MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question AnsweringDownload PDFOpen Website

Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang, Tetsuya Sakai

2021 (modified: 30 Mar 2022)EMNLP (Findings) 2021Readers: Everyone
Abstract: Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang, Tetsuya Sakai. Findings of the Association for Computational Linguistics: EMNLP 2021. 2021.
0 Replies