YAOZONG GAN Yaozong Gan

Short Biography: I received the B.S. degree in Electronic Information Engineering from Sichuan University, China, in 2020, and the M.S. degree in Information Science from Hokkaido University, Japan, in 2023.

I am now a Ph.D. student at the Graduate School of Information Science and Technology at Hokkaido University.

My research interests include large language models (LLM)/large multimodal models (LMM), autonomous driving, and multimodal understanding of sports videos (especially soccer videos). My recent focus has been on LLM and LMM, particularly exploring their potential in real-world scenarios such as autonomous driving and video understanding of sports videos. Additionally, I have been a collaborative researcher with Japan Radio Co., Ltd since 2022.06.

I am looking for research collaboration, especially LLM and LMM-related research for autonomous driving and sports videos.

Also, I am open to research internships. Please feel free to send me an email if you are interested!

E-mail: gan[at]lmd.ist.hokudai.ac.jp

IEEE   recserch

News

[2024/08] Invited to serve as a reviewer for ICLR 2025.

[2024/06] Our MLLM-based work for exploring traffic sign recogntion in autonomous driving is Accepted by ICIP 2024! Many thanks to my co-authors!

Biography

  • 2023/04 ~ Present Hokkaido University, Ph.D. in Information Science
  • 2022/06 ~ Present Japan Radio Co., Ltd., Collaborative Researcher
  • 2021/04 ~ 2023/03 Hokkaido University, M.S. in Information Science
  • 2020/10 ~ 2021/03 Hokkaido University, Research Student
  • 2016/09 ~ 2020/06 Sichuan University, B.S. in Electronic Information Engineering

 

Publication

Journal

  1. Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Think twice before recognizing: Large multimodal models for general fine-grained traffic sign recognition,” Preprint, 2024. [arXiv]
  2. Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Zero-shot Traffic Sign Recognition Based on Midlevel Feature Matching,” Sensors, vol. 23, no. 23, 9607, 2023. [Paper]

International Conference

  1. Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Cross-domain Few-shot In-context Learning for Enhancing Traffic Sign Recognition,” IEEE International Conference on Image Processing (ICIP), 2024. [arXiv]
  2. Yaozong Gan, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Transformer Based Multimodal Scene Recognition in Soccer Videos,” IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp. 1-6, 2022. [Paper]
  3. Yaozong Gan, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Scene Retrieval in Soccer Videos by Spatial-temporal Attention with Video Vision Transformer,” IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), pp. 453-454, 2022. [Paper]
  4. Yaozong Gan, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Multi-class Similar Scene Retrieval in Soccer Videos: A Scene Confusion Reduction Method Based on Combination of Long and Short Frame Sequences,” IEEE Global Conference on Consumer Electronics (GCCE), pp. 117-118, 2021. [Paper]

Domestic Conference

  1. Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Fine-grained Traffic Sign Recognition Via Cross-domain Few-shot In-context Learning,” Meeting on Image Recognition and Understanding (MIRU), pp. 1-5, Kumamoto, 2024.
  2. Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “A Note on Traffic Sign Recognition Based on Vision Transformer Adapter Using Visual Feature Matching,” ITE Technical Report, vol. 47, no. 6, pp. 208-211, Sapporo, 2023.
  3. Yaozong Gan, Ren Togo, Takahiro Ogawa, Miki Haseyama, “A Note on Transformer-based Scene Recognition in Soccer Videos Using Different Length of Clips,” ITE Technical Report, vol. 46, no. 6, pp. 167-170, Sapporo, 2022.

Fellowship

  1. Hokkaido University Next Generation AI Doctoral Fellowship (2024/04 ~ 2026/03) [Link]
  2. Hokkaido University EXEX Doctoral Fellowship (2024/04 ~ 2024/09) [Link]
  3. Hokkaido University Ambitious Doctoral Fellowship (2023/04 ~ 2024/03) [Link]

Society Activity

  1. Reviewer, ICLR, 2025 [Link]
  2. Reviewer, ACM Multimedia, 2024 [Link]
  3. Reviewer, Meeting on Image Recognition and Understanding, 2024 [Link]
  4. Reviewer, International Conference on Electrical, Computer and Energy Technologies, 2024 [Link]
  5. Presentations of SDGs, サイエンスフェスタ 2023 [Link]

Coverage

  1. “博士学生が描く、66のミライ,” サイエンスフェスタ 2023, 2023/12/16. (Efficient Urban Road Recognition Based on Artificial Intelligence) [Link]

Visitors



stats counter
unique visitors since 2024/03/18