韩志 博士，研究员，博士生导师，机器人学研究室副主任

论文发表：

[1] Xudong Wang, Xi'ai Chen, Huijie Fan, Weihong Ren, Shuai Wang, Yandong Tang, Lianqing Liu, Zhi Han. Seeing only the focus: RGB-T object-aware region enhancement for object detection in harsh environments. IEEE Transactions on Multimedia, 2026.      

[2] Xudong Wang, Zebin Han, Zhiyu Liu, Gan Li, Jiahua Dong, Baichen Liu, Lianqing Liu, Zhi Han*. Lifelong language-conditioned robotic manipulation learning. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.

[3] Xing Xie, Jiawei Liu, Ziyue Lin, Huijie Fan, Zhi Han, Yandong Tang, Liangqiong Qu. Unleashing the potential of large language models for text-to-image generation through autoregressive representation alignment. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.

[4] Sihan Wang, Xiyao Liu, Lianqing Liu, Zhi Han. ObjecTok: learning holistic and robust object tokens for MLLMs. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.

[5] Zebin Han, Xudong Wang, Baichen Liu, Qi Lyu, Zhenduo Shang, Jiahua Dong, Lianqing Liu, Zhi Han. SeqWalker: sequential-horizon vision-and-language navigation with hierarchical planning. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.

[6] Jiahua Dong, Xudong Wang, Wenqi Liang, Zongyan Han, Meng Cao, Duzhen Zhang, Hanbin Zhao, Zhi Han*. Salman Khan, Fahad Shahbaz Khan. Bring your dreams to life: continual text-to-video customization. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.

[7] Jinguo Luo, Weihong Ren, Zhiyong Wang, Xi'ai Chen, Huijie Fan, Zhi Han, Honghai Liu. Synergistic prompting learning for human-object interaction detection. IEEE Transactions on Image Processing, 34, 5710-5724, 2025.

[8] Siyuan Wang, Jiawei Liu, Wei Wang, Yeying Jin, Jinsong Du, Zhi Han. MMGT: motion mask guided two-stage network for co-speech gesture video generation. IEEE Transactions on Circuits and Systems for Video Technology, 2025.

[9] Zihang Zhao, Leiyao Cui, Sirui Xie, Saiyao Zhang, Zhi Han, Lecheng Ruan, Yixin Zhu. B*: Efficient and optimal base placement for fixed-base manipulators. IEEE Robotics and Automation Letters, 10(10), 10634-10641, 2025.

[10] Jingyang Qiao, Zhizhong Zhang, Xin Tan, Yanyun Qu, Wensheng Zhang, Zhi Han, Yuan Xie. Gradient projection for continual parameter-efficient tuning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.

[11] Liu, Shiben, Fan, Huijie, Wang, Qiang, Chen, Xi'ai, Han, Zhi, Tang, Yandong. Diverse representations embedding for lifelong person re-identification. IEEE Transactions on Neural Networks and Learning Systems, 36(10), 18145-18157, 2025.

[12] Baichen Liu, Zhi Han*, Xi'ai Chen, Yanmei Wang, Yandong Tang. Rope-net: deep convolutional neural network via robust principal component analysis, Machine Learning, 114, 150, 2025.

[13] Weihong Ren, Yu Gao, Xi'ai Chen, Zhi Han, Zhiyong Wang, Jiaole Wang and Honghai Liu. Facial expression monitoring via fine-grained vision-language alignment. IEEE Transactions on Automation Science and Engineering, 22, 7492-7505, 2025.

[14] Sihan Wang, Zhi Han, Xiyao Liu. DUAL-GDFQ: a dual-generator, dual-phase learning approach for data-free quantization. IEEE Signal Processing Letters, 32, 1600-1604, 2025.

[15] Nan Yang, MengChu Zhou, Xin Luan, Liang Qi, Yandong Tang, Zhi Han*. A subspace-based method for facial image editing. IEEE Transactions on Computational Social Systems, 12(1), 185-197, 2025.

[16] Yanmei Wang, Fupeng Chu, Zhi Han*, Yandong Tang. GeoRecon: geometric coherence for online 3D scene reconstruction from monocular video. IEEE Robotics and Automation Letters, 10(1), 500-507, 2025.

