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 151–200 of 318 papers

TitleStatusHype
HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph GenerationCode1
Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open WorldCode1
Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label LearningCode0
LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating RoomsCode0
Decomposed Prototype Learning for Few-Shot Scene Graph Generation—0
Location-Free Scene Graph GenerationCode1
SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph GenerationCode1
Unified Visual Relationship Detection with Vision and Language ModelsCode0
Hierarchical Relationships: A New Perspective to Enhance Scene Graph GenerationCode1
Prototype-based Embedding Network for Scene Graph GenerationCode1
LANDMARK: Language-guided Representation Enhancement Framework for Scene Graph GenerationCode1
Instance-incremental Scene Graph Generation from Real-world Point Clouds via Normalizing Flows—0
Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection—0
Self-Supervised Relation Alignment for Scene Graph Generation—0
DDS: Decoupled Dynamic Scene-Graph Generation Network—0
Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic SpaceCode1
Fast Contextual Scene Graph Generation With Unbiased Context Augmentation—0
IS-GGT: Iterative Scene Graph Generation With Generative Transformers—0
Skew Class-balanced Re-weighting for Unbiased Scene Graph GenerationCode0
Peer Learning for Unbiased Scene Graph Generation—0
SrTR: Self-reasoning Transformer with Visual-linguistic Knowledge for Scene Graph Generation—0
Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural NetworkCode1
SGDraw: Scene Graph Drawing Interface Using Object-Oriented RepresentationCode0
Iterative Scene Graph Generation with Generative Transformers—0
An Enhanced Object Detection Model for Scene Graph Generation—0
SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation—0
SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation—0
Explore Contextual Information for 3D Scene Graph Generation—0
Unbiased Scene Graph Generation using Predicate Similarities—0
Scalable Regularization of Scene Graph Generation Models using Symbolic Theories—0
Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning—0
Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation—0
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation—0
Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph GenerationCode1
Rethinking the Evaluation of Unbiased Scene Graph Generation—0
NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation—0
Iterative Scene Graph Generation—0
Meta Spatio-Temporal Debiasing for Video Scene Graph Generation—0
Panoptic Scene Graph GenerationCode2
BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard EnvironmentCode1
Dual-branch Hybrid Learning Network for Unbiased Scene Graph GenerationCode1
Adaptive Fine-Grained Predicates Learning for Scene Graph Generation—0
Learning Structured Representations of Visual Scenes—0
Learning To Generate Scene Graph from Head to Tail—0
Doubly Reparameterized Importance Weighted Structure Learning for Scene Graph Generation—0
The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph GenerationCode1
Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and ReasoningCode1
GraphMapper: Efficient Visual Navigation by Scene Graph Generation—0
Importance Weighted Structure Learning for Scene Graph Generation—0
HL-Net: Heterophily Learning Network for Scene Graph GenerationCode1
Show:102550
← PrevPage 4 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