一、个人简介
胡川飞，男，汉族，1992.11出生，讲师
归属学科专业：电气工程
学部任职：无
二、主要学习与工作经历
2025.12---至今 上海应用技术大学，智能技术学部，讲师
2021.9---2025.12 东南大学，电子信息（控制工程），博士
2018.9---2021.6 上海理工大学，控制工程，硕士
2011.9---2015.6 江苏科技大学，电气工程及其自动化，本科
三、主要科研工作与成绩
3.1 科研项目
参与国家自然科学基金重点、联合基金（重点）、JKW重大专项、重点研发计划等横向、纵向项目十余项。
3.2 科研成果
围绕机器智能感知、情感理解开展了系列研究，相关成果在IEEE汇刊（TIE、TCSVT、TITS、TIM、TASE、TII）、Pattern Recognition、ICCV、CVPR等国际知名学术期刊、会议发表论文40余篇，ESI热点论文1篇、高被引论文4篇，累计谷歌学术被引1400余次（https://scholar.google.com/citations?user=pw0K5BAAAAAJ）；授权中国发明专利3件、美国发明专利1件；获2025年吴文俊人工智能科学技术科技进步二等奖（7/12）。
部分学术论文：
[1] Chuanfei Hu, Xinde Li, Jianxin Pang. Trustworthy driver state perception via contextual interaction-driven evidential vision-language fusion in vehicular cyber-physical systems[J]. IEEE Transactions on Intelligent Transportation Systems, 2026, 27(2): 2716-2728.
[2] Chuanfei Hu, Xinde Li. Human-centric context and self-uncertainty-driven multi-modal large language model for training-free vision-based driver state recognition[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, Early Access.
[3] Chuanfei Hu, Chenyang Zhao, Hang Shao, et al. TMFF: Trustworthy multi-focus fusion framework for multi-label sewer defect classification in sewer inspection videos[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(12): 12274-12287.
[4] Chuanfei Hu, Tianyi Xia, et al. Trustworthy multi-phase liver tumor segmentation via evidence-based uncertainty[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108289.
[5] Chuanfei Hu, Bo Dong, Hang Shao, et al. Toward purifying defect feature for multilabel sewer defect classification[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-11.
[6] Chuanfei Hu, Yongxiong Wang. An efficient convolutional neural network model based on object-level attention mechanism for casting defect detection on radiography images[J]. IEEE Transactions on Industrial Electronics, 2020, 67(12): 10922-10930.
[7] Siyuan Li, Xinde Li*, Chuanfei Hu*. Towards revealing trustworthy emotion states via human-object interaction-aware emotion recognition with vision-language model [J]. Pattern Recognition, 2026, Available online.
[8] Chenyang Zhao#, Chuanfei Hu#, et al. PipeCLIP: Defect-conditioned and Cross-focus-driven Vision-language model for video-based sewer defect inspection[J]. IEEE Transactions on Automation Science and Engineering, 2026, Early Access.
[9] Chenyang Zhao#, Chuanfei Hu#, et al. PipeMamba: State space model for efficient Video-based sewer defect classification. IEEE Transactions on Artificial Intelligence, 2026, 7(3): 1390-1403.
[10] Kaixuan Wu, Xinde Li, Xinling Li, Chuanfei Hu, et al. AVQACL: A novel benchmark for audio-visual question answering continual learning[C]//In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, 3252-3261.
部知识产权：
[1] Xinde Li, Chuanfei Hu. Method for emotion recognition based on human-object time-space interaction behavior: U.S. Patent 12,541,999[P]. 2026-2-3.
[2] 李新德,胡川飞.一种基于人-物时空交互行为的情感识别方法:2022105 83163.1[P].2023-08-04.
[3] 王永雄,胡川飞.基于注意力机制的弱监督铸件缺陷识别方法:201910815305.0[P].2023-08-04.
[4] 王永雄,胡川飞,汤振辉,魏国亮,缪银龙. 一种基于灰度显著性的复杂铸件缺陷识别方法:201910071676.2[P].2022-08-12.
四、主要社会学术团体兼职
[1] 中国航空学会信息融合分会人机共融专业委员会委员
[2] 第十八届中国智能机器人大会组织委员会委员
五、主要研究方向
情感理解、智能感知、计算机视觉、医学图像分析。
六、联系方式
办公室：第一学科楼A417
Email地址：cfhu@sit.edu.cn；chuanfei_hu@ieee.org；w64228013@126.com。