[17] Hang Yu, Huijie Fan, Xi'ai Chen, Qiang Wang, Zhi Han, POSR: Pose-assisted outlier sample re-labeling for unsupervised person re-identification. IEEE Transactions on Instrumentation and Measurement, 74, 1-11, 2024.

[18] Yanmei Wang, Xin Wu, Xiyao Liu, Fupeng Chu, Huan Liu, Zhi Han*. Label smoothing regularization-based no hyperparameter domain generalization. Knowledge-Based Systems, 305, 2025.

[19] Zhiyu Liu, Zhi Han, Yandong Tang, Xi-Le Zhao, Yao Wang. Low-tubal-rank tensor recovery via factorized gradient descent. IEEE Transactions on Signal Processing, 72, 5470-5483, 2024.

[20] Weihong Ren, Jinguo Luo, Weibo Jiang, Liangqiong Qu, Zhi Han, Jiandong Tian, Honghai Liu. Learning self- and cross-triplet context clues for human-object interaction detection. IEEE Transactions on Circuits and Systems for Video Technology, 34(10), 9760-9773, 2024.

[21] Xudong Wang, Weihong Ren, Xi'ai Chen, Huijie Fan, Yandong Tang, Zhi Han. Uni-YOLO: vision-language model-guided YOLO for robust and fast universal detection in the open world. MM '24: The 32nd ACM International Conference on Multimedia, 2024.

[22] Zhi Han, Shihong Ding, Baichen Liu, Yandong Tang, Xueshan Qiu, Enhua Wang, Huanyu Zhao. Histopathological differential diagnosis and estrogen receptor/progesterone receptor immunohistochemical evaluation of breast carcinoma using a deep learning-based artificial intelligence architecture. The American Journal of Pathology, 194(12), 2313-2325, 2024.

[23] Xin Luan, Qiang Wang, Huijie Fan, Xi'ai Chen, Zhi Han, Yandong Tang. Feature distillation and guide network for unsupervised underwater image enhancement. Engineering Applications of Artificial Intelligence, 136, 2024.

[24] Xinglong Xu, Weihong Ren, Xi'ai Chen, Huijie Fan, Zhi Han, Honghai Liu. Exploiting multi-modal synergies for enhancing 3D multi-object tracking. IEEE Robotics and Automation Letters, 9(10), 8643-8650, 2024.

[25] Shiben Liu, Huijie Fan, Qiang Wang, Zhi Han, Yu Guan, Yandong Tang. Wavelet–pixel domain progressive fusion network for underwater image enhancement. Knowledge-Based Systems, 299, 2024.

[26] Baichen Liu, Dongwei Wang, Qi Lv, Zhi Han*, Yandong Tang. Towards super compressed neural networks for object identification: quantized low-rank tensor decomposition with self-attention. Electronics, 13(7), 1330, 2024.

[27] Xudong Wang, Xi'ai Chen, Weihong Ren, Zhi Han, Huijie Fan, Yandong Tang, Lianqing Liu. Compensation atmospheric scattering model and two-branch network for single image dehazing. IEEE Transactions on Emerging Topics in Computational Intelligence, 2024.

[28] Jinguo Luo, Weihong Ren, Weibo Jiang, Xi'ai Chen, Qiang Wang, Zhi Han, Honghai Liu. Discovering syntactic interaction clues for human-object interaction detection. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[29] Zhi Han, Yanmei Wang, Shaojie Zhang, Huijie Fan, Yandong Tang, Yao Wang. Online video sparse noise removing via nonlocal robust PCA. IEEE Transactions on Multimedia, 26, 7130-7145, 2024.

[30] Huidi Jia, Yeqing Xiao, Qiang Wang, Xi’ai Chen, Zhi Han, Yandong Tang. Underwater image enhancement network based on dual layers regression. Electronics, 2023.

[31] Xi’ai Chen , Zhen Wang, Kaidong Wang, Huidi Jia, Zhi Han and Yandong Tang. Multi-dimensional low-rank with weighted Schatten p-norm minimization for hyperspectral anomaly detection. Remote Sensing, 16, 74, 2023.

