Paper Detail
Liyang Wang, Zeyu Zhang, Hao Tang
Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview and 3D scene reasoning. Existing methods such as MSG learn scene graph embeddings in Euclidean space using contrastive learning and attention based association. However, Euclidean geometry does not explicitly capture hierarchical entailment relationships between places and objects, limiting the structural consistency of learned representations. To address this, we propose Hyperbolic Scene Graph (HSG), which learns scene graph embeddings in hyperbolic space where hierarchical relationships are naturally encoded through geometric distance. Our results show that HSG improves hierarchical structure quality while maintaining strong retrieval performance. The largest gains are observed in graph level metrics: HSG achieves a PP IoU of 33.17 and the highest Graph IoU of 33.51, outperforming the best AoMSG variant (25.37) by 8.14, highlighting the effectiveness of hyperbolic representation learning for scene graph modeling. Code: https://github.com/AIGeeksGroup/HSG.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{wang2026hsg,
title = {HSG: Hyperbolic Scene Graph},
author = {Liyang Wang and Zeyu Zhang and Hao Tang},
year = {2026},
abstract = {Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview and 3D scene reasoning. Existing methods such as MSG learn scene graph embeddings in Euclidean space using contrastive learning and attention based association. However, Euclidean geometry does not explicitly capture hierarchical entailment relationships between places and objects, limiting the structural consistency of learned representations. T},
url = {https://huggingface.co/papers/2604.17454},
keywords = {scene graph representations, Euclidean space, hyperbolic space, hierarchical entailment relationships, contrastive learning, attention based association, scene graph embeddings, hierarchical structure quality, retrieval performance, graph level metrics, PP IoU, Graph IoU, AoMSG, code available, huggingface daily},
eprint = {2604.17454},
archiveprefix = {arXiv},
}
{}