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 126150 of 318 papers

TitleStatusHype
DSGG: Dense Relation Transformer for an End-to-end Scene Graph GenerationCode0
Situational Scene Graph for Structured Human-centric Situation UnderstandingCode0
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph RetrievalCode0
SGDraw: Scene Graph Drawing Interface Using Object-Oriented RepresentationCode0
Head-Tail Cooperative Learning Network for Unbiased Scene Graph GenerationCode0
Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate ClassesCode0
Adaptive Visual Scene Understanding: Incremental Scene Graph GenerationCode0
GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific NarrativesCode0
S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in ORCode0
Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene GraphsCode0
Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph GenerationCode0
ReFormer: The Relational Transformer for Image CaptioningCode0
Scene Graph Generation from Objects, Phrases and Region CaptionsCode0
Fine-Grained Scene Graph Generation via Sample-Level Bias PredictionCode0
Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph GenerationCode0
Federated Voxel Scene Graph for Intracranial HemorrhageCode0
Pixels to Graphs by Associative EmbeddingCode0
LinkNet: Relational Embedding for Scene GraphCode0
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph GenerationCode0
OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence RoboticsCode0
After All, Only The Last Neuron Matters: Comparing Multi-modal Fusion Functions for Scene Graph GenerationCode0
Exploiting Long-Term Dependencies for Generating Dynamic Scene GraphsCode0
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph GenerationCode0
LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating RoomsCode0
Mapping Images to Scene Graphs with Permutation-Invariant Structured PredictionCode0
Show:102550
← PrevPage 6 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