태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Kinship verification aims to find out whether there is a kin relation for a given pair of facial images.
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
KinFaceW-I dataset contains 533 pairs of facial images of persons with a kin relation. Four different kin relations are considered in the dataset: father and daughter (F-D) with 134 pairs, father and son (F-S) with 156 pairs, mother and daughter (M-D) with 127 pairs, mother and son (M-S) with 116 pairs. Each sample is composed of one parent face image and one child face image. Image Source: Neighborhood Repulsed Metric Learning for Kinship Verification
KinFaceW-II Dataset consists of 1000 pairs of facial images of individuals with a kin relation. This database also considers four common kin relations: father and daughter (F-D), father and son (F-S), mother and daughter (M-D), mother and son (M-S). Different from the KinFaceW-I database, the positive pairs in this dataset are taken from the same photo. Image Source: Neighborhood Repulsed Metric Learning for Kinship Verification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.