DDS: Decoupled Dynamic Scene-Graph Generation Network
Not on the map. Why?
Abstract (arXiv)
Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data. Existing methods show poor performance in detecting triplets outside of a predefined set, primarily due to their reliance on dependent feature learning. To address this issue, we propose DDS -- a decoupled dynamic scene-graph generation network -- that consists of two independent branches that can disentangle extracted features. The key innovation of the current paper is the decoupling of the features representing the relationships from those of the objects, which enables the detection of novel object-relationship combinations. The DDS model is evaluated on three datasets and outperforms previous methods by a significant margin, especially in detecting previously unseen triplets.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 57 of its 84 references that are in the map. First posted on arXiv 18 Jan 2023.
Builds on
57 of 84 references.
References · 57
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2020End-to-End Object Detection with Transformerscited by 7,384
- 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
- 2017Scene Graph Generation by Iterative Message Passingcited by 462
- 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
- 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
- 2016Visual Relationship Detection with Language Priorscited by 333
- 2018Graph R-CNN for Scene Graph Generationcited by 296
- 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 258
38 more
- 2019Action Genome: Actions as Composition of Spatio-temporal Scene Graphscited by 249
- 2017Learning to Detect Human-Object Interactionscited by 238
- 2021HOTR: End-to-End Human-Object Interaction Detection with Transformerscited by 183
- 2018Learning Human-Object Interactions by Graph Parsing Neural Networkscited by 176
- 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
- 2021QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Informationcited by 147
- 2019PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detectioncited by 143
- 2021End-to-End Human Object Interaction Detection with HOI Transformercited by 134
- 2020Visual Compositional Learning for Human-Object Interaction Detectioncited by 129
- 2018iCAN: Instance-Centric Attention Network for Human-Object Interaction Detectioncited by 126
- 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
- 2022GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detectioncited by 119
- 2020DRG: Dual Relation Graph for Human-Object Interaction Detectioncited by 117
- 2020VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutionscited by 115
- 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
- 2021Mining the Benefits of Two-stage and One-stage HOI Detectioncited by 103
- 2019Graphical Contrastive Losses for Scene Graph Parsingcited by 100
- 2021Reformulating HOI Detection as Adaptive Set Predictioncited by 95
- 2021Spatial-Temporal Transformer for Dynamic Scene Graph Generationcited by 95
- 2020Spatially Conditioned Graphs for Detecting Human-Object Interactionscited by 93
- 2019Pose-aware Multi-level Feature Network for Human Object Interaction Detectioncited by 88
- 2020HOI Analysis: Integrating and Decomposing Human-Object Interactioncited by 81
- 2021Detecting Human-Object Interaction via Fabricated Compositional Learningcited by 79
- 2021Affordance Transfer Learning for Human-Object Interaction Detectioncited by 79
- 2020Detecting Human-Object Interactions with Action Co-occurrence Priorscited by 72
- 2021Recovering the Unbiased Scene Graphs from the Biased Onescited by 71
- 2019Deep Contextual Attention for Human-Object Interaction Detectioncited by 54
- 2018Counterfactual Critic Multi-Agent Training for Scene Graph Generationcited by 53
- 2021Target Adaptive Context Aggregation for Video Scene Graph Generationcited by 51
- 2020Contextual Heterogeneous Graph Network for Human-Object Interaction Detectioncited by 50
- 2020ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detectioncited by 45
- 2022Human-Object Interaction Detection via Disentangled Transformercited by 40
- 2017Weakly-supervised learning of visual relationscited by 36
- 2022What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactionscited by 35
- 2022MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detectioncited by 34
- 2020DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detectioncited by 31
- 2021Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphscited by 30
- 2022Iterative Scene Graph Generationcited by 24
50 most cited of 57 All 57 (JSON)
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.