Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning

Zhiyuan Fang, Tejas Gokhale, Pratyay Banerjee, Chitta Baral, Yezhou Yang


Abstract
Captioning is a crucial and challenging task for video understanding. In videos that involve active agents such as humans, the agent’s actions can bring about myriad changes in the scene. Observable changes such as movements, manipulations, and transformations of the objects in the scene, are reflected in conventional video captioning. Unlike images, actions in videos are also inherently linked to social aspects such as intentions (why the action is taking place), effects (what changes due to the action), and attributes that describe the agent. Thus for video understanding, such as when captioning videos or when answering questions about videos, one must have an understanding of these commonsense aspects. We present the first work on generating commonsense captions directly from videos, to describe latent aspects such as intentions, effects, and attributes. We present a new dataset “Video-to-Commonsense (V2C)” that contains ~9k videos of human agents performing various actions, annotated with 3 types of commonsense descriptions. Additionally we explore the use of open-ended video-based commonsense question answering (V2C-QA) as a way to enrich our captions. Both the generation task and the QA task can be used to enrich video captions.
Anthology ID:
2020.emnlp-main.61
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
840–860
Language:
URL:
https://aclanthology.org/2020.emnlp-main.61
DOI:
10.18653/v1/2020.emnlp-main.61
Bibkey:
Cite (ACL):
Zhiyuan Fang, Tejas Gokhale, Pratyay Banerjee, Chitta Baral, and Yezhou Yang. 2020. Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 840–860, Online. Association for Computational Linguistics.
Cite (Informal):
Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning (Fang et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.61.pdf
Video:
 https://slideslive.com/38938840
Code
 jacobswan1/Video2Commonsense +  additional community code
Data
V2C