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

Maitreya Patel, Tejas Gokhale, Chitta Baral, Yezhou Yang

Research output: Contribution to conferencePaperpeer-review

2 Scopus citations

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).

Original languageEnglish (US)
Pages9856-9870
Number of pages15
StatePublished - 2022
Event2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Abu Dhabi, United Arab Emirates
Duration: Dec 7 2022Dec 11 2022

Conference

Conference2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period12/7/2212/11/22

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering'. Together they form a unique fingerprint.

Cite this