王龑

2019年9月至2023年1月  复旦大学 计算机科学与技术 博士

2022年12月至2025年4月   复旦大学智能机器人研究院         博士后 

2025年4月至今        华东师范大学数据科学与工程学院      青年研究员（紫江青年学者）

王龑，华东师范大学数据科学与工程学院，青年研究员（紫江青年学者）。2023年1月获复旦大学计算机科学与技术专业博士学位，在复旦大学继续从事博士后研究（上海市超级博士后、复旦超级博士后）。研究兴趣包括表情识别和情感计算、具身智能、生成式人工智能、多媒体信息处理、机器视觉和增强。近3年，以第一或通讯作者身份在CVPR、ICCV、ECCV、NeurIPS、AAAI、ACM MM、IJCAI、Information Fusion、IEEE TII等顶级会议和期刊发表论文20+篇，谷歌学术被引2500+，高被引论文3篇。主持国家自然科学基金青年项目、科技部国家重点研发计划子课题、2项博士后科学基金（第73批面上和第5批站前特别资助），参与完成科技创新2030“新一代人工智能”重大项目、国家自然科学基金等多个国家级项目。曾获2024年度Information Fusion最佳综述论文奖（2024年度唯一最佳综述论文奖，唯一第一作者）、2024年度复旦大学“十大科技进展”奖（光华一号人形机器人）、AI黑客松医疗健康赛道亚军、2次国家奖学金、2次上海市优秀毕业生等荣誉。

研究方法和研究成果请查看个人主页：

https://wangyanckxx.github.io/

表情识别与情感计算

智能机器人

AIGC(文生图、文生视频等)

机器视觉与增强

1.国家自然科学青年基金项目：基于视觉语言模型的零样本动态人脸表情识别研究，2025.1-2027.12（主持，在研）

2.科技部重点研发计划子课题项目：基于生物标记和表情识别的孤独症早期智能诊断与评估技术，2023.12-2026.11（主持，在研）

3.国家博后科学基金特别资助：开放场景下的动态人脸表情识别研究2023.1-2025.1（主持，结题）

4.国家博后科学基金面上：面向真实环境的跨场景动态人脸表情识别研究，2023.1-2025.1（主持，结题）

5.复旦大学智能机器人研究院揭榜挂帅项目：人形机器人情感理解与交互，2024.1-2025.4（主持，结题）

6.国家科技部“新一代人工智能”2030重大项目：复杂工况环境下的外观缺陷感知建模与仿生成像，2020.12-2023.11（核心骨干，结题）

7.国家自然科学基金面上项目：动态场景中机器人显著性目标识别与表达技术研究，2021.1-2024.12（主要参与，结题）

Selected Papers: 

(#: Corresponding Author)

1. Yan Wang, Wei Song, Wei Tao, Antonio Liotta, Dawei Yang, Xinlei Li, Shuyong Gao, Yixuan Sun, Weifeng Ge, Wei Zhang, Wenqiang Zhang^#. A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances. Information Fusion 2022, 83-84: 19-52. (SCI一区Top, IF = 14.8) [ESI Highly Cited Paper]

2. Yan Wang, Yixuan Sun, Yiwen Huang, Zhongying Liu, Shuyong Gao, Wei Zhang, Weifeng Ge^#, Wenqiang Zhang^#. FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022, 20922-20931. (CCF A)

3. Yan Wang, Yixuan Sun, Wei Song, Shuyong Gao, Yiwen Huang, Zhaoyu Chen, Weifeng Ge^#, Wenqiang Zhang^#. DPCNet: Dual Path Multi-Excitation Collaborative Network for Facial Expression Representation Learning in Videos. Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022, 3656-3665. (CCF A)

4. Yan Wang, Shaoqi Yan, Wei Song, Antonio Liotta, Jing Liu, Dingkang Yang, Shuyong Gao, Wenqiang Zhang^#. MGR³Net: Multigranularity Region Relation Representation Network for Facial Expression Recognition in Affective Robots. IEEE Transactions on Industrial Informatics, 2024, 20 (5): 7216-7226. (SCI一区TOP, IF=11.7)

5. Haoran Wang, Xinji Mai, Zeng Tao, Xuan Tong, Junxiong Lin, Yan Wang^#, Jiawen Yu, Shaoqi Yan, Ziheng Zhou, Wenqiang Zhang^#. D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition. CVPR, 2025.  (CCF A)

6. Yuxuan Lin, Yang Chang, Xuan Tong, Jiawen Yu, Antonio Liotta, Guofan Huang, Wei Song, Zongze Wu, Yan Wang^#, Wenqiang Zhang^#. A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Anomaly Detection. Information Fusion 2025. (SCI一区Top, IF = 14.8)

7. Xinji Mai, Junxiong Lin, Haoran Wang, Zeng Tao, Yan Wang^#, Shaoqi Yan, Xuan Tong, Jiawen Yu, Boyang Wang, Ziheng Zhou, Qing Zhao, Shuyong Gao Wenqiang Zhang. All rivers run into the sea: Unified Modality Brain-like Emotional Central Mechanism. ACM MM, 2024. (CCF A, Oral, Top 4%)

