袁进，理学博士、副教授、博士生导师。2008年，复旦大学计算机信息与技术系数据库专业毕业，获硕士学位；2013年，新加坡国立大学计算机学院多媒体专业毕业，获博士学位；2014年9月加入湖南大学信息科学与工程学院计算机工程系。

计算机视觉包括目标检测、目标跟踪，图像语义标注等；

多媒体信息检索包括图像搜索、视频搜索；

机器学习；

自动驾驶。

    本科生课程：人工智能，机器智能，多媒体技术

    研究生课程：人工智能导论

    留学生课程：Advanced Artificial Intelligence

[1]     Jinhong Hu, Guojin Zhong, Jin Yuan*, Wenbo Pan, XiaopingWang, MCT-CCDiff: Context-aware Contrastive Diffusion model withMediator-bridging Cross-modal Transformer for Image Change Captioning, IEEETransactions on Image Processing (T-IP), 2025. （CCF A）

[2]     Guojin Zhong, Pan Wang, JinYuan*, Zhiyong Li, Long Chen, Multi-Resolution DecomposableDiffusion Model for Non-Stationary Time Series Anomaly Detection, InternationalConference Learning Representations (ICLR), 2025. （CAAI A）

[3]     Guojin Zhong, Jinhong Hu, Jiajun Chen, Jin Yuan*,Wenbo Pan. DECIDER: Difference-aware Contrastive Diffusion Model withAdversarial Perturbations for Image Change Captioning, AAAI Conference onArtificial Intelligence (AAAI), 2025. （CCF A）

[4]     Xu Zhang, Jin Yuan*, Hanwang Zhang, Guojin Zhong, Yongsheng Zang, Jiacheng Lin, Zhiyong Li*. SGDiff: Scene Graph GuidedDiffusion Model for Image Collaborative SegCaptioning, AAAI Conference onArtificial Intelligence (AAAI), 2025.（CCF A）

[5]     Xu Zhang, Kailun Yang, Jiacheng Lin, Jin Yuan*, Zhiyong Li, and Shutao Li. PVPUFormer: Probabilistic Visual Prompt UniffedTransformer for Interactive Image Segmentation, IEEE Transactions on ImageProcessing (T-IP), 2024.（CCF A）

[6]     Guojin Zhong, Yifu Guo, Jin Yuan*, Qianjun Zhang,Weili Guan, Long Chen. PROMOTE: Prior-Guided Diffusion Model withGlobal-Local Contrastive Learning for Exemplar-Based ImageTranslation, ACM International Conference on Multimedia (MM), 2024. （CCF A）

[7]     Zian Wang, Xianghui Liao, Jin Yuan*, You Yao, Zhiyong Li, CDC-YOLOFusion: Leveraging Cross-scale Dynamic Convolution Fusionfor Visible-Infrared Object Detection, in IEEE Transactions on Intelligent Vehicles(T-IV), 2024. （SCI一区）

[8]     Zhiqiang Xiao, Jiacheng Lin, Jiajun Chen, Haolong Fu, Yifan Li, JinYuan*,and Zhiyong Li. Privacy Preservation Network with Global-aware Focal Loss forInteractive Personal Visual Privacy Preservation. Neurocomputing, 2024. （SCI二区）

[9]     HaolongFu, Jin Yuan*, Guojin Zhong, Xuan He,Jiacheng Lin, Zhiyong Li. CF-Deformable DETR: an End-to-end Alignment-freeModel for Weakly Aligned Visible-infrared Object Detection, International JointConference on Artificial Intelligence (IJCAI), 2024. （CCF A）

[10]  Haolong Fu, Hanhao Liu, JinYuan*, Xuan He,Jiacheng Lin, and Zhiyong Li. YOLO-Adaptor: A Fast Adaptive One-Stage Detectorfor Non-Aligned Visible-Infrared Object Detection, IEEE Transactions onIntelligent Vehicles (T-IV), 2024.（SCI一区） 

[11]  Xuan He, Zian Wang, Jiacheng Lin , Ke Nai, Jin Yuan*,and Zhiyong Li, DO-SA&R: Distant Object Augmented Set Abstraction and Regressionfor Point-Based 3D Object Detection. IEEE Transactions on Image Processing(T-IP), 2023.（CCF A）

[12]  Guojin Zhong, JinYuan*, Pan Wang, KailunYang, Weili Guan, Zhiyong Li. Contrast-augmented Diffusion Model withFine-grained Sequence Alignment for Markup-to-Image Generation, ACMInternational Conference on Multimedia (MM), 2023. （CCF A）

[13]  Lin, Jiacheng, Dai, Xianwen, Nai, Ke, Yuan, Jin*,Li,Zhiyong, Zhang, Xu, and Li, Shutao. BRPPNet: Balanced privacy protectionnetwork for referring personal image privacy protection. Expert Systems withApplications (ESWA), 2023.（SCI一区）

[14]  He, Xuan, Jin Yuan*, Mengyao Li, RunminWang, Haidong Wang, and Zhiyong Li. A Text-Specific Domain Adaptive Network forScene Text Detection in the Wild. Applied Intelligence, 2023.（SCI二区）

