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

Showing 125 of 82 papers

TitleStatusHype
Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image InterpretationCode1
Distance-Aware Occlusion Detection with Focused AttentionCode1
Spatial-Temporal Transformer for Dynamic Scene Graph GenerationCode1
LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videosCode1
Explanation-based Weakly-supervised Learning of Visual Relations with Graph NetworksCode1
Exploring Long Tail Visual Relationship Recognition with Large VocabularyCode1
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship DetectionCode1
Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal RepresentationsCode1
Graphical Contrastive Losses for Scene Graph ParsingCode1
Neural Message Passing for Visual Relationship DetectionCode1
NODIS: Neural Ordinary Differential Scene UnderstandingCode1
Recovering the Unbiased Scene Graphs from the Biased OnesCode1
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
2.5D Visual Relationship DetectionCode1
Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship DetectionCode1
RelTransformer: A Transformer-Based Long-Tail Visual Relationship RecognitionCode1
Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language CuesCode0
AVR: Attention based Salient Visual Relationship DetectionCode0
Constructing a Visual Relationship Authenticity DatasetCode0
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph GenerationCode0
Image Scene Graph Generation (SGG) BenchmarkCode0
Improving Visual Relation Detection using Depth MapsCode0
Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute DetectionCode0
BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship DetectionCode0
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

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