个人信息

姓  名: 帅惠 性  別: 男 导师类型: 硕士生导师
技术职称: 讲师 电子邮箱: huishuai@njupt.edu.cn
专业型硕士招生类别(领域): (085400)电子信息
photo

个人简介:

帅惠 讲师 2023年博士毕业于南京信息工程大学,研究方向为计算机视觉、三维环境感知、情感计算等。在IEEE TAPMI、TIP、TGRS、CVPR、ECCV等领域内权威期刊和会议发表论文20余篇,担任IEEE TMM、TCSVT、TII、PRCV等期刊和会议审稿人。先后承担国家青年科学基金项目(C类)、江苏省自然科学基金青年基金项目、江苏省基础研究计划重点项目(子课题),参与2030人工智能重大专项项目、国家自然基金重点项目等,入选2024江苏省青年科技人才托举工程,获得江苏省自然科学百篇优秀学术成果1项,指导学生获“挑战杯”全国大学生课外学术科技作品竞赛2024 年度“揭榜挂帅”专项赛特等奖,获2024年度中国图像图形学会自然科学一等奖。

研究领域:

计算机视觉、三维环境感知、情感计算


科研项目:

[1]国家自然科学基金委员会,青年项目:图像-语言提示的开放世界三维点云语义分割方法研究,2026.01-2028.12,在研,主持;
[2]江苏省科学技术厅,江苏省自然科学基金青年项目:开放世界三维点云语义分割中的跨模态提示方法研究,2028.09-2028.08,在研,主持;
[3]江苏省教育厅,江苏省高等学校基础科学(自然科学)研究面上项目:跨模态特征融合驱动的高效点云语义分割方法研究,2025.10-2027.10,在研,主持;
[4]江苏省科学技术厅,江苏省基础研究计划重点项目:多模态大模型高效训推与可信计算方法研究,2024.01-2027.08,在研,子课题负责人;
[5]国家自然科学基金委员会,联合基金项目:面向复杂环境的快速三维场景数字化方法研究,2025.01-2028.12,在研,参与;
[6]国家自然科学基金委员会,联合基金项目:复杂时空环境下图像理解理论与方法,2022.01-2025.12,结题,参与;
[7]科学技术部,科技创新2030——“新一代人工智能”重大项目,2022.01-2024.12,结题,参与;


代表性学术成果:

[1] Shuai Hui, Wu Lele, Liu Qingshan. Adaptive multi-view and temporal fusing transformer for 3d human pose estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(4): 4122-4135.
[2] Shuai Hui, Xu Xiang, Liu Qingshan. Backward attentive fusing network with local aggregation classifier for 3D point cloud semantic segmentation[J]. IEEE Transactions on Image Processing, 2021, 30: 4973-4984.
[3] Xu Xiang, Kong Lingdong, Shuai Hui, Liu Qingshan. Frnet: Frustum-range networks for scalable lidar segmentation[J]. IEEE Transactions on Image Processing, 2025.
[4] Zhu Yisheng, Shuai Hui, Liu Guangchan, Liu Qingshan. Multilevel spatial–temporal excited graph network for skeleton-based action recognition[J]. IEEE Transactions on Image Processing, 2022, 32: 496-508.
[5] Wang Shanmin, Shuai Hui, Liu Qingshan. Phase space reconstruction driven spatio-temporal feature learning for dynamic facial expression recognition[J]. IEEE Transactions on Affective Computing, 2020, 13(3): 1466-1476.
[6] Zhu Yisheng, Shuai Hui, Liu Guangchan, Liu Qingshan. Self-supervised video representation learning using improved instance-wise contrastive learning and deep clustering[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(10): 6741-6752.
[7] Xu Xiang, Kong Lingdong, Shuai Hui, Zhang Wenwei, Pan Liang, Chen Kai, Liu Ziwei, Liu Qingshan. 4d contrastive superflows are dense 3d representation learners[C]//European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024: 58-80.
[8] Xu Xiang, Kong Lingdong, Shuai Hui, Pan Liang, Liu Ziwei, Liu Qingshan. Limoe: Mixture of lidar representation learners from automotive scenes[C]//Proceedings of the Computer Vision and Pattern Recognition Conference. 2025: 27368-27379.
[9] Shuai Hui, Liu Qingshan. Geometry-injected image-based point cloud semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-10.
[10] Wang Shanmin, Shuai Hui, Liu Chengguang, Liu Qingshan. Bias-based soft label learning for facial expression recognition[J]. IEEE Transactions on Affective Computing, 2022, 14(4): 3257-3268.
[11] Zhou Feng, Hang Renlong, Shuai Hui, Liu Qingshan. Hierarchical context network for airborne image segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 1-12.
[12] Ji Fanfan, Shuai Hui, Yuan Xiaotong. A globally convergent approximate Newton method for non-convex sparse learning[J]. Pattern Recognition, 2022, 126: 108560.
[13] Xu Xiang, Kong Lingdong, Shuai Hui, Zhang Wenwei, Pan Liang, Chen Kai, Liu Ziwei, Liu Qingshan. Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2025.3640589