About Me

My name is Yong-Xiang (Sean) Lin (林詠翔 in Chinese). I received my Ph.D. in Computer Science from National Taiwan University of Science and Technology (NTUST), advised by Prof. Kai-Lung Hua. During my master’s degree, I also spent time as an exchange student at RWTH Aachen University, Germany.

My research interests span Multimodal AI, Computer Vision, and Generative AI, including large language/vision models, image-to-image translation, domain adaptation, semantic segmentation, and multi-sensor fusion (visual, thermal, radar, LiDAR). I am also broadly interested in multi-agent systems, knowledge distillation, and efficient deep learning.

I believe in empowering others through sharing knowledge — this blog is where I break down research papers and technical concepts to make them more accessible. Feel free to reach out if you’re interested in research collaboration or just want to chat about AI.

Medium

Language

  • Chinese: Native
  • English: TOEIC 845
  • Japanese: JLPT N2

Education

Sep 2020 – Jan 2025
國立臺灣科技大學-資工所。
Ph.D. in Computer Science and Information Engineering, National Taiwan University of Science and Technology
Research field: Generative AI, Computer Vision based on Deep learning.
Multimedia and Visual Computing Laboratory advised by Prof. Kai-lung Hua.
Published 5 journal articles and 6 conference papers, including two in IEEE Transactions, presented at ICIP and ICME.
Led more than 20 master students in developing computer vision solutions for collaborative industry projects.
Specialized in multi-sensor fusion systems (visual, thermal, radar, LiDAR) for autonomous systems.

Sep 2019 – Mar 2020
RWTH Aachen University, Germany
Exchange Student, Faculty of Electrical Engineering and Information Technology.

Feb 2018 – Mar 2020
國立臺灣科技大學-資工所。
M.S. in Computer Science and Information Engineering, National Taiwan University of Science and Technology (GPA: 4.12/4.30)
Thesis: Adapting Semantic Segmentation of Urban Scenes via Mask-aware Gated Discriminator.

Sep 2014 – Jan 2018
國立臺灣科技大學，主修資工系。
B.S. in Computer Science and Information Engineering, National Taiwan University of Science and Technology
Early Graduation based on Academic Excellence, GPA - 3.91/4.0 (Ranked 3rd out of 53).

Publication

Google Scholar

  1. Hanrong Ye, Chao-Han Huck Yang, Arushi Goel, Wei Huang, Zhen Wan, Jinchuan Tian, An-Chieh Cheng, Ligeng Zhu, Yuanhang Su, Yuming Lou, Yong-Xiang Lin, Dong Yang, Sreyan Ghosh, Zhijian Liu, Yukang Chen, et al. “OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM,” In Proceedings of the International Conference on Learning Representations (ICLR), 2026.
  2. Jyun-Hao Lin, Shang-Fu Chen, Tsung-Han Lin, Yong-Xiang Lin, Tai-Ming Huang, Shih-Che Chien, Kailung Hua. “PRISM: Pixel-level RGB-Infrared Self-attention Matching for Person Re-Identification,” In Proceedings of the TAAI 2025 Conference, 2025.
  3. Ting-Yu Chu, Yong-Xiang Lin, Ching-Chun Huang, Kai-Lung Hua. “Enhancing Anchor-based Weakly Supervised Referring Expression Comprehension with Cross-Modality Attention.” In Proceedings of the 17th Asian Conference on Computer Vision (ACCV), Hanoi, Vietnam, December 8-12, 2024.
  4. Wei-Tung Lin, Yong-Xiang Lin, Jyun-Wei Chen, Kai-Lung Hua. “PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement.” In Proceedings of the 17th Asian Conference on Computer Vision (ACCV), Hanoi, Vietnam, December 8-12, 2024.
  5. Kuan-Hung Huang, Yao-Bang Huang, Yong-Xiang Lin, Kai-Lung Hua, Mohammad Tanveer, Xuequan Lu, Imran Razzak. “GRA: Graph Representation Alignment for Semi-Supervised Action Recognition,” IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), vol. 35, no. 9, pp. 11896-11905, Sep. 2024. (Impact Factor: 10.451).
  6. Yao-Bang Huang, Yong-Xiang Lin, Ahmad Fauzan Aqil, Yung-Yao Chen, Kai-Lung Hua. “Graph Involutional Networks with Dynamic Feature Fusion for Skeleton-Based Action Recognition.” In Proceedings of the 2024 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, Jan. 5-8, 2024.
  7. Balin Lin, Yong-Xiang Lin, Bayisa Kune Mamade, Yung-Yao Chen, Kai-Lung Hua. “GazeVAE: Gaze Visual Attention Estimator.” In Proceedings of the 2024 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, Jan. 5-8, 2024. (Best Poster Paper Award)
  8. Jilyan Dy, John Jethro Virtusio, Daniel Tan, Yong-Xiang Lin, Joel Ilao, Yung-Yao Chen, Kai-Lung Hua. “MCGAN: Mask Controlled Generative Adversarial Network for Image Retargeting,” Neural Computing and Applications (NCAA), vol. 35, pp. 1-13, Feb. 2023. (Impact Factor: 5.102).
  9. Daniel Stanley Tan, Yong-Xiang Lin, and Kai-Lung Hua. “Incremental Learning of Multi-Domain Image-to-Image Translations,” IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), vol. 31, no. 4, pp. 1526-1539, Apr. 2021. (Impact Factor: 5.859).
  10. Yu-Cheng Liu, Mohammad Shahid, Wannaporn Sarapugdi, Yong-Xiang Lin, Jyh-Cheng Chen, Kai-Lung Hua. “Cascaded Atrous Dual Attention U-Net for Tumor Segmentation,” Multimedia Tools and Applications (MTAP), vol. 80, pp. 30007-30031, Aug. 2021. (Impact Factor: 2.577).
  11. Yong-Xiang Lin, Daniel Stanley Tan, Yung-Yao Chen, Ching-Chun Huang, and Kai-Lung Hua. “Domain Adaptation with Foreground/Background Cues and Gated Discriminators,” IEEE MultiMedia Magazine, vol. 27, no. 3, pp. 44-53, Jul-Sep. 2020. (Impact Factor: 5.633).
  12. Yong-Xiang Lin, Daniel Tan, Wen-Huang Cheng, Yung-Yao Chen, and Kai-Lung Hua. “Spatially-aware Domain Adaptation for Semantic Segmentation,” In Proceedings of the IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, Sep. 22-25, 2019.
  13. Yong-Xiang Lin, Daniel Stanley Tan, Wen-Huang Cheng, Kai-Lung Hua. “Adapting Semantic Segmentation of Urban Scenes via Mask-aware Gated Discriminator,” In Proceedings of the IEEE International Conference on Multimedia & Expo (ICME), Shanghai, China, Jul. 8-12, 2019.

Awards

  • 2024, Best Poster Award at the 42nd International Conference on Consumer Electronics (ICCE)
  • 2024, Student Travel Grant for the International Conference on Consumer Electronics (ICCE)
  • 2022, Excellent Award (NTD 800,000) in the AI+ Star Competition, sponsored by the Ministry of Digital Affairs
  • 2020, Best Master Thesis at the 13th Chinese Image Processing and Pattern Recognition Society (IPPR)
  • 2013, Placed 3rd out of 50+ participants in the 102 National High School Vocational Industrial Skills Competition

© 2018-2024 XiaoSean. All rights reserved.

Powered by Hydejack v9.2.1