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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 82 papers

Title	Date	Tasks	Status	Hype
Graphical Contrastive Losses for Scene Graph Parsing	Mar 7, 2019	Relationship DetectionScene Graph Generation	CodeCode Available	1
Recovering the Unbiased Scene Graphs from the Biased Ones	Jul 5, 2021	Missing LabelsScene Graph Classification	CodeCode Available	1
Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations	Sep 10, 2020	Objectobject-detection	CodeCode Available	1
Spatial-Temporal Transformer for Dynamic Scene Graph Generation	Jul 26, 2021	DecoderScene Graph Generation	CodeCode Available	1
2.5D Visual Relationship Detection	Apr 26, 2021	BenchmarkingDepth Estimation	CodeCode Available	1
Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship Detection	Jan 1, 2021	Common Sense ReasoningGraph Generation	CodeCode Available	1
Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks	Jun 16, 2020	Graph Neural NetworkHuman-Object Interaction Detection	CodeCode Available	1
Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks	Mar 16, 2020	image-classificationImage Classification	—Unverified	0
CPARR: Category-based Proposal Analysis for Referring Relationships	Apr 17, 2020	ObjectRelationship Detection	—Unverified	0
BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation	Sep 11, 2021	Graph GenerationObject	—Unverified	0

Show:10 25 50

← PrevPage 2 of 9Next →

All datasets VRD Relationship Detection VRD Phrase Detection VRD Predicate Detection Visual Genome VRD

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Yu et. al [[Yu et al.2017a]]	R@100	31.89	—	Unverified
2	vrd-dsr	R@100	23.29	—	Unverified
3	BLOCK	R@100	20.96	—	Unverified
4	Dai et. al [[Dai, Zhang, and Lin2017]]	R@100	20.88	—	Unverified
5	Liang et. al [[Liang, Lee, and Xing2017]]	R@100	20.79	—	Unverified
6	Peyre et. al [[Peyre et al.2017]]	R@100	17.1	—	Unverified
7	Zhang et. al [[Hanwang Zhang2017]]	R@100	15.2	—	Unverified
8	Lu et. al [[Lu et al.2016]]	R@100	14.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Yu et. al [[Yu et al.2017a]]	R@100	29.43	—	Unverified
2	BLOCK	R@100	28.96	—	Unverified
3	Dai et. al [[Dai, Zhang, and Lin2017]]	R@100	23.45	—	Unverified
4	Liang et. al [[Liang, Lee, and Xing2017]]	R@100	22.6	—	Unverified
5	Zhang et. al [[Hanwang Zhang2017]]	R@100	22.42	—	Unverified
6	Peyre et. al [[Peyre et al.2017]]	R@100	19.5	—	Unverified
7	Lu et. al [[Lu et al.2016]]	R@100	17.03	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Yu et. al [[Yu et al.2017a]]	R@100	94.65	—	Unverified
2	vrd-dsr	R@100	93.18	—	Unverified
3	BLOCK	R@100	92.58	—	Unverified
4	Dai et. al [[Dai, Zhang, and Lin2017]]	R@100	81.9	—	Unverified
5	Peyre et. al [[Peyre et al.2017]]	R@100	52.6	—	Unverified
6	Lu et. al [[Lu et al.2016]]	R@100	47.87	—	Unverified
7	Zhang et. al [[Hanwang Zhang2017]]	R@100	44.76	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PEVL	R@100	66.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Ours - v	R@50 k=1	15	—	Unverified