柯逍，男，福建福州人，博士，教授，旗山学者，博士生导师，闽江科学传播学者，福建省高层次人才，福州大学电子信息专业博士学位点负责人。现任福建省新媒体行业技术开发基地副主任、大数据智能教育部工程研究中心、福建省网络计算与智能信息处理重点实验室、数字福建大数据基础技术研究院与福建省大数据分析与处理工程研究中心科研骨干。福建省计算机学会理事、福建省人工智能学会理事、中国计算机学会高级会员、中国通信学会高级会员。科技部、教育部、中国科协、国家自然科学基金委、北京市科学技术委员会、上海市科学技术委员会、福建省科技厅、福建省工业和信息化厅、福建省公安厅、福建省生态环境厅、福建省自然资源厅、福建省科协、福州市科技局、工信局与卫健委等专家库成员与评审专家。福建省高级人民法院知识产权技术调查官、福州市中级人民法院知识产权智库专家、福州国际医疗综合实验区专家顾问、国家863软件专业孵化器（福州）基地双创导师。主要从事计算机视觉、人工智能、视频图像分析、机器学习、模式识别以及多媒体数据挖掘等方面的理论研究与应用。近年来，主持包括国家自然科学基金面上项目1项，国家自然科学基金青年项目1项，福建省科技重大专项课题1项，福建省科技引导性项目1项，福建省自然科学基金项目3项等在内的7项国家与省部级课题，以主要成员参与包括1项国家自然科学基金联合基金重点项目、1项国家重点研发计划、5项国家自然科学基金面上与青年项目、2项福建省科技重大专项、5项福建省科技厅重点项目、3项福建省工信厅重点项目等20多项纵向课题以及多项横向课题。在CVPR、NeurIPS、ECCV、AAAI、IJCAI、MM、《IEEE Transactions on Image Processing》、《IEEE Transactions on Multimedia》、《IEEE Transactions on Intelligent Transportation Systems》、《IEEE Transactions on Circuits and Systems for Video Technology》、《软件学报》、《计算机研究与发展》、《电子学报》等国内外权威刊物和国际会议上共计发表了120多篇论文，其中被SCI/EI收录90多篇。同时担任CVPR、NeurIPS、ICML、ECCV、ACL、AAAI、MM、《IEEE Transactions on Pattern Analysis and Machine Intelligence》、《IEEE Transactions on Image Processing》、《IEEE Transactions on Multimedia》、《IEEE Transactions on Neural Networks and Learning Systems》、《计算机学报》、《光学学报》等30多个国际/国内权威期刊与顶级会议的评审专家。申请国家发明专利200余项，授权发明专利140多项，拥有软件著作权50多项。近年来，获得福建省科技进步三等奖、福建省通信学会科学技术一等奖与二等奖、福州大学教学成果二等奖。4次指导研究生获得福建省研究生优秀学位论文，多次指导研究生获得国家奖学金。指导本科生多次主持国家级与省级大学生创新创业计划项目（1项为国家级重点支持领域项目）。积极指导研究生与本科生参与各类竞赛，共获得国家级一等奖2项、二等奖5项、三等奖5项；省级一等奖8项、二等奖10项、三等奖8项。
主要科研项目：
(1) 国家自然科学基金面上项目，基于强化学习与迁移学习的端到端多标签图像自动标注方法研究 (61972097)，2020.01 – 2023.12. （主持）
(2) 国家自然科学基金青年项目，噪声环境下基于深度学习的图像自动标注方法研究 (61502105)，2016.01 – 2018.12. （主持）
(3) 福建省科技重大专项课题，公共安全大数据及人工智能关键技术研究及示范应用 （2025YZ040003），2025.10 – 2028.10. （主持）
(4) 福建省科技引导性项目，基于内容的图像与视频安全过滤关键技术研究及应用 (2017H0015)，2017.04 – 2020.03. （主持）
(5) 福建省自然科学基金面上项目，低数据场景下基于小样本学习的轻量化多模态检索方法研究 （2025J01536），2025.09 – 2028.08. （主持）
(6) 福建省自然科学基金面上项目，基于可迁移深度强化学习的多标签图像自动标注方法研究 (2021J01612)，2021.11 – 2024.11. （主持）
(7) 国家自然科学联合基金项目，跨网络跨媒体两岸热点事件的智能挖掘与推送 (U21A20472)，2022.01 – 2025.12. （主要成员）
(8) 国家重点研发计划，符合三维视觉特性的光场显示评价机制 (2021YFB3600503)，2022.01 – 2025.12. （主要成员）
(9) 国家自然科学基金面上项目，与主观感知一致的立体图像和视频视觉质量客观评价与增强研究 (61672158)，2017.01 – 2020.12. （主要成员）
(10) 福建省科技重大专项，公共安全视频图像安全智能融合关键技术研究和示范应用（2024YZ040001），2024.07 – 2027.07. （主要成员）。
(11) 福建省科技重大专项，智能化视频图像分析关键技术研发及示范应用 (2021HZ022007)，2021.10 – 2024.10. （主要成员）
(12) 福建省技术创新重点攻关及产业化项目，自主可控的高效AI移动终端研发及产业化（2024XQ002），2024.07 – 2025.07. （主要成员）
近年主要研究论文：
1. Huangbiao Xu, HuanqiWu, Xiao Ke*, Junyi Wu, Rui Xu, Jinglin Xu. MCMoE: Completing Missing Modalities with Mixture of Experts for Incomplete Multimodal Action Quality Assessment [C]. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2026. (CCF A)
2. Xiao Ke, Wenyao Chen. SFCE-Det: Sub-feature Fusion and Cross-layer Perceptual Enhancement Detector [J]. IEEE Transactions on Circuits and Systems for Video Technology, 36(1), 2026: 119 - 132. (中科院一区，Top期刊)
3. Xiao Ke, Jingyi Fang, Chaoying Chen, Huanqi Wu. MDANet: A Lightweight Multi-Task Dynamic Adaptive Network for Real-Time Visual Perception in Autonomous Driving [J]. IEEE Transactions on Intelligent Transportation Systems, 2026. (中科院一区，Top期刊)
4. Xiao Ke, Yang Chen, Wenzhong Guo. CoRe: An End-to-End Collaborative Refinement Network for Medical Image Segmentation [J]. IEEE Journal of Biomedical and Health Informatics, 30(2), 2026: 1339 - 1352. (中科院一区，Top期刊)
