SOTAVerified

Scene Graph Generation

A scene graph is a structured representation of an image, where nodes in a scene graph correspond to object bounding boxes with their object categories, and edges correspond to their pairwise relationships between objects. The task of Scene Graph Generation is to generate a visually-grounded scene graph that most accurately correlates with an image.

Source: Scene Graph Generation by Iterative Message Passing

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 318 papers

TitleStatusHype
4D Panoptic Scene Graph GenerationCode3
RelTR: Relation Transformer for Scene Graph GenerationCode2
STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite ImageryCode2
Open World Scene Graph Generation using Vision Language ModelsCode2
RelationField: Relate Anything in Radiance FieldsCode2
SGTR+: End-to-end Scene Graph Generation with TransformerCode2
Learning to Compose Dynamic Tree Structures for Visual ContextsCode2
From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language ModelsCode2
HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph GenerationCode2
REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph GenerationCode2
MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical EnvironmentsCode2
EGTR: Extracting Graph from Transformer for Scene Graph GenerationCode2
Unbiased Scene Graph Generation from Biased TrainingCode2
SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language UnderstandingCode2
Panoptic Scene Graph GenerationCode2
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship DetectionCode1
Graphical Contrastive Losses for Scene Graph ParsingCode1
Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation ModelsCode1
Learning to Generate Scene Graph from Natural Language SupervisionCode1
Graph Density-Aware Losses for Novel Compositions in Scene Graph GenerationCode1
Learning Visual Commonsense for Robust Scene Graph GenerationCode1
Leveraging Predicate and Triplet Learning for Scene Graph GenerationCode1
GPS-Net: Graph Property Sensing Network for Scene Graph GenerationCode1
Generative Compositional Augmentations for Scene Graph PredictionCode1
Bridging Knowledge Graphs to Generate Scene GraphsCode1
Are scene graphs good enough to improve Image Captioning?Code1
BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard EnvironmentCode1
Adaptive Self-training Framework for Fine-grained Scene Graph GenerationCode1
A Review and Efficient Implementation of Scene Graph Generation MetricsCode1
Graph R-CNN for Scene Graph GenerationCode1
From General to Specific: Informative Scene Graph Generation via Balance AdjustmentCode1
Fine-Grained Predicates Learning for Scene Graph GenerationCode1
SPAN: Learning Similarity between Scene Graphs and Images with TransformersCode1
LANDMARK: Language-guided Representation Enhancement Framework for Scene Graph GenerationCode1
Fully Convolutional Scene Graph GenerationCode1
HL-Net: Heterophily Learning Network for Scene Graph GenerationCode1
Learning and Reasoning with the Graph Structure Representation in Robotic SurgeryCode1
Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense KnowledgeCode1
Energy-Based Learning for Scene Graph GenerationCode1
Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and ReasoningCode1
Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph GenerationCode1
Knowledge-Embedded Routing Network for Scene Graph GenerationCode1
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and RetentionCode1
Fine-Grained Scene Graph Generation with Data TransferCode1
Biasing Like Human: A Cognitive Bias Framework for Scene Graph GenerationCode1
Dense Relational Image Captioning via Multi-task Triple-Stream NetworksCode1
Context-Aware Scene Graph Generation With Seq2Seq TransformersCode1
DIFFVSGG: Diffusion-Driven Online Video Scene Graph GenerationCode1
Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph GenerationCode1
4D-OR: Semantic Scene Graphs for OR Domain ModelingCode1
Show:102550
← PrevPage 1 of 7Next →
All datasetsVisual Genome4D-OR3R-ScanVRDGQAMM-ORMS-COCO

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ExpressiveSGGR@10039.12—Unverified
2NeuSyRER@10039.1—Unverified
3KnowZRelzR@10035.65—Unverified
4SpeaQ (without reweighting)Recall@5032.9—Unverified
5SpeaQ (with reweighting)Recall@5032.1—Unverified
6Causal-TDERecall@5031.93—Unverified
7SG-EBMRecall@5031.74—Unverified
8GPS-NetRecall@5028.9—Unverified
9LOGINRecall@5028.2—Unverified
10VCTreeRecall@5027.9—Unverified
#ModelMetricClaimedVerifiedStatus
1ORacleF10.91—Unverified
2MM2SGF10.9—Unverified
3Pix2SGF10.9—Unverified
4LABRAD-ORF10.88—Unverified
54D-OR baselineF10.75—Unverified
#ModelMetricClaimedVerifiedStatus
1SceneGraphFusionTop-5 Accuracy0.87—Unverified
23DSSG [Wald2020_3dssg]Top-5 Accuracy0.66—Unverified
#ModelMetricClaimedVerifiedStatus
1FactorizableNetRecall@5018.32—Unverified
2VRDRecall@5018.16—Unverified
#ModelMetricClaimedVerifiedStatus
1KnowZRelzR@10029.56—Unverified
#ModelMetricClaimedVerifiedStatus
1MM2SGMacro F10.53—Unverified
#ModelMetricClaimedVerifiedStatus
1NeuSyRER@10038.5—Unverified