Papers with Code 아카이브
Scene Graph Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 7
- 보존된 평가 기록
- 31
A scene graph is a structured representation of an image, where nodes in a scene graph correspond to object bounding boxes with their object categories, and edges correspond to their pairwise relationships between objects. The task of Scene Graph Generation is to generate a visually-grounded scene graph that most accurately correlates with an image.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Attentive Relational Networks for Mapping Images to Scene Graphs
An Interpretable Model for Scene Graph Generation
Scene Graph Generation via Conditional Random Fields
LinkNet: Relational Embedding for Scene Graph
Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks
Graph R-CNN for Scene Graph Generation
Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoning
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation
Approximate Query Matching for Image Retrieval
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Generating Triples with Adversarial Networks for Scene Graph Construction
Neural Motifs: Scene Graph Parsing with Global Context
Scene Graph Generation from Objects, Phrases and Region Captions
Pixels to Graphs by Associative Embedding
Scene Graph Generation by Iterative Message Passing
Visual Relationship Detection with Language Priors
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.