5. Jianping Li, Qifan Tan, Songchao Tan, Xiao Ke, Zhiwei Li, Tianyu Shen, Guozhen Tan. UniPerception: Towards Unification of Perception using Multi-stage Training pipeline in Adverse Weather Conditions [J]. IEEE Transactions on Intelligent Vehicles, 2026. (中科院一区，Top期刊)
6. Kairui Zhang, Xiao Ke*, Xin Chen. Dual-stage attention based symmetric framework for stereo video quality assessment [J]. Displays, 91, 2026: 103232. (中科院二区)
7. Xinyi Lai, Xiao Ke*, Huangbiao Xu, Shanghui Wu, Wenzhong Guo. MSP: Multimodal Self-Attention Prompt Learning [J]. IEEE Transactions on Image Processing, 34, 2025: 5978 - 5988. (CCF A)
8. Huangbiao Xu, Xiao Ke*, Huanqi Wu, Rui Xu, Yuezhou Li, Wenzhong Guo. Language-Guided Audio-Visual Learning for Long-Term Sports Assessment [C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025: 23967-23977. (CCF A)
9. Huangbiao Xu, Xiao Ke*, HuanqiWu, et al. DanceFix: An Exploration in Group Dance Neatness Assessment Through Fixing Abnormal Challenges of Human Pose [C]. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF A)
10. Huanqi Wu, Huangbiao Xu, Xiao Ke*. The Devil in the Stego Image: Far from Being Usable in Real-World Scenarios [C]. Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM), 2025. (CCF A)
11. Xiao Ke, Weijie Zhou, Yuzhen Niu. Projection, Interaction and Fusion: A Progressive Difference Fusion Network for Salient Object Detection [C]. Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 2025. (CCF A)
12. Chaowei Huang, Yaru Su, Huangbiao Xu, Xiao Ke*. Progressive Modality-Adaptive Interactive Network for Multi-Modality Image Fusion [C]. Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 2025. (CCF A)
13. Xiao Ke, Yuhang Cai, Baitao Chen, et al. Multi-granularity interaction and feature recombination network for fine-grained visual classification [J]. Pattern Recognition, 166, 2025: 111632. (中科院一区，Top期刊)
14. Huangbiao Xu, Huanqi Wu, Xiao Ke*, et al. Quality-Guided Vision-Language Learning for Long-Term Action Quality Assessment [J]. IEEE Transactions on Multimedia, 27, 2025: 7326 - 7339. (中科院一区，Top期刊)
15. Xiao Ke, Peirong Xu, Wenzhong Guo. Language–Image Consistency Augmentation and Distillation Network for Visual Grounding [J]. Pattern Recognition, 166, 2025: 111663. (中科院一区，Top期刊)
16. Xiao Ke, Baitao Chen, Yuhang Cai, Hao Liu, Wenzhong Guo∗, Weibin Chen. Modality-specific adaptive scaling and attention network for cross-modal retrieval [J]. Neurocomputing, 612, 2025: 128664. (中科院二区)
17. Xiao Ke, Baitao Chen, Xiong Yang, et al. Cross-modal independent matching network for image-text retrieval [J]. Pattern Recognition, 159, 2025: 111096. (中科院一区，Top期刊)
18. Xiao Ke, Guanhong Chen, Hao Liu, Wenzhong Guo∗. MEFA-Net: A mask enhanced feature aggregation network for polyp segmentation [J]. Computers in Biology and Medicine, 186, 2025: 109601. (中科院二区)
19. Wukun Zheng, Xiao Ke*, Wenzhong Guo. Zero-shot 3D anomaly detection via online voter mechanism [J]. Neural Networks, 187, 2025: 107398. (中科院一区，Top期刊)
20. 牛玉贞，张凌昕，兰杰，许瑞，柯逍*. 基于分频式生成对抗网络的非成对水下图像增强[J]. 电子学报, 53(2), 2025: 527-544. (CCF A类中文期刊)
21. Puwei Lian, Xiao Ke, Zhou Tan et al. Achieving Zero-Glance Unlearning with Data-Free Inversion and Selective Parameters Suppression [C]. 2025 IEEE International Conference on Multimedia and Expo (ICME), 2025. (CCF B)
22. Xiao Ke, Xin Miao, Wenzhong Guo. U-Transformer-based multi-levels refinement for weakly supervised action segmentation [J]. Pattern Recognition, 149, 2024: 110199. (中科院一区，Top期刊)
