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 110 of 82 papers

TitleStatusHype
METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship DetectionCode0
End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting0
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship DetectionCode1
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection0
Video Relationship Detection Using Mixture of ExpertsCode0
RelVAE: Generative Pretraining for few-shot Visual Relationship Detection0
Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box ReconstructionCode0
STUPD: A Synthetic Dataset for Spatial and Temporal Relation ReasoningCode0
NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection0
Unified Visual Relationship Detection with Vision and Language ModelsCode0
Show:102550
← PrevPage 1 of 9Next →

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