石恒璨
副教授，博士生导师
国家级高层次青年人才
机器人视觉感知与控制技术国家工程研究中心成员
地址：湖南大学机器人视觉感知与控制技术国家工程研究中心307
邮箱：shihengcan@hnu.edu.cn
一、个人简介
主要研究方向人工智能、多模态大模型、视觉感知、视觉-语言多模态学习、情感计算等。
在计算机视觉与多媒体顶级期刊会议IJCV、CVPR、ECCV、ACMMM、SIGIR、IEEE TMM等发表接收论文40余篇。曾获中国图象图形学学会优秀博士学位论文奖（全国每年仅10人）、遥感图像稀疏表示与智能分析竞赛一等奖（11国2191队伍中第1名）、ACM Multimedia多模态情感计算最佳奖等。
长期担任计算机视觉顶级会议CVPR、ICCV、ECCV、机器学习顶级会议ICML、ICLR、NeurIPS、多媒体领域顶级会议ACMMM、人工智能顶级会议AAAI、IJCAI、机器人顶级会议ICRA、IROS等网络主席、领域主席、程序委员会委员，顶级期刊IEEE TPAMI、IJCV、TIP、TMM、TCSVT、TIE、TNNLS、PR等审稿人。
二、招生、招聘信息
招收博士生、硕士生以及博士后研究人员。课题组隶属于王耀南院士团队。欢迎对人工智能、多模态大模型、视觉感知、视觉-语言多模态学习、情感计算感兴趣的学生加入我们团队。
优秀者可推荐至澳大利亚悉尼大学、莫纳什大学、阿德莱德大学、香港中文大学、香港城市大学等QS前100大学深造或访问交流，腾讯、阿里、百度、字节、商汤等知名企业位于中国、美国、澳大利亚、新加坡等地研发部门工作或实习。
三、教育与工作经历
2024-至今，湖南大学，副教授
2020-2024，澳大利亚莫纳什大学，研究员
2014-2019，电子科技大学，博士
2010-2014，电子科技大学，学士
四、部分代表性科研成果
[1]. Hengcan Shi, Munawar Hayat, and Jianfei Cai. “LLMFormer: Large language model for open-vocabulary semantic segmentation.” International Journal of Computer Vision (IJCV), 2025. （机器视觉顶级期刊，CCF-A）
[2]. Jiateng Liu, Hengcan Shi, Haiwen Liang, Xiaolin Xu, Yuan Zong, Yaonan Wang, Wenming Zheng. " NaME: A Natural Micro-expression Dataset for Micro-expression Recognition in the Wild", Proceedings of the 33rd ACM International Conference on Multimedia (ACMMM), 2025. （多媒体顶级会议，CCF-A）
[3]. Jin Ye, Son Duy Dao, Yicheng Wu, Yasmeen George, Thanh Nguyen-Duc, Daniel F Schmidt, Hengcan Shi, Winston Chong, Jianfei Cai, “New Multiple Sclerosis Lesion Segmentation via Calibrated Inter-patch Blending”, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025.（医学机器视觉顶级会议）
[4]. Duy Tho Le, Chenhui Gou, Stavya Datta, Hengcan Shi, Ian Reid, Jianfei Cai, Hamid Rezatofighi, “JRDB-PanoTrack: An open-world panoptic segmentation and tracking robotic dataset in crowded human environments”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024. （机器视觉顶级会议，CCF-A）
[5]. Hengcan Shi, Munawar Hayat, and Jianfei Cai. "Unified open-vocabulary dense visual prediction." IEEE Transactions on Multimedia (TMM), 2024. （多媒体顶级期刊，一区TOP）
[6]. Duy-Tho Le, Hengcan Shi, Jianfei Cai, Hamid Rezatofighi, “Diffusion model for robust multi-sensor fusion in 3d object detection and bev segmentation”, European Conference on Computer Vision (ECCV), 2024. （机器视觉顶级会议）
[7]. Hengcan Shi, Munawar Hayat, Jianfei Cai, “Transformer Scale Gate for Semantic Segmentation”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. （机器视觉顶级会议，CCF-A）
[8]. Hengcan Shi, Munawar Hayat, and Jianfei Cai. "Open-vocabulary object detection via scene graph discovery." Proceedings of the 31st ACM International Conference on Multimedia (ACMMM), 2023. （多媒体顶级会议，CCF-A）