23. Xinping Chen, Xiao Ke*, Wenzhong Guo. IF-Font: Ideographic Description Sequence-Following Font Generation [C]. The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024. (CCF A)
24. Xiao Ke, HuanqiWu, Wenzhong Guo. StegFormer: Rebuilding the Glory of Autoencoder- Based Steganography [C]. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Canada, 38(3), 2024: 2723-2731. (CCF A)
25. Huangbiao Xu, Xiao Ke*, Yuezhou Li, et al. Vision-Language Action Knowledge Learning for Semantic-Aware Action Quality Assessment [C]. 18th European Conference on Computer Vision (ECCV), Milan, Italy, 2024. (CCF B)
26. Xiao Ke, Hao Liu, Peirong Xu, et al. Text-based person search via cross-modal alignment learning [J]. Pattern Recognition, 152, 2024: 110481. (中科院一区，Top期刊)
27. Xiao Ke, Qiuqin Chen, Hao Liu, Wenzhong Guo. GFENet: Generalization Feature Extraction Network for Few-Shot Object Detection [J]. IEEE Transactions on Circuits and Systems for Video Technology, 34(12), 2024: 12741-12755. (中科院一区，Top期刊)
28. Xiao Ke, Huangbiao Xu, Xiaofeng Lin, Wenzhong Guo. Two-path target-aware contrastive regression for action quality assessment [J]. Information Sciences, 664, 2024: 120347. (中科院一区)
29. Wenzhong Guo, Kairui Zhang, Xiao Ke*. Integrates Spatiotemporal Visual Stimuli for Video Quality Assessment [J]. IEEE Transactions on Broadcasting, 70(1), 2024: 223 - 237. (中科院一区)
30. Hanling Wang, Xiao Ke*, Wenzhong Guo, Wukun Zheng. No-reference stereoscopic image quality assessment based on binocular collaboration [J]. Neural Networks, 180, 2024: 106752. (中科院一区，Top期刊)
31. Wenzhong Guo, Hanling Wang, Xiao Ke*. Splitting the backbone: A novel hierarchical method for assessing light field image quality [J]. Optics and Lasers in Engineering, 178, 2024:108177. (中科院二区)
32. 柯逍, 缪欣，郭文忠. 基于时空交叉感知的实时动作检测方法[J]. 电子学报, 54(2), 2024: 574-588. (CCF A类中文期刊)
33. 王汉灵，柯逍*，江澳鑫，郭文忠. 基于对比性视觉-文本模型的光场图像质量评估[J]. 电子学报, 52(10), 2024: 3562-3577. (CCF A类中文期刊)
34. Jianping Li, Xiao Ke, Zhihao Wang, et al. CUTRANSNET: Transformers to Make Strong Encoders for Multi-task Vision Perception of Autonomous Driving [C]. 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024. (CCF B)
35. Xiao Ke, Yuhang Cai, Baitao Chen, et al. Granularity-aware distillation and structure modeling region proposal network for fine-grained image classification [J]. Pattern Recognition, 137, 2023:109305. (中科院一区，Top期刊)
36. Xiao Ke, Ganxiong Zeng, Wenzhong Guo. An Ultra-Fast Automatic License Plate Recognition Approach for Unconstrained Scenarios [J]. IEEE Transactions on Intelligent Transportation Systems, 24(5), 2023: 5172- 5185. (中科院一区，Top期刊)
37. Xiao Ke, Hao Liu, Wenzhong Guo, et al. Joint Sample Enhancement and Instance-Sensitive Feature Learning for Efficient Person Search [J]. IEEE Transactions on Circuits and Systems for Video Technology, 32(11), 2022: 7924-7937. (中科院一区，Top期刊)
38. Xiao Ke, Yuezhou Li, Wenzhong Guo, Yanyan Huang. Learning deep convolutional descriptor aggregation for efficient visual tracking [J]. Neural Computing and Applications, 34, 2022: 3745-3765. (中科院二区)
39. Xiao Ke, Yanyan Huang, Wenzhong Guo. Weakly supervised fine-grained image classification via two-level attention activation model [J]. Computer Vision and Image Understanding, 218, 2022: 103408. (CCF B)
40. Xiao Ke, BingHui Lin, WenZhong Guo. LocalFace: Learning significant local features for deep face recognition [J]. Image and Vision Computing, 123, 2022: 104484. (中科院二区)
