Papers with Code 아카이브
Semantic correspondence
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 6
- 보존된 평가 기록
- 49
The task of semantic correspondence aims to establish reliable visual correspondence between different instances of the same object category.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
End-to-end weakly-supervised semantic alignment
DCTM: Discrete-Continuous Transformation Matching for Semantic Flow
Order embeddings and character-level convolutions for multimodal alignment
SCNet: Learning Semantic Correspondence
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks
Dense Semantic Correspondence where Every Pixel is a Classifier
BitSim: An Algebraic Similarity Measure for Description Logics Concepts
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.