8. Xinji Mai, Haoran Wang, Zeng Tao, Junxiong Lin, Shaoqi Yan, Yan Wang^#, Jiawen Yu, Xuan Tong, Yating Li, Wenqiang Zhang^#. OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive Problem. AAAI 2025. (CCF A)

9. Zeng Tao, Tong Yang, Junxiong Lin, Xinji Mai, Haoran Wang, Beining Wang, Enyu Zhou, Yan Wang^#, Wenqiang Zhang^#. LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D. NeurIPS, 2024. (CCF A)

10. Zeng Tao, Yan Wang^#, Zhaoyu Chen, Boyang Wang, Shaoqi Yan, Kaixun Jiang, Shuyong Gao, Wenqiang Zhang^#. Freq-HD: an Interpretable Frequency-based High-Dynamics Affective Clip Selection Method for in-the-Wild Facial Expression Recognition in Videos ACM MM 2023. (CCF A, Oral, Top 4%)

11. Kaixun Jiang, Zhaoyu Chen, Tony Huang, Jiafeng Wang, Dingkang Yang, Bo Li, Yan Wang^#, Wenqiang Zhang^#. Efficient Decision-based Black-box Patch Attacks on Video Recognition. ICCV, 2023. (CCF A)

12. Hailei Hei, Qianyu Guo, Zihao Wang, Yan Wang^#, Haofen Wang^#, Wenqiang Zhang^#. A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image. AAAI 2024. (CCF A)

13. Qing Zhao, Yan Wang^#, Boyang Wang, Junxiong Lin, Shaoqi Yan, Wei Song, Antonio Liotta, Jiawen Yu, Shuyong Gao, Wenqiang Zhang^#. MSC-AD: A Multiscene Unsupervised Anomaly Detection Dataset for Small Defect Detection of Casting Surface. IEEE Transactions on Industrial Informatics, 2024: 1-12. (中科院SCI一区Top, IF = 11.7)

14. Shaoqi Yan, Yan Wang^#, Xinji Mai, Zeng Tao, Wei Song , Qing Zhao, Boyang Wang, Haoran Wang, Shuyong Gao, Wenqiang Zhang^#. Observe Finer To Select Better: Learning Key Frame Extraction via Semantic Coherence for Dynamic Facial Expression Recognition in the Wild. Information Sciences. (SCI一区Top, IF=8.1)

15. Boyang Wang, Yan Wang^#, Qing Zhao, Junxiong Lin, Zeng Tao, Pinxue Guo, Zhaoyu Chen, Kaixun Jiang, Shaoqi Yan, Shuyong Gao, Wenqiang Zhang^#. A Capture to Registration Framework for Realistic Image Super-Resolution in the Industry Environment. ACM MM 2023: 7403-7412. (CCF A)

16. Junxiong Lin, Yan Wang^#, Zeng Tao, Boyang Wang, Qing Zhao, Haorang Wang, Xuan Tong, Xinji Mai, Yuxuan Lin, Wei Song, Jiawen Yu, Shaoqi Yan, Wenqiang Zhang. Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution.  ECCV  2024. (CCF B)

17. Junxiong Lin, Zeng Tao, Xuan Tong, Xinji Mai, Haoran Wang, Boyang Wang, Yan Wang^#, Qing Zhao, Jiawen Yu, Yuxuan Lin, Shaoqi Yan, Shuyong Gao, Wenqiang Zhang^#. Suppressing Uncertainties in Degradation Estimation for Blind Super-Resolution ACM MM, 2024. (CCF A)

18. Yang Chang, Yuxuan Lin, Boyang Wang, Qing Zhao, Yan Wang^#, Wenqiang Zhang^#. FD-UAD: Unsupervised Anomaly Detection Platform Based on Defect Autonomous Imaging and Enhancement. IJCAI 2024. (CCF A)

19. Kaixun Jiang, Zhaoyu Chen, Xinyu Zhou, Jingyu Zhang, Lingyi Hong, JiaFeng Wang, Bo Li, Yan Wang^#, Wenqiang Zhang^#. Towards Decision-based Sparse Attacks on Video Recognition ACM MM 2023. (CCF A, Oral, Top 4%)

20. Wei Song, Yan Wang^#, Dongmei Huang^#, Antonio Liotta, Cristian Perra. Enhancement of Underwater Images with Statistical Model of Background Light and Optimization of Transmission Map. IEEE Trans. on Broadcasting, 2020. (SCI一区) [ESI Highly Cited Paper]

2024年，Informaion Fusion 2024最佳综述论文奖

2024年，2024年度复旦大学“十大科技进展”（光华一号”人形机器人）

2023年，上海市超级博士后激励计划、复旦大学超级博士后

2023年，AI黑客松第二名、INSAI23 Best Paper

2022年，博士研究生国家奖学金、上海市优秀毕业生