个人主页

https://faculty.sustech.edu.cn/hezh/

个人简介

何志海，南方科技大学电子与电气工程系讲席教授， IEEE Fellow (2015)。2021年6月全职回国前任美国密苏里大学电子工程系讲席教授。研究方向包括生成式视觉AI、多模态大模型推理与控制优化、健康守护机器人、AI 智能体。2019-2025年连续入选斯坦福大学全球顶级科学家终身科学影响力排行榜。在工业AI检测、AI居家医养领域具有丰富的科研成果产业化经验。作为负责人，承担了国家基金委重点项目和国家自然科学基金天元数学与智能+交叉重点专项。 荣获IEEE TCSVT国际期刊最佳论文、中国人工智能学会吴文俊人工智能技术发明奖等奖项。

课题组网站：https://nkdailab.github.io/

教育经历

博士  1998~2001 美国加州大学圣芭芭拉分校 电子工程

硕士  1994~1997 中国科学院计算数学所 计算数学

本科  1990~1994 中国北京师范大学 数学

工作经历

讲席教授  202106~至今  中国南方科技大学

终身正教授  201309~202106  美国密苏里大学

终身副教授  200909~201308  美国密苏里大学

助理教授  200309~200908  美国密苏里大学

研究工程师  200105~200308  美国大卫索纳福研究中心

研究简介

研究方向：生成式视觉AI、多模态大模型推理与控制优化、健康守护机器人、AI 智能体

主要研究成果包括：建立了图像视频压缩通信系统的统一码率控制模型；第一个把信息论中的香侬率失真（R-D）模型拓展到能量域（P），建立了P-R-D模型，用于移动视频设备的能耗优化；最早提出和研究视觉感应器网络；并广泛应用于健康监控、战场情报、野生动物跟踪、环境保护等领域。

所获荣誉

IEEE TCSVT 最佳论文奖，2002

SPIE VCIP 青年研究员奖，2004

密苏里大学青年教师研究创新奖，2008

密苏里大学杰出青年研究创新奖，2009

IEEE Fellow，2015

密苏⾥大学年度教授奖，2017

深圳市海外高层次人才，2021

2024年度吴文俊人工智能科学技术奖技术发明二等奖，中国人工智能学会，2025

代表性论文

[1] Yi Zhang, Chun-Wun Cheng, Junyi He, Zhihai He, Carola-Bibiane Schönlieb, Yuyan Chen, Angelica I Aviles-Rivero. "Cross-Modal Few-Shot Learning with Second-Order Neural Ordinary Differential Equations."[J] AAAI Conference on Artificial Intelligence (AAAI2025). (Oral paper).

[2] Siqi Wu, Yinda Chen, Dong Liu, Zhihai He. " Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression."[J] AAAI Conference on Artificial Intelligence (AAAI2025). (Oral paper).

[3] Yi Zhang, Ke Yu, Siqi Wu, Zhihai He. "Conceptual Codebook Learning for Vision-Language Models"[J]. European Conference on Computer Vision (ECCV 2024).

[4] Yushun Tang, Shuoshuo Chen, Zhihe Lu, Xinchao Wang, Zhihai He. "Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation"[J]. European Conference on Computer Vision (ECCV 2024).

[5] Yi Zhang, Ke Yu, Angelica I Aviles-Rivero, Jiyuan Jia, Yushun Tang, Zhihai He. "Training-Free Feature Reconstruction with Sparse Optimization for Vision-Language Models"[J]. Proceedings of the 32nd ACM International Conference on Multimedia, 2024. 4387-4396

[6] Yushun Tang, Shuoshuo Chen, Jiyuan Jia, Yi Zhang, Zhihai He. "Domain-Conditioned Transformer for Fully Test-time Adaptation."[J] Proceedings of the 32nd ACM International Conference on Multimedia, 2024. 6260-6269.

