan, Kushal Khangaonkar, Kevin Yang, Arsha Nagrani, Cordelia Schmid, Andy Zeng, Trevor Darrell, Dan Klein
Abstract
Sanjay Subramanian, Medhini Narasimhan, Kushal Khangaonkar, Kevin Yang, Arsha Nagrani, Cordelia Schmid, Andy Zeng, Trevor Darrell, Dan Klein. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2023.
Topics & Concepts
Programming languageModular designComputer scienceComputational linguisticsQuestion answeringCode (set theory)Natural language processingSet (abstract data type)Multimodal Machine Learning ApplicationsVideo Analysis and SummarizationHuman Pose and Action Recognition