[32] Yanmei Wang, Zhi Han*, Siquan Yu, Shaojie Zhang, Baichen Liu and Huijie Fan. DILS: Depth Incremental Learning Strategy. Frontiers in Neurorobotics, 17, 2023.

[33] Nan Yang，Xin Luan, Huidi Jia, Zhi Han, Xiaofeng Li and Yandong Tang. CCR: Facial image editing with continuity, consistency and reversibility. International Journal of Computer Vision, 2023.

[34] Wei Zhang, Zhi Han, Xi’ai Chen, Baichen Liu, Huidi Jia, Yandong Tang. Fully kernected neural networks. Journal of Mathematics, 2023.

[35] 罗琼，韩志*，陈希爱，唐延东. 基于p范数的E-3DTV高光谱去噪模型. 计算机应用与软件, 40(7), 222-228, 2023.

[36] Xiyao Liu, Zhong Ji, Yanwei Pang, Zhi Han. Dual distillation discriminator networks for domain adaptive few-shot learning. Neural Networks, 16, 625-633, 2023.

[37] Xiyao Liu, Zhong Ji, Yanwei Pang, Zhi Han. Self-taught cross-domain few-shot learning with weakly supervised object localization and task-decomposition. Knowledge-Based Systems, 265, 2023.

[38] Zhi Han, Shaojie Zhang, Zhiyu Liu, Yanmei Wang, Junping Yao, Yao Wang. Tensor robust principal component analysis with side information: models and applications. IEEE Transactions on Circuits and Systems for Video Technology, 33(8), 3713-3725, 2023.

[39] Siquan Yu, Zhi Han*, Yandong Tang, Chengdong Wu. Neural network equivalent model for highly efficient massive data classification. Science China Information Sciences, 66(3), 139101:1–139101:2, 2023.

[40] Siyu Guo, Xi’ai Chen, Huidi Jia, Zhi Han, Zhigang Duan, Yandong Tang. Fusing hyperspectral and multispectral images via low-rank Hankel tensor representation. Remote Sensing, 2022.

[41] Baichen Liu, Zhi Han∗, Xi’ai Chen, Wenming Shao, Huidi Jia, Yanmei Wang, Yandong Tang. A novel compact design of convolutional layers with spatial transformation towards lower-rank representation for image classification. Knowledge-Based Systems, 255, 2022.

[42] Huidi Jia, Xi’ai Chen, Zhi Han, Baichen Liu, Tianhui Wen, Yandong Tang. Nonconvex nonlocal tucker decomposition for 3D medical image super-resolution. Frontiers of Neuroinformatics, 2022.

[43] Xi’ai Chen, Siyu Guo, Huidi Jia, Baichen Liu, Zhenyu Li, and Zhi Han. Group Sparsity Regularized High Order Tensor for HSIs Super-Resolution. International Conference on Intelligent Robotics and Applications (ICIRA), 125–137, 2022.

[44] Baichen Liu, Huidi Jia, Zhi Han*, Xi’ai Chen, Yandong Tang. An analysis of low-rank decomposition selection for deep convolutional neural networks. International Conference on Intelligent Robotics and Applications (ICIRA), 480-490, 2022.

[45] Huidi Jia, Siyu Guo, Zhenyu Li, Xi’ai Chen, Zhi Han, Yandong Tang. Low-rank tensor Tucker decomposition for hyperspectral images super-resolution. International Conference on Intelligent Robotics and Applications (ICIRA), 502-512, 2022.

[46] Yang Zhang, Yao Wang*, Zhi Han*, Xi'ai Chen, Yandong Tang. Effective tensor completion via element-wise weighted low-rank tensor train with overlapping ket augmentation. IEEE Transactions on Circuits and Systems for Video Technology, 32(11), 7286-7300, 2022.

[47] Nan Yang, Bingjie Xia, Zhi Han, Tianran Wang. A domain-guided model for facial cartoonlization. IEEE/CAA Journal of Automatica Sinica, 9(10), 1886-1888, 2022.

[48] Zhi Han, Siquan Yu, Shao-Bo Lin, Ding-Xuan Zhou. Depth selection for deep ReLU nets in feature extraction and generalization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(4), 1853-1868, 2022.

