Junyi Wu

Junyi Wu

Auto-generated profile, based on publicly available information

Junyi Wu

Fuzhou University

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
15 August 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
AZAnguo Zhang
Anguo Zhang
JSJieming Shi
Jieming Shi
JWJunyi Wu
Junyi Wu
YZYongcheng Zhou
Yongcheng Zhou
WYWei Yu
Wei Yu
Spiking neural networks (SNNs) have captivated the attention worldwide owing to their compelling advantages in low power consumption, high biological plausibility, and strong robustness. However, the intrinsic latency associated with SNNs during inference poses a significant challenge, impeding their further development and application. This latency is caused by the need for spiking neurons to collect electrical stimuli and generate spikes only when their membrane potential exceeds a firing threshold. Considering the firing threshold plays a crucial role in SNN performance, this article proposes a self-driven adaptive threshold plasticity (SATP) mechanism, wherein neurons autonomously adjust the firing thresholds based on their individual state information using unsupervised learning rules, of which the adjustment is triggered by their own firing events. SATP is based on the principle of maximizing the information contained in the output spike rate distribution of each neuron. This article derives the mathematical expression of SATP and provides extensive experimental results, demonstrating that SATP effectively reduces SNN inference latency, further reduces the computation density while improving computational accuracy, so that SATP facilitates SNN models to be with low latency, sparse computing, and high accuracy.

18 June 2022 in Pattern Recognition
Verified
Journal Article
Closed access
JWJunyi Wu
Junyi Wu
YHYan Huang
Yan Huang
ZGZhipeng Gao
Zhipeng Gao
YHYating Hong
Yating Hong
JZJianqiang Zhao
Jianqiang Zhao
XDXinsheng Du
Xinsheng Du

25 July 2011 in Applied Physics Letters
Verified
Journal Article
Closed access
PDF file
SLSu-Jien Lin
Su-Jien Lin
KLKuang-Che Lee
Kuang-Che Lee
JWJyun-Lin Wu
Jyun-Lin Wu
JWJun-Yi Wu
Jun-Yi Wu
The plasmonic structure of sandwiched TiO2/NPs-Ag/TiO2 electrodes was fabricated by sputter technology and sol–gel and spin coating procedure to enhance the performance of dye-sensitized solar cells. The improvement of the incident photon to photocurrent efficiency spectrum corresponding to the strong absorption and damping reflection indicated light trapping of plasmonic structure to elongate the optical pathways of photons. More light trapped close to photocurrent collecting electrode provides better charge-collection and light harvesting efficiencies. As a result of improved dye absorption, about 23% enhancement in photocurrent density has been achieved.

1 January 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
JWJunyi Wu
Junyi Wu
YHYan Huang
Yan Huang
MGMin Gao
Min Gao
ZGZhipeng Gao
Zhipeng Gao
JZJianqiang Zhao
Jianqiang Zhao
AZAnguo Zhang
Anguo Zhang

9 November 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
JWJunyi Wu
Junyi Wu
YHYan Huang
Yan Huang
MGMin Gao
Min Gao
ZGZhipeng Gao
Zhipeng Gao
JZJianqiang Zhao
Jianqiang Zhao
AZAnguo Zhang
Anguo Zhang
Long-term (also called Clothing-Change) person re-identification (CC-reID) aims at confirming the identity of pedestrians captured at diverse locations and/or times. Current CC-reID methods heavily rely on ID features learned by the CNN architecture. However, with limited receptive fields, CNN is hard to effectively explore some unique but discriminative ID features (e.g., hair style, tattoo and accessories) from small body regions. Compared with CNN, Transformer has certain merits in exploring more diverse ID-unique features 1 and retaining more details by the multi-head self-attention design and the removal of down-sampling operation. In this paper, a two-stream hybrid Convolution-Transformer Network (CT-Net) is proposed for CC-reID by combining both CNN and Transformer parallelly in an end-to-end learning scheme. Specifically, CT-Net contains a CNN-based stream (C-Stream) and a Transformer-based stream (T-Stream). Compared with using C-Stream only, T-Stream is used to encourage the C-Stream to explore more detailed ID-unique features when the clothing information is no reliable in CC-reID. Specifically, a Feature Supplement Module (FSM) is proposed to transfer features learned by T-Stream to C-Stream from low-level to high-level for mining more ID-unique feature. In order to further enhance the discriminability 2 and complementary of ID features learned by our CT-Net, we also introduce a hierarchical supervision with bilinear pooling (HSBP). Experimental results demonstrate that CT-Net performs favorably against the state-of-the-art methods over three CC-reID benchmarks. Meanwhile, CT-Net also demonstrates good generalization ability by achieving comparable performance on traditional person re-ID datasets such as Market-1501 and DukeMTMC-reID.

10 February 2020 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
LHLiqin Huang
Liqin Huang
QYQingqing Yang
Qingqing Yang
JWJunyi Wu
Junyi Wu
YHYan Huang
Yan Huang
QWQiang Wu
Qiang Wu
JXJingsong Xu
Jingsong Xu
Recently, Generative Adversarial Network (GAN) has been adopted to improve person re-identification (person re-ID) performance through data augmentation. However, directly leveraging generated data to train a re-ID model may easily lead to over-fitting issue on these extra data and decrease the generalisability of model to learn true ID-related features from real data. Inspired by the previous approach which assigns multi-pseudo labels on the generated data to reduce the risk of over-fitting, we propose to take sparse regularization into consideration. We attempt to further improve the performance of current re-ID models by using the unlabeled generated data. The proposed Sparse Regularized Multi-Pseudo Label (SRMpL) can effectively prevent the over-fitting issue when some larger weights are assigned to the generated data. Our experiments are carried out on two publicly available person re- ID datasets (e.g., Market-1501 and DukeMTMC-reID). Compared with existing unlabeled generated data re-ID solutions, our approach achieves competitive performance. Two classical re-ID models are used to verify our sparse regularization label on generated data, i.e., an ID-embedding network and a two-stream network.