https://github.com/ruotianluo/iep-ref
CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions
Papers with Code 아카이브
Referring Expression Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 22
- 보존된 평가 기록
- 317
The task aims at labeling the pixels of an image or video that represent an object instance referred by a linguistic expression. In particular, the referring expression (RE) must allow the identification of an individual object in a discourse or scene (the referent). REs unambiguously identify the target instance.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/seanzhuh/seqtr
https://github.com/shikras/d-cube
Advancing Referring Expression Segmentation Beyond Single Image
https://github.com/skynbe/Refer-Youtube-VOS
https://github.com/sosppxo/3d-gres
https://github.com/ssharpe42/NLQAC_Instance_Selection
https://github.com/ssharpe42/NLQAC_ObjSeg
https://github.com/ssharpe42/VNLQAC
https://github.com/thunlp/pevl
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
https://github.com/wusize/harmon
https://github.com/xurige1995/3shnet
Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.