Fashion Image Retrieval Based on Multimodal Features Enhancement and Fusion
Li, Yingjin. (2024). "Fashion Image Retrieval Based on Multimodal Features Enhancement and Fusion." CASA 2024.
CV
Education
- MPhil, The Hong Kong University of Science and Technology (Guangzhou), 2025.09 - Present
- Information Hub / Data Science and Analysis
- B.Sc. in Data Science and Big Data Technology, Wuhan Textile University, 2021.09 - 2025.09
Research Interests
- Computer Vision
- Multimodal AI
- Industrial Anomaly Detection
- Diffusion Models
- Vision-Language Learning
Selected Publications
Honors and Awards
- National Scholarship
Technical Skills
- Modeling areas: deep learning, computer vision, multimodal learning, anomaly detection
- Relevant coursework: machine vision and image processing, Python data analysis and mining, data warehousing, Spark in-memory computing, big data systems and distributed processing
Contact
- Email: yli499@connect.hkust-gz.edu.cn
- GitHub: https://github.com/PattonBrown
- Google Scholar: https://scholar.google.com/citations?user=jC4f6BEAAAAJ&hl=zh-CN