mlsanityData to 14 Oct 2026

Detecting Visual Relationships with Deep Relational Networks

arXiv 1704.03114 ↗First posted 11 Apr 2017cs.CVcited by 97

Not on the map. Why?

Abstract (arXiv)

Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques in recognizing individual objects, reasoning about the relationships among objects remains a challenging task. Previous methods often treat this as a classification problem, considering each type of relationship (e.g. "ride") or each distinct visual phrase (e.g. "person-ride-horse") as a category. Such approaches are faced with significant difficulties caused by the high diversity of visual appearance for each kind of relationships or the large number of distinct visual phrases. We propose an integrated framework to tackle this problem. At the heart of this framework is the Deep Relational Network, a novel formulation designed specifically for exploiting the statistical dependencies between objects and their relationships. On two large datasets, the proposed method achieves substantial improvement over state-of-the-art.

Key facts. Cited by 97 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 27; 2022: 27; 2023: 23; 2024: 12; 2025: 5; 2026: 3.

97 papers.

Sort:

By area:

  1. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 163
  2. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  3. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  4. 2022Panoptic Scene Graph Generationcited by 114
  5. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  6. 2021Spatial-Temporal Transformer for Dynamic Scene Graph Generationcited by 96
  7. 2022RelTR: Relation Transformer for Scene Graph Generationcited by 96
  8. 2024The All-Seeing Project V2: Towards General Relation Comprehension of the Open Worldcited by 90
  9. 2022Multi-Modal Knowledge Graph Construction and Application: A Surveycited by 74
  10. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  11. 2022Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generationcited by 67
  12. 2023HierVL: Learning Hierarchical Video-Language Embeddingscited by 66
38 more
  1. 2021Learning to Generate Scene Graph from Natural Language Supervisioncited by 64
  2. 2021Fully Convolutional Scene Graph Generationcited by 57
  3. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 52
  4. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  5. 2022Deep Learning Approaches on Image Captioning: A Reviewcited by 43
  6. 2022Continuous Scene Representations for Embodied AIcited by 39
  7. 2021Unified Graph Structured Models for Video Understandingcited by 38
  8. 2021Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queriescited by 31
  9. 2021Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioningcited by 27
  10. 2021Visual Distant Supervision for Scene Graph Generationcited by 25
  11. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  12. 2023Devil's on the Edges: Selective Quad Attention for Scene Graph Generationcited by 23
  13. 2021Exploiting Scene Graphs for Human-Object Interaction Detectioncited by 22
  14. 2023HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generationcited by 19
  15. 2023Vision Relation Transformer for Unbiased Scene Graph Generationcited by 18
  16. 2023Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detectioncited by 15
  17. 2024HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generationcited by 14
  18. 2023CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Groundingcited by 13
  19. 2021Semantic Compositional Learning for Low-shot Scene Graph Generationcited by 12
  20. 2023VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generationcited by 12
  21. 2021Predicate correlation learning for scene graph generationcited by 11
  22. 2021ACP++: Action Co-occurrence Priors for Human-Object Interaction Detectioncited by 11
  23. 2024Can Transformers Capture Spatial Relations between Objects?cited by 11
  24. 2025DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generationcited by 11
  25. 2023Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generationcited by 9
  26. 2021Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regionscited by 8
  27. 2022Probabilistic Debiasing of Scene Graphscited by 8
  28. 2023Adaptive Visual Scene Understanding: Incremental Scene Graph Generationcited by 8
  29. 2024Leveraging Predicate and Triplet Learning for Scene Graph Generationcited by 8
  30. 20212.5D Visual Relationship Detectioncited by 7
  31. 2022Complex Scene Image Editing by Scene Graph Comprehensioncited by 7
  32. 2025Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generationcited by 7
  33. 2021Neural Belief Propagation for Scene Graph Generationcited by 6
  34. 2022Neural Message Passing for Visual Relationship Detectioncited by 6
  35. 2022Distance-Aware Occlusion Detection with Focused Attentioncited by 6
  36. 2024Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learningcited by 6
  37. 2021Computer vision for liquid samples in hospitals and medical labs using hierarchical image segmentation and relations predictioncited by 5
  38. 2021Magic Layouts: Structural Prior for Component Detection in User Interface Designscited by 5

50 most cited of 97 All 97 (JSON)