W
Wei Chen
Researcher at Leiden University
Publications - 27
Citations - 329
Wei Chen is an academic researcher from Leiden University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 5, co-authored 22 publications receiving 105 citations.
Papers
More filters
Journal ArticleDOI
A survey of traditional and deep learning-based feature descriptors for high dimensional data in computer vision
TL;DR: This survey gives a comprehensive overview and key insights into the state of the art of higher dimensional features from deep learning and also traditional approaches, and presents the major challenges and future directions.
Journal ArticleDOI
SwapGAN: A Multistage Generative Approach for Person-to-Person Fashion Style Transfer
TL;DR: This paper proposes a multistage deep generative approach named SwapGAN that exploits three generators and one discriminator in a unified framework to fulfill the task end-to-end and demonstrates the improvements of SwapGAN over other existing approaches through both quantitative and qualitative evaluations.
Proceedings ArticleDOI
Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
TL;DR: In this paper, an adaptive knowledge accumulation (AKA) framework is proposed to learn continuously across multiple domains and even generalise on new and unseen domains, which can alleviate catastrophic forgetting on seen domains and demonstrates the ability to generalize to unseen domains.
Proceedings ArticleDOI
Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
TL;DR: In this article, a dual Gaussian-based variational auto-encoder (DG-VAE) is proposed to disentangle an identity discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture of Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively.
Posted Content
Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
TL;DR: A carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an Identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively.