PhysScene: A scene graph dataset for scientific visual reasoning in physics experiments

Zou, Minghao, Zeng, Qingtian, Liu, Shangkun, Meng, Yanda, Yue, Guanghui, Zhao, Baoquan, Saddik, Abdulmotaleb El and Zhou, Wei 2026. PhysScene: A scene graph dataset for scientific visual reasoning in physics experiments. Presented at: 34th ACM International Conference on Multimedia, Rio de Janeiro, Brazil, 10-14 Nov 2026. Proceedings of the 34th ACM International Conference on Multimedia. ACM, p. 17089. 10.1145/3767308.3838663

PDF - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1MB)

Abstract

Scene Graphs (SGs) provide structured representations of visual scenes by modeling objects and their pairwise relationships. Despite recent progress, existing datasets primarily focus on generic natural contexts, leaving domain-specific and function-oriented scenes largely underexplored. This limitation restricts the evaluation of relational reasoning in scientific experimental scenes, thereby hindering the development of intelligent monitoring, analysis, and related applications in such scenes. To address this gap, we introduce PhysScene, the first SG dataset tailored to physics experiments. PhysScene encompasses specialized instruments, structured experimental setups, and functional relations intrinsic to experimental environments, enabling reasoning that extends beyond spatial co-occurrence to logical dependencies. Rather than pursuing large data scale, PhysScene focuses on strong semantic constraints and high relation density in experimental scenes, posing new challenges for existing scene parsing algorithms while offering opportunities for further improvements. Extensive analyses and experiments show that PhysScene complements existing benchmarks and establishes a valuable testbed for advancing scientific visual reasoning. The dataset is publicly available at https://github.com/ZMH-SDUST/PhysScene.

Item Type:	Conference or Workshop Item - published (UNSPECIFIED)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computational & Mathematical Sciences
Publisher:	ACM
ISBN:	9798400722134
Date of First Compliant Deposit:	12 November 2026
Last Modified:	12 Nov 2026 13:30
URI:	https://orca.cardiff.ac.uk/id/eprint/190885

Actions (repository staff only)

Edit Item