comphyreasoning.github.io - ComPhy

Description: ComPhy: Compositional Physical Reasoning ofObjects and Events from Videos

video (50720) machine learning (3318) physics (1168) deep learning (1092) computer vision (736) reasoning (60)

Example domain paragraphs

Overview Abstract Example Dataset Paper & Code

Objects’ motions in nature are governed by complex interactions and their properties. While some properties, such as shape and material, can be identified via the object’s visual appearances, others like mass and electric charge are not directly visible. The compositionality between the visible and hidden properties poses unique challenges for AI models to reason from the physical world, whereas humans can effortlessly infer them with limited observations. Existing studies on video reasoning mainly focus on

In each example, models will be given one target video, four reference videos and a set of questions related to the target video. To answer the questions, the models need to unravel objects' compositional hidden properties, such as mass and charge, and use this knowledge to predict objects' dynamics.

Links to comphyreasoning.github.io (4)

yunzhuli.github.io Yunzhu Li
zfchenunique.github.io Zhenfang Chen
dingmyu.github.io Mingyu Ding - 丁明宇
mvcs-workshop.github.io CVPR2023 MVCS