[49] 郭思雨, 陈希爱, 贾慧迪, 韩志, 刘佳鑫, 郭锐, 唐延东. 基于非凸低秩张量近似的图像超分辨率重建, 计算机应用研究, 2021.

[50] Wei Wu, Qiang Wang, Siquan Yu, Qiong Luo, Sen Lin, Zhi Han, Yandong Tang. Outside box and contactless palm vein recognition based on a wavelet denoising ResNet. IEEE Access, 9, 82471-82484, 2021.

[51] Yanmei Wang, Jiaxin Liu, Siquan Yu, Kai Wang, Zhi Han, Yandong Tang. Underwater object detection based on YOLO-v3 network. IEEE International Conference on Unmanned Systems (ICUS), 2021.

[52] Jiaxin Liu, Dongwei Wang, Siquan Yu, Xueliang Li, Zhi Han, Yandong Tang. A survey of image clustering: Taxonomy and recent methods. IEEE International Conference on Real-Time Computing and Robotics (RCAR), Xining, China, July 15-19, 2021.

[53] Shengchuan Li, Yanmei Wang, Qiong Luo, Kai Wang, Zhi Han, Yandong Tang. Total variation regularized low-rank tensor decomposition with nonlocal for single image denoising. IEEE International Conference on Real-Time Computing and Robotics (RCAR), Xining, China, July 15-19, 2021.

[54] 张少杰, 罗琼, 韩志, 唐延东. 基于边信息的高光谱图像恢复模型. 计算机应用研究, 38(10), 3166-3171, 2021.

[55] Siquan Yu, Jiaxin Liu, Zhi Han*, Yong Li, Yandong Tang, Chengdong Wu. Representation learning based on autoencoder and deep adaptive clustering for image clustering. Mathematical Problems in Engineering, 2021.

[56] Qiong Luo, Baichen Liu, Yang Zhang, Zhi Han*, Yandong Tang. Low-rank decomposition on transformed feature maps domain for image denoising. The Visual Computer, 37, 1899-1915, 2021.

[57] Jianjiang Zhu, Siquan Yu, Lei Gao, Zhi Han*, Yandong Tang. Saliency-based diver target detection and localization method. Mathematical Problems in Engineering, 2020.

[58] Qian Zhao, Xiangyu Rui, Zhi Han, and Deyu Meng. Multilinear multitask learning by rank-product regularization. IEEE Transactions on Neural Networks and Learning Systems, 31(4), 1336-1350, 2020.

[59] 高振远, 韩志*, 唐延东. 基于整体和非局部低秩分解的视频脉冲噪声去除方法. 计算机应用, 40(S1) ,165-170, 2020.

[60] 贾慧迪, 韩志*, 陈希爱, 唐延东. 基于非局部张量火车分解的彩色图像修补. 模式识别与人工智能, 32(10): 955-963, 2019.

[61] 张杨, 韩志*, 罗琼, 唐延东. 基于张量火车分解因子折凹范数的张量补全算法. 计算机应用研究, 36, 366-368, 2019.

[62] Jianjiang Zhu, Siquan Yu, Zhi Han*, Yandong Tang, Chengdong Wu. Underwater object recognition using transformable template matching based on prior knowledge. Mathematical Problems in Engineering, 2019.

[63] Guiping Shen, Zhi Han*, Xi'ai Chen, Yandong Tang, Yang Zhang. Background reconstruction via low rank tensor factorization. 10th International Conference on Graphics and Image Processing (ICGIP 2018), 2018.

[64] Yang Zhang, Zhi Han*, Yandong Tang. Color image denoising based on low-rank tensor train. 10th International Conference on Graphics and Image Processing (ICGIP 2018), 2018.

[65] Xiuyi Yang, Zhi Han, Yandong Tang, Jianda Han. A experimental study to invariance of several groups action to the input of residual networks. IEEE International Conference on Information and Automation (ICIA), 2018. IEEE.

[66] Xiuyi Yang, Zhi Han, Yandong Tang, Jianda Han. Switch unit (SU): a novel type of unit for the activation function. IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2018. IEEE.

