mlsanityData to 7 Oct 2026

Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs

arXiv 2112.09828 ↗First posted 18 Dec 2021cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Dynamic scene graph generation from a video is challenging due to the temporal dynamics of the scene and the inherent temporal fluctuations of predictions. We hypothesize that capturing long-term temporal dependencies is the key to effective generation of dynamic scene graphs. We propose to learn the long-term dependencies in a video by capturing the object-level consistency and inter-object relationship dynamics over object-level long-term tracklets using transformers. Experimental results demonstrate that our Dynamic Scene Graph Detection Transformer (DSG-DETR) outperforms state-of-the-art methods by a significant margin on the benchmark dataset Action Genome. Our ablation studies validate the effectiveness of each component of the proposed approach. The source code is available at https://github.com/Shengyu-Feng/DSG-DETR.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 18 Dec 2021.

Builds on

32 of 48 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  8. 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 820
  9. 2018Image Transformercited by 770
  10. 2019VideoBERT: A Joint Model for Video and Language Representation Learningcited by 702
  11. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
  12. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
20 more
  1. 2016Visual Relationship Detection with Language Priorscited by 333
  2. 2018Image Generation from Scene Graphscited by 324
  3. 2018Video Action Transformer Networkcited by 316
  4. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 258
  5. 2018Auto-Encoding Scene Graphs for Image Captioningcited by 254
  6. 2019Action Genome: Actions as Composition of Spatio-temporal Scene Graphscited by 249
  7. 2018Exploring Visual Relationship for Image Captioningcited by 215
  8. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 165
  9. 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
  10. 2019Graphical Contrastive Losses for Scene Graph Parsingcited by 100
  11. 2021Spatial-Temporal Transformer for Dynamic Scene Graph Generationcited by 95
  12. 2019Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrievalcited by 66
  13. 2021Target Adaptive Context Aggregation for Video Scene Graph Generationcited by 51
  14. 2021Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Trackingcited by 47
  15. 2019PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graphcited by 44
  16. 2021Unified Graph Structured Models for Video Understandingcited by 38
  17. 2020RetrieveGAN: Image Synthesis via Differentiable Patch Retrievalcited by 35
  18. 2021In Defense of Scene Graphs for Image Captioningcited by 31
  19. 2021Video Relation Detection via Tracklet based Visual Transformercited by 17
  20. 2020Knowledge-Based Video Question Answering with Unsupervised Scene Descriptionscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 7; 2025: 12; 2026: 4.

30 papers.

Sort:

By area:

  1. 2023Action Scene Graphs for Long-Form Understanding of Egocentric Videoscited by 51
  2. 2024OED: Towards One-stage End-to-End Dynamic Scene Graph Generationcited by 22
  3. 2024HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipationcited by 17
  4. 2023Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labelingcited by 15
  5. 2023Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphscited by 13
  6. 2025Universal Scene Graph Generationcited by 11
  7. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  8. 2024Towards Scene Graph Anticipationcited by 10
  9. 2025DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generationcited by 10
  10. 2023A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videoscited by 7
  11. 2024Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipationcited by 6
  12. 2024Situational Scene Graph for Structured Human-centric Situation Understandingcited by 4
18 more
  1. 2025Weakly Supervised Video Scene Graph Generation via Natural Language Supervisioncited by 4
  2. 2023DDS: Decoupled Dynamic Scene-Graph Generation Networkcited by 3
  3. 2023Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learningcited by 3
  4. 2025TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferringcited by 3
  5. 2023Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generationcited by 1
  6. 2024TD^2-Net: Toward Denoising and Debiasing for Dynamic Scene Graph Generationcited by 1
  7. 2025FORESCENE: FOREcasting human activity via latent SCENE graphs diffusioncited by 1
  8. 2025FDSG: Forecasting Dynamic Scene Graphscited by 1
  9. 2025Language-Driven Object-Oriented Two-Stage Method for Scene Graph Anticipationcited by 1
  10. 2025UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learningcited by 1
  11. 2025VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generationcited by 1
  12. 2026Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learningcited by 1
  13. 2026SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Modelscited by 1
  14. 2025A Closer Look at Dynamic Scene Graph Generation In the Era of Multimodal Large Language Modelscited by 0
  15. 2025THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footagecited by 0
  16. 2025Click2Graph: Interactive Panoptic Video Scene Graphs from a Single Clickcited by 0
  17. 2026Frequency-guided Multi-level Reasoning for Scene Graph Generation in Videocited by 0
  18. 2026OvDSGG: End-to-End Open-Vocabulary Dynamic Scene Graph Generationcited by 0