mlsanityData to 7 Oct 2026

Fully Convolutional Scene Graph Generation

arXiv 2103.16083 ↗First posted 30 Mar 2021cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

This paper presents a fully convolutional scene graph generation (FCSGG) model that detects objects and relations simultaneously. Most of the scene graph generation frameworks use a pre-trained two-stage object detector, like Faster R-CNN, and build scene graphs using bounding box features. Such pipeline usually has a large number of parameters and low inference speed. Unlike these approaches, FCSGG is a conceptually elegant and efficient bottom-up approach that encodes objects as bounding box center points, and relationships as 2D vector fields which are named as Relation Affinity Fields (RAFs). RAFs encode both semantic and spatial features, and explicitly represent the relationship between a pair of objects by the integral on a sub-region that points from subject to object. FCSGG only utilizes visual features and still generates strong results for scene graph generation. Comprehensive experiments on the Visual Genome dataset demonstrate the efficacy, efficiency, and generalizability of the proposed method. FCSGG achieves highly competitive results on recall and zero-shot recall with significantly reduced inference time.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 46 of its 67 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

46 of 67 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2015Fast R-CNNcited by 2,930
  8. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  9. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  10. 2018Group Normalizationcited by 1,514
  11. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  12. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
34 more
  1. 2019Objects as Pointscited by 1,172
  2. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  3. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  4. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  5. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  6. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  7. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  8. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  9. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  10. 2018Image Generation from Scene Graphscited by 324
  11. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  12. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  13. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 258
  14. 2018Auto-Encoding Scene Graphs for Image Captioningcited by 254
  15. 2018Exploring Visual Relationship for Image Captioningcited by 215
  16. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 165
  17. 2019Knowledge-Embedded Routing Network for Scene Graph Generationcited by 163
  18. 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
  19. 2016Graph-Structured Representations for Visual Question Answeringcited by 123
  20. 2017Visual Translation Embedding Network for Visual Relation Detectioncited by 112
  21. 2019Scene Graph Generation with External Knowledge and Image Reconstructioncited by 102
  22. 2017Detecting Visual Relationships with Deep Relational Networkscited by 97
  23. 2020Bridging Knowledge Graphs to Generate Scene Graphscited by 86
  24. 2018Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generationcited by 78
  25. 2017Visual Relationship Detection with Internal and External Linguistic Knowledge Distillationcited by 60
  26. 2017Pixels to Graphs by Associative Embeddingcited by 58
  27. 2018Counterfactual Critic Multi-Agent Training for Scene Graph Generationcited by 53
  28. 2020Learning Visual Commonsense for Robust Scene Graph Generationcited by 47
  29. 2018LinkNet: Relational Embedding for Scene Graphcited by 45
  30. 2019Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speechcited by 44
  31. 2016Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cuescited by 33
  32. 2019Scene Graph Prediction with Limited Labelscited by 32
  33. 2020Graph Density-Aware Losses for Novel Compositions in Scene Graph Generationcited by 31
  34. 2018Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Featurescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 14; 2023: 21; 2024: 10; 2025: 6; 2026: 2.

57 papers.

Sort:

By area:

  1. 2021SGTR: End-to-end Scene Graph Generation with Transformercited by 102
  2. 2022RelTR: Relation Transformer for Scene Graph Generationcited by 95
  3. 2022Relationformer: A Unified Framework for Image-to-Graph Generationcited by 67
  4. 2024EGTR: Extracting Graph from Transformer for Scene Graph Generationcited by 45
  5. 2021Structured Sparse R-CNN for Direct Scene Graph Generationcited by 44
  6. 2023RLIPv2: Fast Scaling of Relational Language-Image Pre-trainingcited by 44
  7. 2023Incremental 3D Semantic Scene Graph Prediction from RGB Sequencescited by 39
  8. 2023Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retentioncited by 29
  9. 2022Iterative Scene Graph Generationcited by 24
  10. 2022Iterative Scene Graph Generation with Generative Transformerscited by 22
  11. 2022Plane Geometry Diagram Parsingcited by 20
  12. 2022Meta Spatio-Temporal Debiasing for Video Scene Graph Generationcited by 20
38 more
  1. 2021Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulationcited by 17
  2. 2023Pair then Relation: Pair-Net for Panoptic Scene Graph Generationcited by 17
  3. 2024Scene Graph Generation with Role-Playing Large Language Modelscited by 16
  4. 2023Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detectioncited by 15
  5. 2021Grounded Situation Recognition with Transformerscited by 14
  6. 2022PGDP5K: A Diagram Parsing Dataset for Plane Geometry Problemscited by 14
  7. 2022Label Semantic Knowledge Distillation for Unbiased Scene Graph Generationcited by 14
  8. 2023LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervisioncited by 13
  9. 2024DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generationcited by 11
  10. 2025Universal Scene Graph Generationcited by 11
  11. 2024Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generationcited by 10
  12. 2022Rethinking the Evaluation of Unbiased Scene Graph Generationcited by 9
  13. 2025Reusing Attention for One-stage Lane Topology Understandingcited by 9
  14. 2022SSGVS: Semantic Scene Graph-to-Video Synthesiscited by 8
  15. 2024Leveraging Predicate and Triplet Learning for Scene Graph Generationcited by 8
  16. 2023Single-Stage Visual Relationship Learning using Conditional Queriescited by 7
  17. 2023Skew Class-balanced Re-weighting for Unbiased Scene Graph Generationcited by 5
  18. 2024AUG: A New Dataset and An Efficient Model for Aerial Image Urban Scene Graph Generationcited by 5
  19. 2026RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generationcited by 5
  20. 2023Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generationcited by 4
  21. 2023Improving Scene Graph Generation with Superpixel-Based Interaction Learningcited by 4
  22. 2022Constrained Structure Learning for Scene Graph Generationcited by 3
  23. 2023Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learningcited by 3
  24. 2023SPAN: Learning Similarity between Scene Graphs and Images with Transformerscited by 3
  25. 2023Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generationcited by 3
  26. 2023Generalized Unbiased Scene Graph Generationcited by 3
  27. 2024BCTR: Bidirectional Conditioning Transformer for Scene Graph Generationcited by 3
  28. 2025Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generationcited by 3
  29. 2023Informative Scene Graph Generation via Debiasingcited by 2
  30. 2023RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generationcited by 2
  31. 2024RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphscited by 2
  32. 2025From Data to Modeling: Fully Open-vocabulary Scene Graph Generationcited by 2
  33. 2022Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generationcited by 1
  34. 2023Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generationcited by 1
  35. 2024SGTR+: End-to-end Scene Graph Generation with Transformercited by 1
  36. 2024S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in ORcited by 1
  37. 2025SiLVi: Simple Interface for Labeling Video Interactionscited by 1
  38. 2022Self-Supervised Road Layout Parsing with Graph Auto-Encodingcited by 0

50 most cited of 57 All 57 (JSON)