[9]. Son Duy Dao, Hengcan Shi, Dinh Phung, Jianfei Cai. "Class Enhancement Losses with Pseudo Labels for Open-Vocabulary Semantic Segmentation." IEEE Transactions on Multimedia (TMM), 2023. （多媒体顶级期刊，一区TOP）
[10]. Hengcan Shi, Munawar Hayat, Yicheng Wu, Jianfei Cai, “ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022. （机器视觉顶级会议，CCF-A）
[11]. Duy Tho Le, Hengcan Shi, Hamid Rezatofighi, Jianfei Cai, “Accurate and real-time 3D pedestrian detection using an efficient attentive pillar network”, IEEE Robotics and Automation Letters (RA-L) 2022. （机器人高水平期刊，二区TOP）
[12]. Tingtian Li, Zixun Sun, Haoruo Zhang, Jin Li, Ziming Wu, Hui Zhan, Yipeng Yu, Hengcan Shi, “Deep Music Retrieval for Fine-Grained Videos by Exploiting Cross-Modal-Encoded Voice-Overs”, Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2021. （信息检索顶级会议，CCF-A）
[13]. Hengcan Shi, Hongliang Li, Qingbo Wu, and King Ngi Ngan, “Query Reconstruction Network for Referring Expression Image Segmentation”, IEEE Transactions on Multimedia (TMM), 2020. （多媒体顶级期刊，一区TOP）
[14]. Heqian Qiu, Hongliang Li, Qingbo Wu, and Hengcan Shi, “Offset Bin Classification Network for Accurate Object Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. （机器视觉顶级会议，CCF-A）
[15]. Heqian Qiu, Hongliang Li, Qingbo Wu, FanmanMeng, Hengcan Shi, Taijin Zhao, and King Ngi Ngan, “Language-Aware Fine-Grained Object Representation for Referring Expression Comprehension”, ACM international conference on Multimedia (ACMMM), 2020. （多媒体顶级会议，CCF-A）
[16]. Heqian Qiu, Hongliang Li, Qingbo Wu, Fanman Meng, Linfeng Xu, King Ngi Ngan, and Hengcan Shi, “Hierarchical Context Features Embedding for Object Detection”, IEEE Transactions on Multimedia (TMM), 2020. （多媒体顶级期刊，一区TOP）
[17]. Hengcan Shi, Hongliang Li, Qingbo Wu, and Zichen Song, “Scene Parsing via Integrated Classification Model and Variance-Based Regularization”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. （机器视觉顶级会议，CCF-A）
[18]. Hengcan Shi, Hongliang Li, Qingbo Wu, FanmanMeng, and King Ngi Ngan, “Boosting scene parsing performance via reliable scale prediction”, ACM international conference on Multimedia (ACMMM), 2018. （多媒体顶级会议，CCF-A, Oral）
[19]. Hengcan Shi, Hongliang Li, Fanman Meng, and Qingbo Wu, “Key-Word-Aware Network for Referring Expression Image Segmentation”, European Conference on Computer Vision (ECCV), 2018. （机器视觉顶级会议）
[20]. Hengcan Shi, Hongliang Li, Fanman Meng, Qingbo Wu, Linfeng Xu, and King N. Ngan,“Hierarchical Parsing Net: Semantic Scene Parsing from Global Scene to Objects”, IEEE Transactions on Multimedia (TMM), 2018 （多媒体顶级期刊，一区TOP）
