Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering

Ahjeong Seo, Gi-Cheon Kang, Joonhan Park, Byoung-Tak Zhang


Abstract
Video Question Answering is a task which requires an AI agent to answer questions grounded in video. This task entails three key challenges: (1) understand the intention of various questions, (2) capturing various elements of the input video (e.g., object, action, causality), and (3) cross-modal grounding between language and vision information. We propose Motion-Appearance Synergistic Networks (MASN), which embed two cross-modal features grounded on motion and appearance information and selectively utilize them depending on the question’s intentions. MASN consists of a motion module, an appearance module, and a motion-appearance fusion module. The motion module computes the action-oriented cross-modal joint representations, while the appearance module focuses on the appearance aspect of the input video. Finally, the motion-appearance fusion module takes each output of the motion module and the appearance module as input, and performs question-guided fusion. As a result, MASN achieves new state-of-the-art performance on the TGIF-QA and MSVD-QA datasets. We also conduct qualitative analysis by visualizing the inference results of MASN.
Anthology ID:
2021.acl-long.481
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6167–6177
Language:
URL:
https://aclanthology.org/2021.acl-long.481
DOI:
10.18653/v1/2021.acl-long.481
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.481.pdf
Code
 ahjeongseo/MASN-pytorch
Data
Visual Question Answering