H
Haibin Yan
Researcher at Beijing University of Posts and Telecommunications
Publications - 4
Citations - 15
Haibin Yan is an academic researcher from Beijing University of Posts and Telecommunications. The author has contributed to research in topics: Discriminative model & Sparse approximation. The author has an hindex of 1, co-authored 4 publications receiving 6 citations.
Papers
More filters
Proceedings ArticleDOI
KINMIX: A Data Augmentation Approach for Kinship Verification
Chaohui Song,Haibin Yan +1 more
TL;DR: A KinMix method to generate positive samples in the feature space for facial kinship verification by using a pair of features with a kin relationship to construct a feature space instead of a single image, which aims to maintain the clustering results of features.
Journal ArticleDOI
Structure-aware fusion network for 3D scene understanding
TL;DR: A structural deep metric learning method on pixels and points is proposed to explore the relations and further utilize them to adaptively map the images and point clouds into a common canonical space for prediction.
Proceedings ArticleDOI
Domain transfer sparse representation for single sample face recognition
Venice Erin Liong,Haibin Yan +1 more
TL;DR: A domain transfer sparse representation-based classification method by using an auxiliary dataset to learn intra-class variations and transferring them into the single-sample training set, extended to discriminative DT-SRC (DDTSRC) by making use of the label information samples in the auxiliary set to exploit more discriminating information in the learned meta-space.
Proceedings ArticleDOI
Discriminative metric learning for video-based kinship verification
TL;DR: A new video face dataset called Kinship Face Videos in the Wild (KFVW) is presented which were captured in wild conditions for the video-based kinship verification study, as well as the standard benchmark.