SOTAVerified

Visual Relationship Detection

Visual relationship detection (VRD) is one newly developed computer vision task aiming to recognize relations or interactions between objects in an image. It is a further learning task after object recognition and is essential for fully understanding images, even the visual world.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 82 papers

TitleStatusHype
Explanation-based Weakly-supervised Learning of Visual Relations with Graph NetworksCode1
Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image InterpretationCode1
Distance-Aware Occlusion Detection with Focused AttentionCode1
2.5D Visual Relationship DetectionCode1
Graphical Contrastive Losses for Scene Graph ParsingCode1
Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship DetectionCode1
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship DetectionCode1
LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videosCode1
Exploring Long Tail Visual Relationship Recognition with Large VocabularyCode1
Neural Message Passing for Visual Relationship DetectionCode1
NODIS: Neural Ordinary Differential Scene UnderstandingCode1
One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection TasksCode1
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language ModelsCode1
Recovering the Unbiased Scene Graphs from the Biased OnesCode1
RelTransformer: A Transformer-Based Long-Tail Visual Relationship RecognitionCode1
Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal RepresentationsCode1
Spatial-Temporal Transformer for Dynamic Scene Graph GenerationCode1
Towards Overcoming False Positives in Visual Relationship Detection—0
Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation—0
End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting—0
Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition—0
ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks—0
RelVAE: Generative Pretraining for few-shot Visual Relationship Detection—0
Visual Semantic Information Pursuit: A Survey—0
Scene Graph Generation: A Comprehensive Survey—0
Scene Graph Generation with External Knowledge and Image Reconstruction—0
A Comprehensive Survey of Scene Graphs: Generation and Application—0
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection—0
VReBERT: A Simple and Flexible Transformer for Visual Relationship Detection—0
Tensorize, Factorize and Regularize: Robust Visual Relationship Learning—0
An Interpretable Model for Scene Graph Generation—0
A Probabilistic Graphical Model Based on Neural-Symbolic Reasoning for Visual Relationship Detection—0
A Problem Reduction Approach for Visual Relationships Detection—0
Attend and Interact: Higher-Order Object Interactions for Video Understanding—0
BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation—0
Bounding-box Channels for Visual Relationship Detection—0
Care about you: towards large-scale human-centric visual relationship detection—0
Context-Dependent Diffusion Network for Visual Relationship Detection—0
CPARR: Category-based Proposal Analysis for Referring Relationships—0
Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks—0
Deep Contextual Attention for Human-Object Interaction Detection—0
Target-Tailored Source-Transformation for Scene Graph Generation—0
Fixed-size Objects Encoding for Visual Relationship Detection—0
ViP-CNN: Visual Phrase Guided Convolutional Neural Network—0
Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries—0
Hierarchical Graph Attention Network for Visual Relationship Detection—0
Image Semantic Relation Generation—0
Improving Information Extraction from Images with Learned Semantic Models—0
Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions—0
Introduction to the 1st Place Winning Model of OpenImages Relationship Detection Challenge—0
Show:102550
← PrevPage 1 of 2Next →
All datasetsVRD Relationship DetectionVRD Phrase DetectionVRD Predicate DetectionVisual GenomeVRD

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Yu et. al [[Yu et al.2017a]]R@10031.89—Unverified
2vrd-dsrR@10023.29—Unverified
3BLOCKR@10020.96—Unverified
4Dai et. al [[Dai, Zhang, and Lin2017]]R@10020.88—Unverified
5Liang et. al [[Liang, Lee, and Xing2017]]R@10020.79—Unverified
6Peyre et. al [[Peyre et al.2017]]R@10017.1—Unverified
7Zhang et. al [[Hanwang Zhang2017]]R@10015.2—Unverified
8Lu et. al [[Lu et al.2016]]R@10014.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Yu et. al [[Yu et al.2017a]]R@10029.43—Unverified
2BLOCKR@10028.96—Unverified
3Dai et. al [[Dai, Zhang, and Lin2017]]R@10023.45—Unverified
4Liang et. al [[Liang, Lee, and Xing2017]]R@10022.6—Unverified
5Zhang et. al [[Hanwang Zhang2017]]R@10022.42—Unverified
6Peyre et. al [[Peyre et al.2017]]R@10019.5—Unverified
7Lu et. al [[Lu et al.2016]]R@10017.03—Unverified
#ModelMetricClaimedVerifiedStatus
1Yu et. al [[Yu et al.2017a]]R@10094.65—Unverified
2vrd-dsrR@10093.18—Unverified
3BLOCKR@10092.58—Unverified
4Dai et. al [[Dai, Zhang, and Lin2017]]R@10081.9—Unverified
5Peyre et. al [[Peyre et al.2017]]R@10052.6—Unverified
6Lu et. al [[Lu et al.2016]]R@10047.87—Unverified
7Zhang et. al [[Hanwang Zhang2017]]R@10044.76—Unverified
#ModelMetricClaimedVerifiedStatus
1PEVLR@10066.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Ours - vR@50 k=115—Unverified