[7] Zhehan Kan, Shuoshuo Chen, Ce Zhang, Yushun Tang, Zhihai He, "Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation." 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5537-5546, 17-24 June 2023.

[8] Yushun Tang, Ce Zhang, Heng Xu, Shuoshuo Chen, Jie Cheng, Luziwei Leng, Qinghai Guo, Zhihai He, "Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation."  In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3728-3738. 2023.17-24 June 2023.

[9] Zhehan Kan, Shuoshuo Chen, Zeng Li, Zhihai He, "Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation." Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part V. Cham: Springer Nature Switzerland, 2022.

[10] Shichao Kan, Yigang Cen, and Zhihai He, Relative Order Analysis and Optimization for Unsupervised Learning of Discriminative Features, IEEE Proceedings of Computer Vision and Pattern Recognition (CVPR), June 2021.

[11] Hao Sun and Zhihai He, “Reciprocal learning networks for human trajectory prediction,” IEEE Proceedings of Computer Vision and Pattern Recognition (CVPR), June 2020 (Oral paper).

[12] Yang Li, Zhiqun Zhao, Yigang Cen, and Zhihai He, Snowball: Iterative Model Evolution and Confident Sample Discovery for Semi-Supervised Learning on Very Small Labeled Datasets, accepted by IEEE Transactions on Multimedia, May 2020.

[13] Jianhe Yuan and Zhihai He, “Ensemble generative cleaning for adversarial defense of deep neural networks,” IEEE Proceedings of Computer Vision and Pattern Recognition (CVPR), June 2020.

[14] Kan, Shichao, Yigang Cen, Zhihai He, Zhi Zhang, Linna Zhang, and Yanhong Wang. "Supervised deep feature embedding with handcrafted feature." IEEE Transactions on Image Processing 28, no. 12 (2019): 5809-5823.

[15] Zhi Zhang, Zhihai He, and Wenmin Cao, Animal Detection from Highly Cluttered Natural Scenes Using Spatiotemporal Object Region Proposals and Patch Verification, IEEE Transaction on Multimedia, Vol. 18, No. 10, pp. 2079-2092, July 2016. 

[16] Chenglin Li, Hongkai Xiong, Junni Zou, Zhihai He, "Joint Source and Flow Optimization for Scalable Video Multi-rate Multicast over Hybrid Wired/Wireless Coded Networks", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 21, No. 5, pp. 550-564, May 2011.

[17] Zhou, Zhongna, Xi Chen, Yu-Chia Chung, Zhihai He, Tony X. Han, and James M. Keller. "Activity analysis, summarization, and visualization for indoor human activity monitoring." IEEE transactions on circuits and systems for video technology 18, no. 11 (2008): 1489-1498.

[18] He, Zhihai, and Sanjit K. Mitra. "A linear source model and a unified rate control algorithm for DCT video coding." IEEE transactions on Circuits and Systems for Video Technology 12, no. 11 (2002): 970-982.

[19] He, Zhihai, Jianfei Cai, and Chang Wen Chen. "Joint source channel rate-distortion analysis for adaptive mode selection and rate control in wireless video coding." IEEE Transactions on circuits and systems for video technology 12, no. 6 (2002): 511-523.

[20] He, Zhihai, and Sanjit K. Mitra. "A unified rate-distortion analysis framework for transform coding." IEEE Transactions on Circuits and Systems for Video Technology 11, no. 12 (2001): 1221-1236. (Best Paper)

招聘信息

何志海课题组正在招聘生成式视觉AI、多模态大模型推理与控制优化、健康守护机器人、AI 智能体等相关专业博士后、博士等，同时欢迎来自国内外大学及科研机构的访问学者和交流学生，有意加入者请将简历发送至：hezh@sustech.edu.cn。

联系地址：广东省深圳市南山区学苑大道1088号南方科技大学工学院南楼434

电话：+86 13602642426

联系方式

南方科技大学电子与电气工程系人工智能实验室

深圳市南山区学苑大道1088号南方科技大学工学院南楼434室