博士生导师
硕士生导师
学位:博士学位
性别:男
毕业院校:北京邮电大学
学历:研究生毕业
在职信息:在职
所在单位:计算机学院(国家示范性软件学院)
电子邮箱:
获武汉大学计算机学士学位与经济法学士学位;获北京邮电大学硕士和博士学位;曾博士后访问UCLA。现任北京邮电大学教授,主要研究方向:计算美学、计算摄影、具身智能。
个人主页:http://www.vrobotit.cn/~mal
近三年主持国家级项目5项。偏好真实需求牵引的科研,与企业合作“实事求是”,部分与企业联合研发(更多项目见:projects):
1、小米 “计算摄影应用落地” 联合研发组
近三年国际顶会竞赛获奖:
1、CVPR NTIRE 2023 Video Quality Assessment(冠军);
2、CVPR NTIRE 2024 AIGC:图像质量评估赛道(冠军)/ 视频质量评估赛道(第5);
3、CVPR NTIRE 2024 Short-form Video Quality Assessment:第9。
近三年部分代表作(更多论文见:publications):
[1] Limin Liu, Shuai He, Anlong Ming*, Rui Xie, Huadong Ma, ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models, in Proceedings of the 41th international Conference on Machine Learning (ICML), 2024. 注:机器学习领域顶会 (CCF-A)
[2] Haiyang Zhang, Mengchao Wang, Shuai He, Anlong Ming*, AK4Prompts: Aesthetics-driven Automatically Keywords-Ranking for Prompts in Text-To-Image Models, in Proceedings of the 33st International Joint Conference on Artificial Intelligence (IJCAI), 2024. 注:人工智能领域顶会 (CCF-A)
[3] Dongxiang Jiang, Yongchang Zhang, Shuai He, Anlong Ming*, M2Beats: When Motion Meets Beats in Short-form Videos, in Proceedings of the 33st International Joint Conference on Artificial Intelligence (IJCAI), 2024. 注:人工智能领域顶会 (CCF-A)
[4] Shai He, Anlong Ming*, Yaqi Li, Jinyuan Sun, ShunTian Zheng, Huadong Ma, Thinking Image Color Aesthetics Assessment: Models, Datasets and Benchmarks, in Proceedings of International Conference on Computer Vision (ICCV), 2023. 注:计算机视觉领域顶会 (CCF-A)
[5] Wenteng Liang, Feng Xue, Yihao Liu, Guofeng Zhong and Anlong Ming*, Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. 注:计算机视觉领域顶会 (CCF-A)
[6] Chunxiao Li, Xuejing Kang, Zhifeng Zhang, Anlong Ming*, SWBNet: A Stable White Balance Network for sRGB images, in Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023. 注:人工智能领域顶会 (CCF-A)
[7] Shai He, Anlong Ming*, Shuntian Zheng, Haobin Zhong, Huadong Ma, EAT: An Enhancer for Aesthetics-Oriented Transformers, in Proceedings of the 31th ACM International Conference on Multimedia (MM), 2023. 注:多媒体领域顶会 (CCF-A)
[8] Chunxiao Li, Xuejing Kang, Anlong Ming*, WBFlow: Few-shot White Balance for sRGB Images via Reversible Neural Flows, in Proceedings of the 32st International Joint Conference on Artificial Intelligence (IJCAI), 2023. 注:人工智能领域顶会 (CCF-A)
[9] Shuai He, Yongchang Zhang, Dongxiang Jiang, Rui Xie, Anlong Ming*, Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks, in Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), 2022. 注:人工智能领域顶会 (CCF-A)
[10] Yuxiang Tang, Xuejing Kang, Chunxiao Li, Zhaowen Lin, Anlong Ming*, Transfer Learning for Color Constancy via Statistic Perspective, in Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI), 2022. 注:人工智能领域顶会 (CCF-A)
本实验室致力于计算机视觉、机器人与各类智能技术交叉融合,故命名为 “视觉机器人与智能技术”实验室,但 “视觉机器人” 一词暂无严格的学术定义。
实验室提倡开放的与更多企业合作协同创新,以计算美学为核心,深耕图像颜色处理、图像美学评估、图像美学摄制、摄影具身智能等共性技术,深耕面向垂直场景的应用技术。实验室目前有在任教师1人、本科/硕士/博士学生约45人,每年计划招收(含联合培养)硕士研究生约10人、博士研究生1—2人。
欢迎志同道合者加入本实验室,合作深耕上述共性技术或探索令人兴奋的应用!