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.
Introduction to the 1st Place Winning Model of OpenImages Relationship Detection Challenge
A Problem Reduction Approach for Visual Relationships Detection
Context-Dependent Diffusion Network for Visual Relationship Detection
Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions
Improving Information Extraction from Images with Learned Semantic Models
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation
Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation
Natural Language Guided Visual Relationship Detection
Attend and Interact: Higher-Order Object Interactions for Video Understanding
Weakly-supervised learning of visual relations
Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
Care about you: towards large-scale human-centric visual relationship detection
Detecting Visual Relationships with Deep Relational Networks
Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
Visual Translation Embedding Network for Visual Relation Detection
ViP-CNN: Visual Phrase Guided Convolutional Neural Network
Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues
Visual Relationship Detection with Language Priors
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.