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 1–10 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 Prompting—0
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship DetectionCode1
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection—0
Video Relationship Detection Using Mixture of ExpertsCode0
RelVAE: Generative Pretraining for few-shot Visual Relationship Detection—0
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 Detection—0
Unified Visual Relationship Detection with Vision and Language ModelsCode0
Show:102550
← PrevPage 1 of 9Next →
All datasetsVRD Relationship DetectionVRD Phrase DetectionVRD Predicate DetectionVisual GenomeVRD

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Ours - vR@50 k=115—Unverified