AI Paper Atlas

Research map / Video / Video-language understanding

Compositional Physical Reasoning of Objects and Events From Videos

Zhenfang Chen, Shilong Dong, Kexin Yi, Yunzhu Li, Mingyu Ding, Antonio B. Torralba, Joshua B. Tenenbaum, Chuang Gan

TPAMI 2025 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 65 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add reference videos for property learning (ablation)PCR · ComPhy (validation set)factual accuracy: 68.7 -> 78.3Improved
add reference videos for property learning (ablation)PCR · ComPhy (validation set)predictive accuracy (per question): 28.1 -> 56.5Improved
add reference videos for property learning (ablation)PCR · ComPhy (validation set) concept learningcharge classification accuracy: 45.0 -> 68.1Improved
add counterfactual imagination (ablation)PCR · ComPhy (validation set)counterfactual accuracy (per question): 28.0 -> 50.2Improved
add counterfactual imagination (ablation)PCR · ComPhy (validation set)factual accuracy: 70.3 -> 78.3Improved
add counterfactual imagination (ablation)PCR · ComPhy (validation set) concept learningcharge classification accuracy: 44.8 -> 68.1Improved
replace CPL with PCR (no dense property labels)CPL · ComPhy (test set)predictive accuracy (per question): 56.4 -> 62.0Improved
replace CPL with PCR (no dense property labels)CPL · ComPhy (test set)factual accuracy: 80.5 -> 76.0Hurt
add reference videos as input to ALOEALOE · ComPhyfactual accuracy: 54.3 -> 57.7Improved
add reference videos as input to MACMAC · ComPhyfactual accuracy: 68.6 -> 65.8Hurt
use large vision-language model GPT-4V instead of ALOEALOE · ComPhycounterfactual accuracy (per question): 20.8 -> 8.9Hurt
use PCR instead of MACMAC · ComPhy-DIVfactual accuracy: 51.7 -> 68.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy