Data to 7 Oct 2026

Knowledge-Embedded Routing Network for Scene Graph Generation

arXiv 1903.03326 ↗First posted 8 Mar 2019cs.CVcited by 163

Not on the map. Why?

Abstract (arXiv)

To understand a scene in depth not only involves locating/recognizing individual objects, but also requires to infer the relationships and interactions among them. However, since the distribution of real-world relationships is seriously unbalanced, existing methods perform quite poorly for the less frequent relationships. In this work, we find that the statistical correlations between object pairs and their relationships can effectively regularize semantic space and make prediction less ambiguous, and thus well address the unbalanced distribution issue. To achieve this, we incorporate these statistical correlations into deep neural networks to facilitate scene graph generation by developing a Knowledge-Embedded Routing Network. More specifically, we show that the statistical correlations between objects appearing in images and their relationships, can be explicitly represented by a structured knowledge graph, and a routing mechanism is learned to propagate messages through the graph to explore their interactions. Extensive experiments on the large-scale Visual Genome dataset demonstrate the superiority of the proposed method over current state-of-the-art competitors.

Key facts. Cited by 163 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 46; 2023: 45; 2024: 19; 2025: 16; 2026: 8.

163 papers.

Sort:

By area:

2021CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Modelscited by 182
2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
2022Panoptic Scene Graph Generationcited by 114
2021Learning to Predict Visual Attributes in the Wildcited by 95
2022RelTR: Relation Transformer for Scene Graph Generationcited by 95
2024Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationshipscited by 76
2022Scene Graph Generation: A Comprehensive Surveycited by 73
2021Recovering the Unbiased Scene Graphs from the Biased Onescited by 71
2023GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graphcited by 69
2022Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generationcited by 67
2022Relationformer: A Unified Framework for Image-to-Graph Generationcited by 67

38 more

2021Learning of Visual Relations: The Devil is in the Tailscited by 65
2021Learning to Generate Scene Graph from Natural Language Supervisioncited by 64
2022The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generationcited by 60
2021Fully Convolutional Scene Graph Generationcited by 57
2022Fine-Grained Scene Graph Generation with Data Transfercited by 57
2022Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuningcited by 54
2021From General to Specific: Informative Scene Graph Generation via Balance Adjustmentcited by 51
2023RLIPv2: Fast Scaling of Relational Language-Image Pre-trainingcited by 44
2024From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Modelscited by 43
2021Spatio-Temporal Dynamic Inference Network for Group Activity Recognitioncited by 42
2023VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloudcited by 42
2023Panoptic Scene Graph Generation with Semantics-Prototype Learningcited by 42
2021Structured Semantic Transfer for Multi-Label Recognition with Partial Labelscited by 41
2023Unbiased Scene Graph Generation in Videoscited by 38
2023Prototype-based Embedding Network for Scene Graph Generationcited by 37
2022MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answeringcited by 36
2021Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generationcited by 35
2023Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open Worldcited by 35
2021Linguistic Structures as Weak Supervision for Visual Scene Graph Generationcited by 29
2022Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labelscited by 29
2023Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retentioncited by 29
2022RU-Net: Regularized Unrolling Network for Scene Graph Generationcited by 28
2022Fine-Grained Predicates Learning for Scene Graph Generationcited by 27
2021Visual Distant Supervision for Scene Graph Generationcited by 25
2021Segmentation-grounded Scene Graph Generationcited by 25
2021Coarse-to-Fine Reasoning for Visual Question Answeringcited by 25
2022Reasoning with Scene Graphs for Robot Planning under Partial Observabilitycited by 25
2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
2022Iterative Scene Graph Generationcited by 24
2023Devil's on the Edges: Selective Quad Attention for Scene Graph Generationcited by 23
2022Resistance Training using Prior Bias: toward Unbiased Scene Graph Generationcited by 22
2022Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semanticscited by 22
2022HL-Net: Heterophily Learning Network for Scene Graph Generationcited by 22
2022Iterative Scene Graph Generation with Generative Transformerscited by 22
2021Not All Relations are Equal: Mining Informative Labels for Scene Graph Generationcited by 21
2023Unbiased Scene Graph Generation via Two-stage Causal Modelingcited by 21
2022Meta Spatio-Temporal Debiasing for Video Scene Graph Generationcited by 20
2022Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generationcited by 20

50 most cited of 163 All 163 (JSON)