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 101–125 of 318 papers

TitleStatusHype
Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph GenerationCode1
Generative Compositional Augmentations for Scene Graph PredictionCode1
Learning and Reasoning with the Graph Structure Representation in Robotic SurgeryCode1
Learning Visual Commonsense for Robust Scene Graph GenerationCode1
Graph Density-Aware Losses for Novel Compositions in Scene Graph GenerationCode1
Relation Transformer NetworkCode1
GPS-Net: Graph Property Sensing Network for Scene Graph GenerationCode1
NODIS: Neural Ordinary Differential Scene UnderstandingCode1
Weakly Supervised Visual Semantic ParsingCode1
Bridging Knowledge Graphs to Generate Scene GraphsCode1
Knowledge-Embedded Routing Network for Scene Graph GenerationCode1
Graphical Contrastive Losses for Scene Graph ParsingCode1
Graph R-CNN for Scene Graph GenerationCode1
Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoningCode1
Scene Graph Generation by Iterative Message PassingCode1
SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning—0
CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery—0
CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations—0
HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions—0
Hi-Dyna Graph: Hierarchical Dynamic Scene Graph for Robotic Autonomy in Human-Centric Environments—0
A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation—0
LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical StudyCode0
From Data to Modeling: Fully Open-vocabulary Scene Graph Generation—0
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph RetrievalCode0
ORQA: A Benchmark and Foundation Model for Holistic Operating Room Modeling—0
Show:102550
← PrevPage 5 of 13Next →
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