Papers with Code 아카이브
Visual Relationship Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 5
- 보존된 평가 기록
- 24
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
OpenVidVRD: Open-Vocabulary Video Visual Relation Detection via Prompt-Driven Semantic Space Alignment
Improving Trust Estimation in Human-Robot Collaboration Using Beta Reputation at Fine-grained Timescales
End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting
VrdONE: One-stage Video Visual Relation Detection
SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
Video Relationship Detection Using Mixture of Experts
RelVAE: Generative Pretraining for few-shot Visual Relationship Detection
Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction
STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning
In Defense of Clip-based Video Relation Detection
NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection
Cognition Guided Human-Object Relationship Detection
Unified Visual Relationship Detection with Vision and Language Models
Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
Image Semantic Relation Generation
Distance-Aware Occlusion Detection with Focused Attention
Neural Message Passing for Visual Relationship Detection
Meta Spatio-Temporal Debiasing for Video Scene Graph Generation
Learning Structured Representations of Visual Scenes
VReBERT: A Simple and Flexible Transformer for Visual Relationship Detection
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
Scene Graph Generation: A Comprehensive Survey
Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation
Video Relation Detection via Tracklet based Visual Transformer
Social Fabric: Tubelet Compositions for Video Relation Detection
Image Scene Graph Generation (SGG) Benchmark
Spatial-Temporal Transformer for Dynamic Scene Graph Generation
What and When to Look?: Temporal Span Proposal Network for Video Relation Detection
Recovering the Unbiased Scene Graphs from the Biased Ones
Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries
2.5D Visual Relationship Detection
RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.