mlsanityData to 14 Oct 2026

HSG: Hyperbolic Scene Graph

arXiv 2604.17454 ↗First posted 19 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 50 of its 59 references that are in the map. First posted on arXiv 19 Apr 2026.

Builds on

50 of 59 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2022A ConvNet for the 2020scited by 3,579
  9. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  10. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  11. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  12. 2025DINOv3cited by 1,414
38 more
  1. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  2. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  3. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 692
  4. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
  5. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  6. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  7. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 414
  8. 2019Hyperbolic Graph Convolutional Neural Networkscited by 402
  9. 2018Graph R-CNN for Scene Graph Generationcited by 298
  10. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 265
  11. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 208
  12. 2018Representation Tradeoffs for Hyperbolic Embeddingscited by 206
  13. 2019Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mappingcited by 184
  14. 2022Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimizationcited by 178
  15. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 177
  16. 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 162
  17. 2023Hyperbolic Image-Text Representationscited by 136
  18. 2015Order-Embeddings of Images and Languagecited by 113
  19. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 111
  20. 2019Constant Curvature Graph Convolutional Networkscited by 108
  21. 2021SGTR: End-to-end Scene Graph Generation with Transformercited by 103
  22. 2022Hyperbolic Image Segmentationcited by 102
  23. 2022RelTR: Relation Transformer for Scene Graph Generationcited by 96
  24. 2024Compositional Entailment Learning for Hyperbolic Vision-Language Modelscited by 74
  25. 2018Probabilistic Embedding of Knowledge Graphs with Box Lattice Measurescited by 64
  26. 2022Hyperbolic Contrastive Learning for Visual Representations beyond Objectscited by 61
  27. 2019Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddingscited by 49
  28. 2024From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Modelscited by 43
  29. 2021Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Conescited by 38
  30. 2020Improving Local Identifiability in Probabilistic Box Embeddingscited by 35
  31. 2023Hyperbolic Representation Learning: Revisiting and Advancingcited by 21
  32. 2017Hierarchical Embeddings for Hypernymy Detection and Directionalitycited by 19
  33. 2023Towards Democratizing Joint-Embedding Self-Supervised Learningcited by 18
  34. 2023Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learningcited by 18
  35. 2024Learning Structured Representations with Hyperbolic Embeddingscited by 16
  36. 2024Multiview Scene Graphcited by 9
  37. 2024HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generationcited by 8
  38. 2026GeoWorld: Geometric World Modelscited by 6

Built on by

Not cited yet.