CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering

Maitreya Patel, Tejas Gokhale, Chitta Baral, Yezhou Yang


Abstract
Videos often capture objects, their visible properties, their motion, and the interactions between different objects. Objects also have physical properties such as mass, which the imaging pipeline is unable to directly capture. However, these properties can be estimated by utilizing cues from relative object motion and the dynamics introduced by collisions. In this paper, we introduce CRIPP-VQA, a new video question answering dataset for reasoning about the implicit physical properties of objects in a scene. CRIPP-VQA contains videos of objects in motion, annotated with questions that involve counterfactual reasoning about the effect of actions, questions about planning in order to reach a goal, and descriptive questions about visible properties of objects. The CRIPP-VQA test set enables evaluation under several out-of-distribution settings – videos with objects with masses, coefficients of friction, and initial velocities that are not observed in the training distribution. Our experiments reveal a surprising and significant performance gap in terms of answering questions about implicit properties (the focus of this paper) and explicit properties of objects (the focus of prior work).
Anthology ID:
2022.emnlp-main.670
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9856–9870
Language:
URL:
https://aclanthology.org/2022.emnlp-main.670
DOI:
10.18653/v1/2022.emnlp-main.670
Bibkey:
Cite (ACL):
Maitreya Patel, Tejas Gokhale, Chitta Baral, and Yezhou Yang. 2022. CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9856–9870, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering (Patel et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2022.emnlp-main.670.pdf