J
Jiawei Li
Researcher at Hong Kong Baptist University
Publications - 11
Citations - 1188
Jiawei Li is an academic researcher from Hong Kong Baptist University. The author has contributed to research in topics: Discriminative model & Graph (abstract data type). The author has an hindex of 8, co-authored 9 publications receiving 787 citations.
Papers
More filters
Proceedings Article
Hierarchical Discriminative Learning for Visible Thermal Person Re-Identification
TL;DR: An improved two-stream CNN network is presented to learn the multimodality sharable feature representations and identity loss and contrastive loss are integrated to enhance the discriminability and modality-invariance with partially shared layer parameters.
Proceedings ArticleDOI
Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
TL;DR: This work proposes to learn a generalized feature space via a novel multi-adversarial discriminative deep domain generalization framework under a dual-force triplet-mining constraint, which ensures that the learned feature space is discriminating and shared by multiple source domains, and thus more generalized to new face presentation attacks.
Posted Content
Dynamic Label Graph Matching for Unsupervised Video Re-Identification
TL;DR: In this paper, a dynamic graph matching (DGM) method is proposed to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association.
Proceedings ArticleDOI
Dynamic Label Graph Matching for Unsupervised Video Re-identification
TL;DR: In this paper, a dynamic graph matching (DGM) method is proposed to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association.
Proceedings ArticleDOI
Domain Transfer Support Vector Ranking for Person Re-identification without Target Camera Label Information
TL;DR: Experimental results show that the proposed DTRSVM outperforms existing methods without using label information in target cameras, and the top 30 rank accuracy can be improved by the proposed method upto 9.40% on publicly available person re-identification datasets.