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.
Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation
Scene Graph Generation with Geometric Context
Topic Scene Graph Generation by Attention Distillation from Caption
Scene Graph Generation for Better Image Captioning?
BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation
GeneAnnotator: A Semi-automatic Annotation Tool for Visual Scene Graph
Learning to Generate Scene Graph from Natural Language Supervision
roadscene2vec: A Tool for Extracting and Embedding Road Scene-Graphs
From General to Specific: Informative Scene Graph Generation via Balance Adjustment
Learning of Visual Relations: The Devil is in the Tails
Semantic Compositional Learning for Low-shot Scene Graph Generation
Target Adaptive Context Aggregation for Video Scene Graph Generation
Unconditional Scene Graph Generation
ReFormer: The Relational Transformer for Image Captioning
Image Scene Graph Generation (SGG) Benchmark
Spatial-Temporal Transformer for Dynamic Scene Graph Generation
Scenes and Surroundings: Scene Graph Generation using Relation Transformer
Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration
Predicate correlation learning for scene graph generation
Recovering the Unbiased Scene Graphs from the Biased Ones
Structured Sparse R-CNN for Direct Scene Graph Generation
Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions
Linguistic Structures as Weak Supervision for Visual Scene Graph Generation
Survey of Visual-Semantic Embedding Methods for Zero-Shot Image Retrieval
Segmentation-grounded Scene Graph Generation
Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
Fully Convolutional Scene Graph Generation
Visual Distant Supervision for Scene Graph Generation
SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation
Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis
Energy-Based Learning for Scene Graph Generation
Understanding the Role of Scene Graphs in Visual Question Answering
Self-Supervised Real-to-Sim Scene Generation
Bridging Scene Understanding and Task Execution with Flexible Simulation Environments
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.