[15]  He, Xuan, Zhiyong Li, Jiacheng Lin, KeNai, Jin Yuan,Yifan Li, and Runmin Wang. Domain adaptive multigranularity proposal networkfor text detection under extreme traffic scenes. Computer Vision and ImageUnderstanding (CVIU), 2023.（CCF B）

[16]  He, Xuan, Fan Yang, Jiacheng Lin, HaolongFu, JinYuan*, Kailun Yang, and Zhiyong Li. SSD-MonoDETR: SupervisedScale-aware Deformable Transformer for Monocular3D Object Detection. IEEETransactions on Intelligent Vehicles (T-IV), 2023.（SCI一区）

[17]  Jin Yuan*, Shuai Zhu, Shuyin Huang, Hanwang Zhang, YaoqiangXiao, Zhiyong Li*, and Meng Wang, Discriminative Style Learning forCross-domain Image Captioning, IEEE Transactions on Image Processing (T-IP), 2022.（CCF A）

[18]  Handong Wang, Xuan He, Zhiyong Li*, Jin Yuan*,Shutao Li, JDAN: Joint Detection and Association Network for Real-Time OnlineMulti-Object Tracking, ACM Transactions on Multimedia Computing, Communications,and Applications (TOMM), 2022.（CCF B） 

[19]  Haidong Wang, Zhiyong Li*, Ke Nai, Jin Yuan, ShutaoLi, XianghuaLi, BTN: Neuroanatomical aligningbetween visual object tracking in deep neural network and smooth pursuit in brain. Neurocomputing,2022. （SCI 二区）

[20]  Zhiyong Li*，ChenmingHu, Ke Nai, Jin Yuan, Siamese target estimation network withAIoU loss for real-time visual tracking, Journal of Visual Communication andImage Representation, 2021. （CCF C）

[21]  Zhiyong Li*，JingyiLv, Ying Chen, Jin Yuan, Person re-identification with partprediction alignment, Computer Vision and Image Understanding (CVIU), 2021.  （CCF B）

[22]  Yaoqiang Xiao, Yi Li, Jin Yuan, History-basedattention in seq2seq model for multi-label text classification, Knowledge-BasedSystems (KBS), 2021. （CCF C）

[23]  Jin Yuan*，LeiZhang，Songrui Guo，Yi Xiao，and Zhiyong Li, Image captioning with a joint attention mechanism byvisual concept samples, ACM Transactions on Multimedia Computing, Communications,and Applications (TOMM), 2020. （CCF B）

[24]  Zhihao Ye，GongyaoJiang， Ye Liu， Zhiyong Li, JinYuan*,Document and Word Representations Generated by Graph Convolutional Network andBERT for Short Text Classification, European Conference on ArtificialIntelligence (ECAI), 2020.（CCF B）

[25]  Yiqiang Wu, Zhiyong Li, Ying Chen , Ke Nai , JinYuan*, Real-time traffic sign detection and classificationtowards real traffic scene. Multimedia Tools and Applications, 2020. （CCF C）

[26]  Xianyi Zhu, Jin Yuan*, Yi Xiao,YanZheng, Zheng Qin, Stroke classification for sketch segmentation byfine-tuning a developmental vggnet16. Multimedia Tools and Applications, 2020. （CCF C）

[27]  Jin Yuan*, Heng-Chang Xiong, Yi Xiao, Weili Guan, Meng Wang, Richang Hong, andZhiYong Li, Gated CNN: Integrating multi-scale feature layers for object detection,Pattern Recognition (PR), 2019. （CCF B）

[28]  Jin Yuan*, Xingxing Hou, Yaoqiang Xiao, Da Cao and Liqiang Nie, Multi-CriteriaActive Deep Learning for Image Classification. Journal of Knowledge-basedSystem (KBS), 2019. （CCF C）

[29]  Y. Chen, J. Yuan, Z. Y. Li, Y. Q. Wu,M.Nouioua, G. Q. Xie, Person re-identification based on re-ranking withexpanded k-reciprocal nearest neighbors”, Journal of Visual Communication and ImageRepresentation, 2019. （CCF C）

[30]  Y. Zheng, X. Cao, Y. Xiao, X.Y. Zhu, J. Yuan*, Jointresidual pyramid for joint image super-resolution, Journal of VisualCommunication and Image Representation, 2019. （CCF C）

[31]  Y. Xiao, C. Pan, Y. Zheng, X. Y. Zhu, Z. Qin, J.Yuan,Gradient- Guided DCNN for Inverse Halftoning and Image Expanding, AsianConference on Computer Vision (ACCV), 2018. （CCF C）

[32]  J. Yuan, D. Xu, H. C. Xiong and Z. Y. Li, A Novel Object Tracking Algorithmbased on Enhanced Perception Hash and Online Template Matching, IEEE InternationalConference on Natural Computation, Fuzzy Systems and Knowledge Discovery, 2016.

