朱轶昇，博士，讲师，主要研究方向为以人为中心的视觉理解，动作识别，姿态估计等，在IEEE TIP、TCSVT、ICCV等国内外学术期刊、会议上发表论文6篇，欢迎感兴趣的同学联系，邮箱地址：20230172@njupt.edu.cn

细粒度骨骼人体动作识别关键技术研究，在研，2026.01-2028.12，国自青基

[1] Y. Zhu and G. Liu, Dynamic Prompting Spatial Temporal Actor Transformer for Fine-grained Skeleton-based Action Recognition, in IEEE Transactions on Circuits and Systems for Video Technology, 2026. (CCF B)

[2] Y. Zhu, H. Han, Z. Yu and G. Liu, Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition, in 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2023 pp. 13867-13876. (CCF A)

[3] Y. Zhu, H. Shuai, G. Liu and Q. Liu, Multilevel Spatial–Temporal Excited Graph Network for Skeleton-Based Action Recognition [J], IEEE Transactions on Image Processing, vol. 32, pp. 496-508, 2023. (CCF A)

[4] Y. Zhu, H. Shuai, G. Liu and Q. Liu, Self-Supervised Video Representation Learning Using Improved Instance-Wise Contrastive Learning and Deep Clustering [J], IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 10, pp. 6741-6752, Oct. 2022. (CCF B)

[5] Y. Zhu, H. Hu, G. Liu and Q. Liu, Collaborative Local-Global Learning for Temporal Action Proposal [J], ACM Trans. Intell. Syst. Technol. 12, 5, Article 55 (October 2021).

[6] Y. Zhu, G. Liu. Fine-grained action recognition using multi-view attentions[J]. The Visual Computer, 2020, 36(9): 1771-1781. (CCF C)