mlsanityData to 14 Oct 2026

UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning

arXiv 2509.06165 ↗First posted 7 Sep 2025cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Video Scene Graph Generation (VidSGG) aims to represent dynamic visual content by detecting objects and modeling their temporal interactions as structured graphs. Prior studies typically target either coarse-grained box-level or fine-grained panoptic pixel-level VidSGG, often requiring task-specific architectures and multi-stage training pipelines. In this paper, we present UNO (UNified Object-centric VidSGG), a single-stage, unified framework that jointly addresses both tasks within an end-to-end architecture. UNO is designed to minimize task-specific modifications and maximize parameter sharing, enabling generalization across different levels of visual granularity. The core of UNO is an extended slot attention mechanism that decomposes visual features into object and relation slots. To ensure robust temporal modeling, we introduce object temporal consistency learning, which enforces consistent object representations across frames without relying on explicit tracking modules. Additionally, a dynamic triplet prediction module links relation slots to corresponding object pairs, capturing evolving interactions over time. We evaluate UNO on standard box-level and pixel-level VidSGG benchmarks. Results demonstrate that UNO not only achieves competitive performance across both tasks but also offers improved efficiency through a unified, object-centric design. Code is available at: https://github.com/Fsoft-AIC/UNO

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 60 of its 73 references that are in the map. First posted on arXiv 7 Sep 2025.

Builds on

60 of 73 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  9. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  10. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  11. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  12. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
38 more
  1. 2020Object-Centric Learning with Slot Attentioncited by 876
  2. 2018Panoptic Segmentationcited by 802
  3. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  4. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 531
  5. 2019SOLO: Segmenting Objects by Locationscited by 289
  6. 2019Action Genome: Actions as Composition of Spatio-temporal Scene Graphscited by 250
  7. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  8. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 166
  9. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 136
  10. 2023Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusioncited by 131
  11. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  12. 2017Learning non-maximum suppressioncited by 113
  13. 2021Spatial-Temporal Transformer for Dynamic Scene Graph Generationcited by 96
  14. 2022Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentationcited by 79
  15. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  16. 2019Relation Distillation Networks for Video Object Detectioncited by 77
  17. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  18. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  19. 2022Improving Object-centric Learning with Query Optimizationcited by 60
  20. 2021Target Adaptive Context Aggregation for Video Scene Graph Generationcited by 52
  21. 2023Action Scene Graphs for Long-Form Understanding of Egocentric Videoscited by 51
  22. 2023Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignmentcited by 46
  23. 2023Panoptic Video Scene Graph Generationcited by 46
  24. 2020Learning 3D Dynamic Scene Representations for Robot Manipulationcited by 39
  25. 2023Unbiased Scene Graph Generation in Videoscited by 39
  26. 2019Explainable Video Action Reasoning via Prior Knowledge and State Transitionscited by 33
  27. 2021Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphscited by 31
  28. 2020SCOUTER: Slot Attention-based Classifier for Explainable Image Recognitioncited by 29
  29. 2021Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentationcited by 24
  30. 2024OED: Towards One-stage End-to-End Dynamic Scene Graph Generationcited by 23
  31. 20244D Panoptic Scene Graph Generationcited by 22
  32. 2023Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videoscited by 20
  33. 2021Revisiting spatio-temporal layouts for compositional action recognitioncited by 19
  34. 2021Shaping embodied agent behavior with activity-context priors from egocentric videocited by 17
  35. 2023RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understandingcited by 17
  36. 2023Pair then Relation: Pair-Net for Panoptic Scene Graph Generationcited by 17
  37. 2024Slot State Space Modelscited by 17
  38. 2024Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Modelscited by 16

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulationcited by 9
  2. 2026RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generationcited by 0