X
Xiantong Zhen
Researcher at University of Amsterdam
Publications - 149
Citations - 3940
Xiantong Zhen is an academic researcher from University of Amsterdam. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 29, co-authored 119 publications receiving 2721 citations. Previous affiliations of Xiantong Zhen include Zayed University & University of Sheffield.
Papers
More filters
Journal ArticleDOI
Spatio-Temporal Laplacian Pyramid Coding for Action Recognition
TL;DR: The proposed STLPC method achieves superb recognition rates on the KTH, the multiview IXMAS, the challenging UCF Sports, and the newly released HMDB51 datasets, and outperforms state of the art methods showing its great potential on action recognition.
Journal ArticleDOI
Identification of Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Multivariate Predictors
Yue Cui,Bing Liu,Suhuai Luo,Xiantong Zhen,Ming Fan,Tao Liu,Tao Liu,Wanlin Zhu,Mira Park,Tianzi Jiang,Tianzi Jiang,Jesse S. Jin +11 more
TL;DR: This study establishes meaningful multivariate predictors composed of selected NM, MRI and CSF measures which may be useful and practical for clinical diagnosis.
Posted Content
Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
TL;DR: This paper proposes a trellis encoder-decoder network (TEDnet) for crowd counting that achieves the best overall performance in terms of both density map quality and counting accuracy, and proposes a new combinatorial loss to enforce similarities in local coherence and spatial correlation between maps.
Proceedings ArticleDOI
Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks
TL;DR: TEDnet as mentioned in this paper proposes a trellis encoder-decoder network for crowd counting, which employs dense skip connections interleaved across paths to facilitate multi-scale feature fusions, which also helps TEDnet to absorb the supervision information.
Proceedings ArticleDOI
Relational Attention Network for Crowd Counting
TL;DR: A Relational Attention Network (RANet) with a self-attention mechanism for capturing interdependence of pixels is proposed, which consistently reduces estimation errors and surpasses the state-of-the-art approaches by large margins.