mlsanityData to 7 Oct 2026

ReLIC-SGG: Relation Lattice Completion for Open-Vocabulary Scene Graph Generation

arXiv 2604.22546 ↗First posted 24 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible relation phrases beyond a fixed predicate set. Existing methods usually treat annotated triplets as positives and all unannotated object-pair relations as negatives. However, scene graph annotations are inherently incomplete: many valid relations are missing, and the same interaction can be described at different granularities, e.g., textiton, textitstanding on, textitresting on, and textitsupported by. This issue becomes more severe in open-vocabulary SGG due to the much larger relation space. We propose ReLIC-SGG, a relation-incompleteness-aware framework that treats unannotated relations as latent variables rather than definite negatives. ReLIC-SGG builds a semantic relation lattice to model similarity, entailment, and contradiction among open-vocabulary predicates, and uses it to infer missing positive relations from visual-language compatibility, graph context, and semantic consistency. A positive-unlabeled graph learning objective further reduces false-negative supervision, while lattice-guided decoding produces compact and semantically consistent scene graphs. Experiments on conventional, open-vocabulary, and panoptic SGG benchmarks show that ReLIC-SGG improves rare and unseen predicate recognition and better recovers missing relations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 48 of its 81 references that are in the map. First posted on arXiv 24 Apr 2026.

Builds on

48 of 81 references.

References · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  6. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  9. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  10. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  11. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  12. 2016Visual Relationship Detection with Language Priorscited by 333
36 more
  1. 2018Graph R-CNN for Scene Graph Generationcited by 296
  2. 20193D Scene Graph: A Structure for Unified Semantics, 3D Space, and Cameracited by 280
  3. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 258
  4. 2017Positive-Unlabeled Learning with Non-Negative Risk Estimatorcited by 217
  5. 2019Knowledge-Embedded Routing Network for Scene Graph Generationcited by 163
  6. 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
  7. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  8. 2022Panoptic Scene Graph Generationcited by 114
  9. 2020Progressive Identification of True Labels for Partial-Label Learningcited by 102
  10. 2021SGTR: End-to-end Scene Graph Generation with Transformercited by 102
  11. 2022Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuningcited by 54
  12. 2023Panoptic Video Scene Graph Generationcited by 46
  13. 2024From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Modelscited by 43
  14. 2023Prototype-based Embedding Network for Scene Graph Generationcited by 37
  15. 2023Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retentioncited by 29
  16. 2022Fine-Grained Predicates Learning for Scene Graph Generationcited by 27
  17. 2017Binary Generative Adversarial Networks for Image Retrievalcited by 22
  18. 2020Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generationcited by 22
  19. 2021Exploiting Scene Graphs for Human-Object Interaction Detectioncited by 22
  20. 2025Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognitioncited by 16
  21. 2023Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detectioncited by 15
  22. 2024OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Modelscited by 15
  23. 2021Semantic Compositional Learning for Low-shot Scene Graph Generationcited by 12
  24. 2024Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentationcited by 12
  25. 2024MuAP: Multi-step Adaptive Prompt Learning for Vision-Language Model with Missing Modalitycited by 10
  26. 2026Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillationcited by 10
  27. 2025SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoningcited by 9
  28. 2017Deep Discrete Hashing with Self-supervised Pairwise Labelscited by 8
  29. 2021Semi-supervised Network Embedding with Differentiable Deep Quantisationcited by 7
  30. 2026Unbiased Dynamic Multimodal Fusioncited by 7
  31. 2017Deep Region Hashing for Efficient Large-scale Instance Search from Imagescited by 6
  32. 2019One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Networkcited by 6
  33. 2024Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learningcited by 6
  34. 2025TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognitioncited by 4
  35. 2025LangPrecip: Language-Aware Multimodal Precipitation Nowcastingcited by 2
  36. 2026One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessmentcited by 1

Built on by

Not cited yet.