[67] Zilu Ma, Shiqi Liu, Deyu Meng, Yong Zhang, SioLong Lo, Zhi Han. On convergence properties of implicit self-paced objective. Information Sciences, 462, 132-140, 2018.

[68] Jiandong Tian, Zhi Han, Weihong Ren, Xi'ai Chen, Yandong Tang. Snowflake removal for videos via global and local low-rank decomposition. IEEE Transactions on Multimedia, 20(10), 2659-2669, 2018.

[69] Xi'ai Chen, Zhi Han*, Yao Wang, Qian Zhao, Deyu Meng, Lin Lin, Yandong Tang. A generalized model for robust tensor factorization with noise modeling by mixture of Gaussians. IEEE Transactions on Neural Networks and Learning Systems, 29(11), 5380-5393, 2018.

[70] Guiping Shen, Zhi Han*, Xi'ai Chen, Yandong Tang. Robust video denoising with sparse and dense noise modelings. Science China Information Sciences, 61(1), 018103, 2018.

[71] 余思泉, 韩志, 唐延东, 吴成东. 基于对抗生成网络的纹理合成方法. 红外与激光工程, 47 (2), 43-48, 2018.

[72] Yao Wang, Xi'ai Chen, Zhi Han*, Shiying He. Hyperspectral image super-resolution via nonlocal low-rank tensor approximation and total variation regularization. Remote Sensing, 9 (12), 1286, 2017.

[73] Zhi Han, Guiping Shen, Siquan Yu, Naida Ding, Jiandong Tian, Yandong Tang. Active trace: a sparse spatiotemporal representation for videos. IEEE Access, 5, 22433-22442, 2017.

[74] 李冰锋, 唐延东, 韩志. 几何结构保持非负矩阵分解的数据表达方法. 信息与控制, 46 (1), 53-59, 2017.

[75] 李冰锋, 唐延东, 韩志. 基于超图直推非负矩阵分解的图像标注法研究. 计算机仿真, 34 (2), 380-384, 440, 2017.

[76] Qiong Luo, Zhi Han*, Xi'ai Chen, Yao Wang, Deyu Meng, Dong Liang, Yandong Tang. Tensor RPCA by Bayesian CP factorization with complex noise. International Conference on Computer Vision (ICCV), 2017.

[77] Weihong Ren, Jiandong Tian, Zhi Han, Antoni Chan, Yandong Tang. Video desnowing and deraining based on matrix decomposition. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

[78] Xi'ai Chen, Zhi Han*, Guiping Shen, Yao Wang and Yandong Tang. Robust tensor factorization with MRF under complex noise. IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2017. IEEE.

[79] Zhi Han, Jiandong Tian, Liangqiong Qu, and Yandong Tang. A new intrinsic-lighting color space for daytime outdoor images. IEEE Transactions on Image Processing, 26 (2), 1031-1039, 2017.

[80] Siquan Yu, Jinxin Shao, Zhi Han*, Lei Gao, Yang Lin, Yandong Tang, and Chengdong Wu. Mine Like Object Detection and Recognition Based on Intrackability and Improved BOW. IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2016. 222-227. IEEE.

[81] Shiying He, Haiwei Zhou, Yao Wang, Wenfei Cao, and Zhi Han. Super-resolution reconstruction of hyperspectral images via low rank tensor modeling and total variation regularization, IGARSS, 2016.

[82] Bingfeng Li, Yandong Tang and Zhi Han. Robust Structure Preserving non-negative matrix factorization for dimensionality reduction. Mathematical Problems in Engineering, vol. 2016, Article ID 7474839, 14 pages, 2016. doi:10.1155/2016/7474839.

[83] 李冰锋, 唐延东, 韩志. 基于改进的 NMF 人脸识别算法研究. 计算机仿真, 2016 (3): 428-432.

[84] Xi'ai Chen, Zhi Han*, Yao Wang, Qian Zhao, Deyu Meng, and Yandong Tang. Robust tensor factorization with unknown noise, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[85] Xi'ai Chen, Zhi Han*, Yao Wang, Yandong Tang, and Haibin Yu. Nonconvex plus quadratic penalized low-rank and sparse decomposition for noisy image alignment, Science China Information Sciences, 59(5), 2016.

