|
Liyun Zhang
Special Appointed Assistant Professor
|
Graduate
Biography
I am currently a Special Appointed Assistant Professor at 
Aonishi Lab,
The University of Tokyo.
I was a Specially-Appointed Researcher/Fellow at 
ISLab,
The University of Osaka.
I obtained my Ph.D. degree at 
Takemura Lab,
The University of Osaka,
advised by Prof. Haruo Takemura and Prof. Photchara Ratsamee.
I was a visiting scholar at 
Georgia Tech
advised by Prof. Animesh Garg.
I was a specially appointed researcher at 
Sysmex Corporation,
and embedded software engineer worked at 
Huawei,
ZTE Corporation, etc.
Research interests: Multimodal Large Language Model, Embodied AI, Affective Computing, and Explainable AI.
Openings: I am open to receiving all kinds and forms of collaboration opportunities related to my research interests!
News
• 2025.8: One paper about Evaluation Framework for Multi-Annotator Tendency Learning submitted to arXiv.
• 2025.4: One paper about Multi-Annotator Learning with Missing Labels submitted to arXiv.
• 2025.2: One paper about Multi-Annotator Tendency Learning submitted to arXiv.
• 2024.11: One paper about Diffusion Policy submitted to arXiv.
• 2024.8: One paper about Multimodal Large Language Model accepted to MRAC’24 @ ACMMM.
• 2024.4: I start a new research career as a Specially-Appointed Researcher/Fellow at ISLab, The University of Osaka.
• 2023.6: One paper about Vision Enhancement accepted to TCSVT.
• 2023.2: I start a research collaboration with Georgia Tech, advised by Prof. Animesh Garg.
• 2023.1: One paper about Image Translation accepted to WACV 2023.
• 2022.11: One paper about Robotic Perception accepted to SSRR 2022.
Publications
# Corresponding author; * Equal contribution|
|
|
|
MicroEmo: Time-Sensitive Multimodal Emotion Recognition with Subtle Clue Dynamics in Video Dialogues
Liyun Zhang, Zhaojie Luo, Shuqiong Wu, Yuta Nakashima#. In Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing (MRAC’24 @ ACMMM), 2024. [Paper] |
|
|
|
|
Panoptic-Level Image-to-Image Translation for Object Recognition and Visual Odometry Enhancement
Liyun Zhang, Photchara Ratsamee#, Zhaojie Luo#, Yuki Uranishi, Manabu Higashida, Haruo Takemura. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023. [Paper] [Code,Data] |
|
|
|
|
Panoptic-aware Image-to-Image Translation
Liyun Zhang, Photchara Ratsamee, Bowen Wang, Zhaojie Luo, Yuki Uranishi, Manabu Higashida, Haruo Takemura. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023. [Paper] [Code,Data] [DOI] |
|
|
|
|
Thermal-to-Color Image Translation for Enhancing Visual Odometry of Thermal Vision
Liyun Zhang, Photchara Ratsamee, Yuki Uranishi, Manabu Higashida, Haruo Takemura. IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), 2022. [Paper] |
|
|
|
|
Uneven Illumination Image Segmentation Based on Multi-threshold S-F
Liyun Zhang, Nanyan Liu, Yuanbin Hou, Xiaojian Liu. Opto-Electronic Engineering (OEE), 2014. [Paper] |
Teams
Embodied AI Group:
 Animesh Garg Professor (Georgia Tech) |
 Jason Orlosky Professor (Augusta University & The University of Osaka) |
 Photchara Ratsamee Associate Professor (Kansai University & The University of Osaka) |
 Masato Kobayashi Assistant Professor (The University of Osaka) |
Affective Computing Group:
 Zheng Lian Associate Professor (Institute of Automation, Chinese Academy of Sciences) |
 Zhaojie Luo Associate Professor (Southeast University) |
 Shuqiong Wu Associate Professor (The University of Osaka) |
Students:
 Xuanmeng Sha PhD Student (The University of Osaka) |
Teaching & Working
| 2025.10-Current | Special Appointed Assistant Professor | The University of Tokyo |
| 2024.4-2025.9 | Specially-Appointed Researcher/Fellow | The University of Osaka |
| 2023.2-2024.3 | Visiting Scholar | Georgia Tech |
| 2023.7-2024.2 | Research Assistant | The University of Osaka |
| 2021.5-2023.3 | Student Researcher | Sysmex |
| 2021.4-2021.9 | Teaching Assistant | The University of Osaka |
| 2020.10-2021.3 | Research Assistant | The University of Osaka |
| 2017.12-2018.9 | Embedded Software Engineer | ZTE |
| 2016.11-2017.3 | Software R&D Engineer | Huawei |
| 2015.7-2017.12 | Embedded Software Engineer |  Huaqin Tech |
Invited Talks
| In Progress |
Recent Community Services
Reviewer Service
| Conference on Computer Vision and Pattern Recognition (CVPR) | 2026 |
| ACM International Conference on Multimedia (ACMMM) | 2025 |
| International Conference on Computer Vision (ICCV) | 2025 |
| Conference on Computer Vision and Pattern Recognition (CVPR) | 2025 |
| Pattern Recognition (PR) | 2024 |
| IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) | 2023 |
| IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) | 2023 |
| Conference on Computer Vision and Pattern Recognition (CVPR) | 2022 |
| European Conference on Computer Vision (ECCV) | 2022 |