# Compositional Physical Reasoning of Objects and Events from Videos

arXiv: https://arxiv.org/abs/2408.02687 · HTML: https://mlsanity.com/paper/2408.02687/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 71 references that are in the map.
- First posted on arXiv 2 Aug 2024.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Learning to Simulate Complex Physics with Graph Networks](https://mlsanity.com/paper/2002.09405/) (2020)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering](https://mlsanity.com/paper/1704.04497/) (2017)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/1802.04687/) (2018)
- [MovieQA: Understanding Stories in Movies through Question-Answering](https://mlsanity.com/paper/1512.02902/) (2015)
- [Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding](https://mlsanity.com/paper/1810.02338/) (2018)
- [Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids](https://mlsanity.com/paper/1810.01566/) (2018)
- [Compositional Attention Networks for Machine Reasoning](https://mlsanity.com/paper/1803.03067/) (2018)
- [Hierarchical Conditional Relation Networks for Video Question Answering](https://mlsanity.com/paper/2002.10698/) (2020)
- [TVQA+: Spatio-Temporal Grounding for Video Question Answering](https://mlsanity.com/paper/1904.11574/) (2019)
- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)

## Built on by (most cited first, 12 of 12)

- [PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos](https://mlsanity.com/paper/2412.01800/) (2024)
- [Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics](https://mlsanity.com/paper/2411.11467/) (2024)
- [One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs](https://mlsanity.com/paper/2408.12674/) (2024)
- [Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI](https://mlsanity.com/paper/2510.04978/) (2025)
- [InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning](https://mlsanity.com/paper/2509.12263/) (2025)
- [Rethinking Object-Centric Representations for Video Dynamics Modeling](https://mlsanity.com/paper/2606.23436/) (2026)
- [Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos](https://mlsanity.com/paper/2601.16471/) (2026)
- [Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning](https://mlsanity.com/paper/2605.15967/) (2026)
- [SRNN: Spatiotemporal Relational Neural Network for Intuitive Physics Understanding](https://mlsanity.com/paper/2511.06761/) (2025)
- [ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?](https://mlsanity.com/paper/2606.07962/) (2026)
- [ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting](https://mlsanity.com/paper/2608.20009/) (2026)
- [World Embedding Benchmark](https://mlsanity.com/paper/2610.03632/) (2026)

## Abstract (arXiv)

Understanding and reasoning about objects' physical properties in the natural world is a fundamental challenge in artificial intelligence. While some properties like colors and shapes can be directly observed, others, such as mass and electric charge, are hidden from the objects' visual appearance. This paper addresses the unique challenge of inferring these hidden physical properties from objects' motion and interactions and predicting corresponding dynamics based on the inferred physical properties. We first introduce the Compositional Physical Reasoning (ComPhy) dataset. For a given set of objects, ComPhy includes limited videos of them moving and interacting under different initial conditions. The model is evaluated based on its capability to unravel the compositional hidden properties, such as mass and charge, and use this knowledge to answer a set of questions. Besides the synthetic videos from simulators, we also collect a real-world dataset to show further test physical reasoning abilities of different models. We evaluate state-of-the-art video reasoning models on ComPhy and reveal their limited ability to capture these hidden properties, which leads to inferior performance. We also propose a novel neuro-symbolic framework, Physical Concept Reasoner (PCR), that learns and reasons about both visible and hidden physical properties from question answering. After training, PCR demonstrates remarkable capabilities. It can detect and associate objects across frames, ground visible and hidden physical properties, make future and counterfactual predictions, and utilize these extracted representations to answer challenging questions.