[33]  Jin Yuan*, Yiliang Zhao, Huangbo Luan, Meng Wang and Tat-seng Chua. Memory Recallbased Video Search: Finding Videos You Have Seen Before based on Your Memory, ACMTransactions on Multimedia Computing, Communications, and Applications (TOMM), 2014. （CCF B）

[34]  X. J. Zhao, J. Yuan, M. Wang, G. D. Li, R. C. Hong, Z. J.Li, T.–S. Chua, Video recommendation over multiple information sources. Journalon Multimedia System, 2013. （CCF C）

[35]  J. Yuan, H. -B. Luan, D. J. Hou, H. Zhang, Y. -Tao Zheng, Z. –J.Zha, T.-S.Chua, Video Browser Showdown by NUS. ACM International Conference on MultimediaModeling, 2012. （CCF C）

[36]  X. J. Zhao, J. Yuan, R. C. Hong,M.Wang, Z. J. Li, T. -S. Chua, On Video Recommendation over Social Network. ACMInternational Conference on Multimedia Modeling, 2012. （CCF C）

[37]  X. J. Zhao, J. Yuan, G. D. Li, T. -S. Chua. RelationshipStrength Estimation for Online Social Networks with the Study on Facebook,Neurocomputing, 2012. （CCF C） 

[38]  Jin Yuan, Zhengjun Zha, Yantao Zheng, Meng Wang, Xiangdong Zhou and Tat-sengChua, Utilizing Related Samples to Enhance Interactive Concept-Based VideoSearch, IEEE Transactions on Multimedia (T-MM), 2011. （CCF B）

[39]  Jin Yuan, Zhengjun Zha, Yantao Zheng, Meng Wang, Xiangdong Zhou and Tat-sengChua, Learning Concept Bundles for Video Search with Complex Queries, ACMInternational Conference on Multimedia (MM), 2011. （CCF A）

[40]  X. J. Zhao, G. D. Li, M. Wang, J. Yuan, Z.-JZha, Z. J. Li, T.-S Chua，IntegratingRich Information for Video Recommendation with Multi-Task Rank Aggregation, ACMInternational Conference on Multimedia (MM), 2011. （CCF A）

[41]  J. Yuan, Z. -J. Zha, Z. D. Zhao, X. D. Zhou, and T. -S. Chua, Utilizingrelated samples to learn complex queries in interactive concept-based videosearch. ACM International Conference on Image and Video Retrieval (CIVR), 2010. （CCF B）

[42]  X. Y. Chen, J. Yuan, L. Q. Nie, Z.-J.Zha, S. C. Yan and T. -S. Chua, TRECVID 2010 Known-item Search by NUS, TRECVIDWorkshop, 2010.

横向项目

1.自动的车辆重定位技术，2022（主持）

2.多媒体智能检索技术,2022（主持）

3.模态有缺失环境下的跨膜台目标感知技术,2023（主持）

4.AI图像自动生成技术,2023（主持）

5.动态障碍物长时轨迹预测技术研究,2024（主持）

纵向项目

1.交互式可控图像描述迁移学习关键技术研究（主持，国家自然科学基金面上，2023-2026）

2.城市智能客车多模态协同感知与安全高效行驶关键技术研究（参与，国家自然科学基金，2022-2025）

3.边缘计算中异常检测及自适应网络控制研究（参与，国家自然科学基金，2020-2023）

4.面向光纤无线融合系统的混沌加密技术及其性能研究（参与，国家自然科学基金，2020-2023）

5.自动驾驶系统的CPS计算架构与视觉感知方法研究（参与，国家自然科学基金，2020-2023）

6.基于深度神经网络的交互式图像编辑与视频颜色编辑（参与，国家自然科学基金，2019-2021）

7.基于多模态数据融合的短视频信息检索及推荐方法研究（参与，国家自然科学基金，2019-2021）

8.面向微博的用户动态兴趣建模和智能推荐方法研究（参与，国家自然科学基金，2018-2020）

9.交互式cosplay动漫数字表演系统（主持，湖南省科技计划项目，2017-2019）

10.基于复杂查询类型的多媒体检索（主持，国家自然科学基金，2016-2018）

1．尚昊璞，李胜奇，王嘉淇，袁进，“盲人之窗-针对盲人的现实识别系统”，第八届“华为杯”中国大学生智能设计竞赛，一等奖，2018；

2．任晓凡，庞家强，李青青，袁进，“基于多摄像头的跨区域特定车辆检索系统”. 第七届“华为杯”中国大学生智能设计竞赛，一等奖，2017；

3．鲁信金，陈瑶，尹业荣,袁进，“车标识别系统”，第六届“华为杯”中国大学生智能设计竞赛，二等奖，2016；

4．袁进，“湖南大学2018年度创新创业优秀指导教师”，2018；

5．廖琨，黄淑茵，袁进，“Integrating local visual representation and feature information for vehicle re-identification”, ACM ICFEICT,2021, best paper。

6. 袁进，朱帅，“基于风格的跨域图像语义描述技术”， 湖南大学优秀硕士学位论文。

7. 袁进，钟国金，“基于扩散模型的可控图像生成技术研究”，湖南大学优秀硕士学位论文。

8. 袁进，王盼，“基于扩散模型的非平稳时间序列异常检测方法研究”，湖南大学优秀硕士学位论文。