闫寒,东华大学信息科学与技术学院讲师。2024年5月博士毕业于哈尔滨工业大学计算机科学与技术学院,主要研究方向为计算机视觉,包括扩散模型(Diffusion)、生成对抗网络(GAN)以及高动态范围成像(HDR)等。在这些领域内,近年来发表了20余篇国内外学术论文,其中作为第一作者或通讯作者发表了10余篇。同时,申请了三项发明专利。对计算机视觉和生成式AI感兴趣的同学,欢迎联系我探讨研究。
研究方向:
计算机视觉、生成式AI(Diffusion、GAN、LLM)、HDR、运筹优化
科研项目(参与):
(1)中国国家自然科学基金,哈尔滨工业大学(深圳),内容感知的视链学习及优化关键技术研究,61972112,2020年1月 - 2023年12月,参与
(2)中国国家自然科学基金,哈尔滨工业大学(深圳),大数据环境下的大服务理论与方法研究,61832004,2019年1月 - 2023年12月,参与
(3)北京百分点信息科技有限公司,哈尔滨工业大学(深圳),面向智能服装制造的系统化方法,2019年10月 - 2020年4月,项目主要参与人
代表性科研成果(部分):
[1] Han Yan, Haijun Zhang*, Linlin Liu, Dongliang Zhou, Xiaofei Xu, Zhao Zhang, Shuicheng Yan, “Toward intelligent design: An ai-based fashion designer using generative adversarial networks aided by sketch and rendering generators”, IEEE Transactions on Multimedia (TMM), 2022. (中科院一区,Top 期刊, JCR 1 区,IF: 7.3,谷歌学术引用49次,one of Top 50 popular papers in TMM,ESI highly cited paper)
[2] Han Yan, Haijun Zhang*, Jianyang Shi, Jianghong Ma, “Texture Brush for Fashion Inspiration Transfer: A Generative Adversarial Network with Heatmap-guided Semantic Disentanglement”, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022.(中科院一区, Top 期刊, JCR 1 区, IF: 8.4)
[3] Han Yan, Haijun Zhang*, et al., “Learning to Disentangle the Colors, Textures, and Shapes of Fashion Items: A Unified Framework”. IEEE Transactions on Multimedia (TMM), 2023. (中科院一区, Top 期刊, JCR 1 区, IF: 7.3)
[4] Han Yan, Haijun Zhang*, Xiangyu Mu, Jicong Fan, Zhao Zhang, “FashionDiff: A Controllable Diffusion Model Using Pairwise Fashion Elements for Intelligent Design”, ACM International Conference on Multimedia (ACM MM), 2023. (CCF-A会议论文)
[5] Han Yan, Haijun Zhang*, Jie Hou, Jicong Fan, Zhao Zhang, “InspirNET: An Unsupervised Generative Adversarial Network with Controllable Fine-grained Texture Disentanglement for Fashion Generation”, ACM International Conference on Multimedia (ACM MM), 2023. (CCF-A会议论文)
[6] Han Yan, Haijun Zhang*, Jianyang Shi, Jianghong Ma, “Toward intelligent fashion design: A texture and shape disentangled generative adversarial network”, ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2023.( JCR 1 区,CCF-B, IF: 5.1)
[7] Han Yan, Haijun Zhang*, Jianyang Shi, Jianghong Ma, “Inspiration Transfer for Intelligent Design: A Generative Adversarial Network with Fashion Attributes Disentanglement”, IEEE Transactions on Consumer Electronics (TCE), 2023.( 中科院二区,IF: 4.3)
[8] Han Yan, Haijun Zhang*, et al., “Mixing and Matching Elements for Intelligent Fashion Design: A Generative Adversarial Network with Structure and Texture Disentanglement”. IEEE Transactions on Consumer Electronics (TCE), 2023.( 中科院二区,IF: 4.3)
[9] Han Yan, Xiaomeng Du*, Lu Xu, Shichao Xu, Yanfeng Zhang, Peng Gong, “Toward intelligent clothes manufacturing: a systematic method for static and dynamic task allocation by genetic optimization”, Neural Computing and Applications (NCAA), 2022.( JCR 1 区,IF: 6.0)
[10] Ming Zhao, Han Yan*,Gaofeng Cao, Xihong Liu, “Robust recommendation algorithm based on core user extraction with user trust and similarity”, Journal of Electronics & Information Technology.(CCF T2, 北大核心期刊)
[11] Gaofeng Cao, Fei Zhou, Han Yan, et al. KPN-MFI: A Kernel Prediction Network with Multi-frame Interaction for Video Inverse Tone Mapping, IJCAI. 2022: 806-812. (CCF-A会议论文)
教学情况:
本科生课程《数学建模》等。
联系方式:
邮箱:yanhan@dhu.edu.cn