Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2021

Abstract

Conventional textual-based causal knowledge acquisition methods typically require laborious and expensive human annotations. As a result, their scale is often limited. Moreover, as no context is provided during the annotation, the resulting causal knowledge records (e.g., ConceptNet) typically do not consider the context. In this paper, we move out of the textual domain to explore a more scalable way of acquiring causal knowledge and investigate the possibility of learning contextual causality from the visual signal. Specifically, we first propose a high-quality dataset Vis-Causal and then conduct experiments to demonstrate that with good language and visual representations, it is possible to discover meaningful causal knowledge from the videos. Further analysis also shows that the contextual property of causal relations indeed exists and considering the contextual property can help better predict the causal relation between events. The Vis-Causal dataset and experiment code are available at https://github.com/HKUST-KnowComp/Vis_Causal.

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville, TN, USA, June 19-25

First Page

1

Last Page

4

Identifier

10.1109/CVPRW53098.2021.00193

Publisher

IEEE

City or Country

Pistacataway

Additional URL

https://doi.org/https://doi.org/10.1109/CVPRW53098.2021.00193

Download

Share

COinS