https://github.com/suprosanna/relationformer
공식 코드Relationformer: A Unified Framework for Image-to-Graph Generation
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/taksau/GPS-Net
공식 코드GPS-Net: Graph Property Sensing Network for Scene Graph Generation
https://github.com/thunlp/visualds
공식 코드https://github.com/umich-vl/px2graph
공식 코드https://github.com/visinf/veto
공식 코드Vision Relation Transformer for Unbiased Scene Graph Generation
https://github.com/vl-group/penet
공식 코드Prototype-based Embedding Network for Scene Graph Generation
https://github.com/wanglei0618/htcl
공식 코드Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation
https://github.com/waxnkw/ietrans-sgg.pytorch
공식 코드https://github.com/xcppy/ws-sgg
공식 코드https://github.com/xinyulyu/fgpl
공식 코드https://github.com/yangxue0827/STAR-MMRotate
공식 코드https://github.com/yangxue0827/rsg-mmrotate
공식 코드https://github.com/yekeren/WSSGG
공식 코드Linguistic Structures as Weak Supervision for Visual Scene Graph Generation
https://github.com/yikang-li/FactorizableNet
공식 코드Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation
https://github.com/yikang-li/MSDN
공식 코드Scene Graph Generation from Objects, Phrases and Region Captions
https://github.com/yiwuzhong/sgg_from_nls
공식 코드Learning to Generate Scene Graph from Natural Language Supervision
https://github.com/yrcong/NODIS
공식 코드https://github.com/yrcong/RelTR
공식 코드https://github.com/yrcong/learning_similarity_between_graphs_images
공식 코드SPAN: Learning Similarity between Scene Graphs and Images with Transformers
https://github.com/yrcong/sttran
공식 코드Spatial-Temporal Transformer for Dynamic Scene Graph Generation
https://github.com/yuweihao/KERN
공식 코드Knowledge-Embedded Routing Network for Scene Graph Generation
https://github.com/zeeshanhayder/dsgg
공식 코드DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation
https://github.com/zhangce01/HiKER-SGG
공식 코드HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
https://github.com/zhanglab-deepneurocoglab/csegg
공식 코드Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
https://github.com/zhugekongkong/sgg-g2s
공식 코드From General to Specific: Informative Scene Graph Generation via Balance Adjustment
https://github.com/zhuzi24/sgg-toolkit
공식 코드https://github.com/zty0304/sgdraw
공식 코드SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation
https://github.com/2023-MindSpore-1/ms-code-210/tree/main/cnn_direction_model
https://github.com/2023-MindSpore-1/ms-code-211/tree/main/dlinknet
https://github.com/2023-MindSpore-1/ms-code-6/tree/main/cnn_direction_model
https://github.com/2024-MindSpore-1/Code7/tree/main/cnn_direction_model
https://github.com/HCPLab-SYSU/KERN
https://github.com/KaihuaTang/VCTree-Scene-Graph-Generation
Learning to Compose Dynamic Tree Structures for Visual Contexts
https://github.com/KaihuaTang/VCTree-Visual-Question-Answering
Learning to Compose Dynamic Tree Structures for Visual Contexts
https://github.com/MindCode-4/code-4/tree/main/realm
https://github.com/MindSpore-paper-code-3/code8/tree/main/dlinknet
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.