[86] Jiandong Tian, Zhigang Duan, Weihong Ren, Zhi Han and Yandong Tang. Simple and effective calculations about spectral power distributions of outdoor light sources for computer vision. Optics Express, 24 (7), 7266-7286, 2016.

[87] Liangqiong Qu, Zhigang Duan, Jiandong Tian, Zhi Han, and Yandong Tang. Object color constancy for outdoor multiple light sources. CCF Chinese Conference on Computer Vision. Springer Berlin Heidelberg, 369-378, 2015.

[88] Xi'ai Chen, Zhi Han*, and Yandong Tang. Manifold mapping learning by regression tree boosting. IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2015. 1579-1583. IEEE.

[89] Zhi Han, Zongben Xu, and Song-Chun Zhu. Video primal sketch: a unified middle-level representation for video. Journal of Mathematical Imaging and Vision, vol. 53 (2), 151-170, 2015.

[90] Liangqiong Qu, Jiandong Tian, Zhi Han, and Yandong Tang, Pixel-wise orthogonal decomposition for color illumination invariant and shadow-free image. Optics Express, vol. 23, 2220-2239, 2015.

[91] Wenfei Cao, Yao Wang, Can Yang, Xiangyu Chang, Zhi Han, Zongben Xu. Folded-concave penalization approaches to tensor completion. Neurocomputing, vol. 152, 261-273, 2014.

[92] Guiping Shen, Zhi Han* and Yandong Tang. Robust video denoising by low-rank decomposition and modeling noises with mixture of Gaussian. IEEE International Conference on Robotics and Biomimetics (ROBIO), 2014.

[93] Zhi Han, Jianjun Wang, Jia Jing, and Hai Zhang, A simple Gaussian measurement bound for exact recovery of block-sparse signals, Discrete Dynamics in Nature and Society, vol. 2014, Article ID 104709, 8 pages, 2014. doi:10.1155/2014/104709

[94] Zhi Han, Zongben Xu, and Song-Chun Zhu. Video primal sketch: a generic middle-level representation of video. International Conference on Computer Vision (ICCV), 2011. 1283-1290, IEEE, NJ, USA.

[95] Zhi Han, Deyu Meng, Zongben Xu, and Nannan Gu. Incremental alignment manifold learning. Journal of computer science and technology (JCST), Vol. 26 (1): 153-165, 2011.

[96] 韩志, 朱旭, 徐宗本. 基于度分析的广义胞映射分析方法.应用数学学报, 34 (2): 240-253, 2011.

[97] 朱旭, 韩志. 求解大规模TSP问题的混合算法. 工程数学学报, 2007年 05期 923-926.

研究项目：

1、国家自然科学基金重大项目：机器人行为驱动的类生命智能生成机制

经费来源：国家自然科学基金；2026.01-2030.12; 项目负责人

2、国家重点研发计划项目：智能-驱动一体化的类生命机器人理论与方法

经费来源：国家科技部；2025.01-2027.12; 项目负责人

3、国家自然科学基金联合基金重点项目：面向海洋牧场养护的水下机器人协同感知与高效作业

经费来源：国家自然科学基金；2024.01-2027.12; 项目负责人

4、中科院稳定支持基础研究领域青年团队计划项目(课题)：神经网络辨识建模

经费来源：中国科学院；2023-2027; 课题负责人

5、国家重点研发计划项目: 基于类生命孪生的机器人智能学习方法 

经费来源：国家科技部；2021-2023; 项目负责人

6、基于低秩张量特性的图像视频表达建模及其算法应用研究

经费来源：中国科学院（中科院青年创新促进会优秀会员）；2018-2021;项目负责人

7、深海环境机器视觉感知方法研究

经费来源：国家自然科学基金；2021-2024;项目负责人

8、目标背景与算法仿真 可视化系统

经费来源：企业服务项目；2017-2018;项目负责人

9、视频的中层视觉表达与高层行为识别研究

经费来源：国家自然科学基金；2014-2016;项目负责人

10、机器人视觉环境理解理论方法研究

经费来源：机器人学国家重点实验室; 2012 -2013