Liu Yuhan

Liu Yuhan

A beginner

Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

Neuromorphic event-based recognition boosted by motion-aware learning

Published in Neurocomputing, 2025

This paper proposes a motion-aware branch (MAB) to enhance event-based recognition using neuromorphic visual sensors. By integrating motion features via attention mechanisms, the method improves recognition performance under challenging conditions.

Recommended citation: Liu, Yuhan, Deng, Yongjian, Xie, Bochen, Liu, Hai, Yang, Zhen, and Li, Youfu. (2025). "Neuromorphic event-based recognition boosted by motion-aware learning." Neurocomputing. 630:129678.
Download Paper

Conference Papers

Video frame interpolation via direct synthesis with the event-based reference

Published in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

This paper presents a novel video frame interpolation method that synthesizes intermediate frames using event-based references, improving temporal consistency and sharpness in challenging scenarios.

Recommended citation: Liu, Yuhan, Deng, Yongjian, Chen, Hao, and Yang, Zhen. (2024). "Video frame interpolation via direct synthesis with the event-based reference." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8477–8487.
Download Paper

Sam-event-adapter: Adapting segment anything model for event-RGB semantic segmentation

Published in 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024

This paper introduces the Sam-Event-Adapter, which adapts the Segment Anything Model for semantic segmentation using both event-based and RGB data, enhancing performance under challenging visual conditions.

Recommended citation: Yao, Bowen, Deng, Yongjian, Liu, Yuhan, Chen, Hao, Li, Youfu, and Yang, Zhen. (2024). "Sam-event-adapter: Adapting segment anything model for event-RGB semantic segmentation." Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), 9093–9100.
Download Paper