CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering
This addresses the challenge of inferring unseen physical properties in AI systems, but it is incremental as it builds on prior VQA work with a new dataset.
The authors tackled the problem of reasoning about implicit physical properties like mass from videos by introducing CRIPP-VQA, a new video question answering dataset, and found a significant performance gap where models struggle with implicit properties compared to explicit ones.
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).