BIOGRAPGHY

I am a Ph.D student at School of Data Science, University of Virginia. My advisor is Prof. Sheng Li. Before that, I was a Master’s student at the School of Artificial Intelligence, Xidian University, advised by Prof. Yuwei Guo. For my undergraduate studies, I attended the School of Computer Science at Xidian University.

EDUCATION AND QUALIFICATIONS

Xidian University Artificial Intelligence (GPA 3.8/4.0) M.S., 2025 Xidian University Computer Science (GPA 3.7/4.0) B.S. 2022

RESEARCH EXPERIENCE

2024

RENet: Reliable and Efficient Cross Modality Learning for Unsupervised Visible and Infrared Person Re-identification (USL-VI-ReID)

renet

Proposed Hashing-based Metric to reliably measure the cross-modal similarity, improving the Rank-1 accuracy by 2.39% compared to the commonly used distance metrics.
Devised a Multi-directional Update module to efficiently bridge the modal gap, achieving SOTA performance.

A 6-month Internship at the Wan Lab, University of Nebraska Medical Center

6-mon

Collaborated on advancing the project in predicting brain age using local image features of T1-MRI scans.
Optimized and enhanced the Local U-Net for Brain Age Prediction by utilizing the Swin Transformer Block. The code has been open-sourced and is available at Wan Lab.
Secured a Strong Recommendation.

2023

Lightweight Directional-Aware Network for Classification

ldan

Conducted a comprehensive review of all non-learned operators-based Deep Learning models, providing a classification of current methods.
Introduced a lightweight directional-aware network, achieving state-of-the-art performance at a significantly lower computational cost.
Submission Update: Accepted by Artificial Intelligence Review (IF:10.7).

Transferring Modality-Aware Pedestrian Attentive Learning for Visible-Infrared Person Re-Identification (VI-ReID)

tran

Proposed a data augmentation PedMix, tailored for VI-ReID, effectively improving the mean Average Precision (mAP) by 4.67%.
Introduced a Modality Feature Transfer module, integrating cross-attention and convolution networks with minimum computational overhead, generating discriminative modality-complete features.
Submission Update: AAAI 2024 (3 wa & 1 wr) to SP.

PUBLICATIONS

Yuwei Guo, Wenhao Zhang, Yupeng Gao, Licheng Jiao, Rong Qu, Shuang Wang, Fang Liu, Jiabo Du. (2024). Revisiting Non-Learned Operators Based Deep Learning: A Lightweight Directional-Aware Network for Classification. In Artificial Intelligence Review.
Yuwei Guo, Wenhao Zhang, Licheng Jiao, Jiabo Du, Shuo Wang, Shuang Wang and Liu Fang. (2024). Visible-infrared person re-identification with region-based augmentation and cross modality attention. In Scientific Reports.

PATENTS

Yuwei Guo, Wenhao Zhang, Jiabo Du, Wei Zhan. (2023). Cross-Modal Pedestrian Re-Identification Method Based on Spatial Data Augmentation and Symmetric Cross-Modal Attention. CN Patent, Application No. 202310838299.7.
Yuwei Guo, Jiabo Du, Wenhao Zhang, Yupeng Gao. (2022). Causal Inference Based Semi-Supervised Image Classification Method. CN Patent, Application No. 202210896650.3.
Yuwei Guo, Yupeng Gao, Jiabo Du, Wenhao Zhang. (2022). Image Classification Method based on Shearlet Networks and Directional Attention Mechanism. CN Patent, Application No. 202211044682.7.

HONORS AND AWARDS

Xidian First-Class Fellowship, Xidian University (2022-2024)
Xidian Scholarship, Xidian University (2018-2022)
Provincial First Prize in the 8th China International College Students ‘Internet+’ Innovation and Entrepreneurship Competition Skills (2022)
Provincial Second Prize in the 7th China International College Students ‘Internet+’ Innovation and Entrepreneurship Competition Skills (2021)