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

Showing 5175 of 318 papers

TitleStatusHype
Graph R-CNN for Scene Graph GenerationCode1
Dual-branch Hybrid Learning Network for Unbiased Scene Graph GenerationCode1
Are scene graphs good enough to improve Image Captioning?Code1
Learning to Generate Scene Graph from Natural Language SupervisionCode1
OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal ModelsCode1
EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity UnderstandingCode1
NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph EnrichmentCode1
Energy-Based Learning for Scene Graph GenerationCode1
A Review and Efficient Implementation of Scene Graph Generation MetricsCode1
Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense KnowledgeCode1
Learning and Reasoning with the Graph Structure Representation in Robotic SurgeryCode1
Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker DetectionCode1
NODIS: Neural Ordinary Differential Scene UnderstandingCode1
Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph AnalysisCode1
A Fair Ranking and New Model for Panoptic Scene Graph GenerationCode1
Fully Convolutional Scene Graph GenerationCode1
Compositional Feature Augmentation for Unbiased Scene Graph GenerationCode1
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and RetentionCode1
From General to Specific: Informative Scene Graph Generation via Balance AdjustmentCode1
Fine-Grained Scene Graph Generation with Data TransferCode1
4D-OR: Semantic Scene Graphs for OR Domain ModelingCode1
Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and ReasoningCode1
Context-Aware Scene Graph Generation With Seq2Seq TransformersCode1
Generative Compositional Augmentations for Scene Graph PredictionCode1
CogTree: Cognition Tree Loss for Unbiased Scene Graph GenerationCode1
Show:102550
← PrevPage 3 of 13Next →

Benchmark Results

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