Weijia Fan

Hi, there! I'm weijia, currently a postgraduate student at the Computer Vision Institute (CVI), Shenzhen University, under the supervision of Professor Qiufu Li. The principal investigator (PI) of our institute is Professor Linlin Shen. My current research focuses on representation learning and visual recognition tasks. In the future, I aim to explore research in cross-modal models, particularly focusing on vision-language models. My goal is to develop effective training strategies and loss functions that enhance the performance of these models across both common and downstream tasks.

I am actively seeking a Ph.D. position focused on cross-modal learning and vision-language models. If my research profile aligns with your interests, please contact me at: fanweijia2023 at email dot szu dot edu dot cn.

I am seeking be a visiting student from February to August 2025.

If you are interested in connecting with me, feel free to reach out via email: fanweijia2023 at email dot szu dot edu dot cn / wakinghoursszu at outlook dot com.

Email / CV_En / CV_Zh / Google Scholar / Github

News

[2024/07] Achieved 2nd place in the Micro-Expression Recognition Competition at the China Conference on Affective Computing (CCAC). Congratulations to Zihan and Hang Xiao for their outstanding performance! For more details, visit the official competition page.

Works

BCE3S: Binary Cross-entropy based Tripartite Synergistic Learning for Long-tailed Recognition
Weijia Fan, Qiufu Li*, Jiajun Wen, Xiaoyang Peng, Linlin Shen
CoreA Submission
We propose a BCE-based tripartite synergistic learning method (BCE3S) that enhances feature compactness, classifier separability, and balance between head and tail classes in long-tailed recognition tasks, achieving high accuracy on imbalanced datasets.

EPL: Empirical Prototype Learning for Deep Face Recognition
Weijia Fan, Jiajun Wen, Xi Jia, Linlin Shen, Jiancan Zhou, Qiufu Li*
arxiv.org/2405.12447
We propose an Empirical Prototype Learning (EPL) method designed to mitigate performance degradation caused by hard samples tending to deviate the prototype away from the ideal class center.

A short-term price prediction-based trading strategy
Weijia Fan, Ru Zhang*, Hao He, Siyu Hou, Yongbo Tan
Plos One 19 (3), e0294970
Stock trading strategies based on short-term price predictions, with case studies on gold and Bitcoin.

Sailing through uncertainty: The impact of geopolitical risks on technology adoption in U.S. corporations—A corporate culture lens
Shizhen Bai, Yongbo Tan, Chunjia Han, Mu Yang, Weijia Fan, Brij B Gupta, Varsha Arya
Technological Forecasting and Social Change, 2025, 213: 124025.

Exploring thematic influences on theme park visitors' satisfaction: An empirical study on Disneyland China
Shizhen Bai, Hao He, Chunjia Han*, Mu Yang, Dingyao Yu, Xinrui Bi, Brij B. Gupta*, Weijia Fan, Prabin Kumar Panigrahi
Journal of Consumer Behaviour 23 (1), 90-106
we analyze user-generated data using structural topic modeling to explore the impact of themes on visitor satisfaction at Shanghai Disneyland, revealing dynamic changes in visitor focus and the diminishing correlation between reviews and ratings over time, offering valuable insights into consumer behavior and tourism research.

What makes a theme park experience less enjoyable? Evidence from online customer reviews of Disneyland China
Shizhen Bai, Hao He, Chunjia Han, Mu Yang*, Xinrui Bi,Weijia Fan
Frontiers in Psychology 14, 1120483
we leverage structural topic modeling and sentiment analysis on 112,000 reviews of Shanghai Disneyland to uncover key factors behind visitors’ dissatisfaction, providing insights into addressing issues like parking, service attitude, and entry processes to improve theme park management and visitor experience.

Education

	Shenzhen University, Shenzhen, China Master's Degree in Computer Science (CS) • Sep. 2023 - Jun. 2026 GPA: 3.65/4, Average Score: 88.2/100, Ranking: 22/132 (Overall) Supervisors: Prof. Qiufu Li
	Harbin University of Commerce, Harbin, China Bachelor's Degree in Internet of Things (IOT) • Sep. 2019 - Jun. 2023 GPA: 3.67/4, Average Score: 92.67/100, Ranking: 1/118 (Overall)

Language

IELTS Overall Band Score (Dec. 2024): 6.0 (Listening: 5.5, Reading: 7.0, Writing: 5.5, Speaking: 6.0). Currently striving to improve my IELTS score (ToT).

Honors & Scholarships

China National Scholarship (Rate<=0.02%), 2023

Personal Interests