He Zhang

Mr. He Zhang

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 February 2024 in Signal, Image and Video Processing
Verified
Journal Article
Closed access
PDF file
HZHe Zhang
He Zhang
LYLu Yin
Lu Yin
HZHanling Zhang
Hanling Zhang
XWXuesong Wu
Xuesong Wu


22 July 2022 in Signal, Image and Video Processing
Verified
Journal Article
Closed access
PDF file
HZHe Zhang
He Zhang
ZYZhaoyuan Yin
Zhaoyuan Yin
HZHanling Zhang
Hanling Zhang

31 March 2023 in Multimedia Systems
Verified
Journal Article
Closed access
PDF file
HZHe Zhang
He Zhang
LYLu Yin
Lu Yin
HZHanling Zhang
Hanling Zhang

20 December 2021 in arXiv
Verified
Preprint
Open access
PDF file
CYChenglin Yang
Chenglin Yang
YWYilin Wang
Yilin Wang
Jianming ZhangJianming Zhang
Jianming Zhang
HZHe Zhang
He Zhang
ZWZijun Wei
Zijun Wei
AYAlan Yuille
Alan Yuille
Despite the impressive representation capacity of vision transformer models, current light-weight vision transformer models still suffer from inconsistent and incorrect dense predictions at local regions. We suspect that the power of their self-attention mechanism is limited in shallower and thinner networks. We propose Lite Vision Transformer (LVT), a novel light-weight transformer network with two enhanced self-attention mechanisms to improve the model performances for mobile deployment. For the low-level features, we introduce Convolutional Self-Attention (CSA). Unlike previous approaches of merging convolution and self-attention, CSA introduces local self-attention into the convolution within a kernel of size 3x3 to enrich low-level features in the first stage of LVT. For the high-level features, we propose Recursive Atrous Self-Attention (RASA), which utilizes the multi-scale context when calculating the similarity map and a recursive mechanism to increase the representation capability with marginal extra parameter cost. The superiority of LVT is demonstrated on ImageNet recognition, ADE20K semantic segmentation, and COCO panoptic segmentation. The code is made publicly available.

13 January 2023 in TechRxiv
Verified
Preprint
Open access
PDF file
HZHe Zhang
He Zhang
HZHanling Zhang
Hanling Zhang
LYLu Yin
Lu Yin
Transformer-based Micro-expression Recognition Improved by Data Expansion and Relabeling