阚美娜，研究员，博士生导师。研究领域为计算机视觉，尤其具身视觉、迁移学习、人脸识别、图像编辑与生成等问题。相关成果在TPAMI、IJCV、CVPR、ICCV等相关领域主流国际期刊与会议上面发表论文60余篇，谷歌学术引用7000余次。作为负责人承担国家自然科学基金重点项目课题、优青项目、面上项目、青年项目等，并参与多项国家重点研发、基金重点、基金面上及企业合作等课题。此外，获IROS2025 世界模型竞赛冠军、FG 2015 PaSC视频人脸识别竞赛第一名、ICCV 2015社会年龄估计竞赛第二名、CVPR 2017面部关键点定位第二名。获2014年中国计算机学会优秀博士学位论文奖、2014中科院优秀博士学位论文奖、2016年中国计算机学会青年人才发展计划、2018年中国图象图形学学会石青云女科学家奖青年奖、2019年北京市科技新星计划、中科院计算所优秀员工以及卓越之星等。

2023年9月 — 今：中国科学院计算技术研究所，研究员 

2015年9月 — 2023年9月：中国科学院计算技术研究所，副研究员 

2013年9月 — 2015年9月：中国科学院计算技术研究所，助理研究员 

2007年9月 — 2013年7月：中国科学院计算技术研究所，博士 

2011年1月 — 2011年9月：新加坡南洋理工大学，交流生 

2003年7月— 2007年9月：山东大学，计算机学院，学士 

[1] Xiaolong Tang, Meina Kan, Shiguang Shan, Xilin Chen. Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling. International Conference on Learning Representations (ICLR), 2026

[2] Zuyan Zhao, Zhenliang He, Meina Kan, Shiguang Shan, Xilin Chen. UniPercept: A Unified Diffusion Model for Generalizable Visual Perception, IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2026.

[3] Zongyao Xue, Meina Kan, Shiguang Shan, Xilin Chen. Feature Decomposition-Recomposition in Large Vision-Language Model for Few-Shot Class-Incremental Learning. IEEE/CVF International Conference on Computer Vision (ICCV), 2025. 

[4] Xinkuan Qiu, Meina Kan, Yongbin Zhou, Shiguang Shan. Benchmarking Multimodal Large Language Models Against Image Corruptions. IEEE/CVF International Conference on Computer Vision (ICCV), 2025. 

[5] Hao Liang, Meina Kan, Shiguang Shan, Xilin Chen. Task-Oriented Token Pruning for Efficient Object Detection and Segmentation. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025. 

[6] Lixuan Zhang, Meina Kan, Shiguang Shan, Xilin Chen. PreLAR: World Model Pre-training with Learnable Action Representation. European Conference on Computer Vision (ECCV) , 2024.

[7] Xiaolong Tang, Meina Kan, Shiguang Shan, Zhilong Ji, Jinfeng Bai, Xilin Chen. HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[8] Yude Wang, Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen. BLPSeg: Balance the Label Preference in Scribble-Supervised Semantic Segmentation. IEEE Trans. on Image Processing (TIP), pp. 4921 – 4934, 2023. 

[9] Chunrui Han, Shiguang Shan, Meina Kan, Shuzhe Wu, and Xilin Chen, Personalized Convolution for Face Recognition, International Journal of Computer Vision (IJCV), pp. 344–362, 2022. 

[10] Nan Lai, Meina Kan, Chunrui Han, Xingguang Song, Shiguang Shan. Learning to Learn Adaptive Classifier-Predictor for Few Shot Learning. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020. 

[11] Shuzhe Wu, Meina Kan, Shiguang Shan, and Xilin Chen. Hierarchical Attention for Part-Aware Face Detection. International Journal of Computer Vision (IJCV), vo. 127, no. 6-7, pp 560–578, 2019. 

[12] Zhenliang He, Wangmeng Zuo, Meina Kan, Shiguang Shan, Xilin Chen. AttGAN: Facial Attribute Editing by Only Changing What You Want. IEEE Trans. on Image Processing (TIP), vol. 28, no. 11, pp. 5464 – 5478, 2019. 

[13] Meina Kan, Shiguang Shan,Haihong Zhang, Shihong Lao, and Xilin Chen. Multi-view Discriminant Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.  

[14] Lanqing Hu, Meina Kan, Shiguang Shan, Xilin Chen. DandelionNet: Domain Composition with Instance Adaptive Classification for Domain Generalization. IEEE/CVF International Conference on Computer Vision (ICCV), 2023. 

[15] Dongyang Liu, Meina Kan, Shiguang Shan, Xilin Chen. Function-Consistent Feature Distillation. International Conference on Learning Representations (ICLR), 2023. 

[16] Xuyang Guo, Meina Kan, Tianle Chen, Shiguang Shan. GAN with Multivariate Disentangling for Controllable Hair Editing. European Conference on Computer Vision (ECCV), 2022. 

[17] Yuanyuan Xu, Meina Kan, Shiguang Shan, Xilin Chen. Mutual Learning of Joint and Separate Domain Alignments for Multi-Source Domain Adaptation. EEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022. 

[18] Zhenliang He, Meina Kan, Shiguang Shan. EigenGAN: Layer-Wise Eigen-Learning for GANs. International Conference on Computer Vision (ICCV), 2021. 

[19] Lanqing Hu, Meina Kan, Shiguang Shan, Xilin Chen. Unsupervised Domain Adaptation With Hierarchical Gradient Synchronization. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 

[20] Yude Wang, Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen. Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 

[21] Zhenliang He, Meina Kan, Shiguang Shan, Xilin Chen. S^2GAN: Share Aging Factors across Ages and Share Aging Trends among Individuals. IEEE International Conference on Computer Vision (ICCV), 2019. 

[22] Xiaoyan Li, Meina Kan, Shiguang Shan, Xilin Chen. Weakly Supervised Object Detection with Segmentation Collaboration. IEEE International Conference on Computer Vision (ICCV), 2019. 

[23] Xijun Wang, Meina Kan, Shiguang Shan, Xilin Chen. Fully Learnable Group Convolution for Acceleration of Deep Neural Networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. 

[24] Lanqing Hu, Meina Kan, Shiguang Shan, Xilin Chen. Duplex Generative Adversarial Network for Unsupervised Domain Adaptation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. 

[25] Xuepeng Shi, Shiguang Shan, Meina Kan, Shuzhe Wu, Xilin Chen. Real-Time Rotation-Invariant Face Detection With Progressive Calibration Networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. 

[26] Chunrui Han, Shiguang Shan, Meina Kan, Shuzhe Wu, Xilin Chen. Face Recognition with Contrastive Convolution. European Conference on Computer Vision (ECCV), 2018. 

[27] Gang Zhang, Meina Kan, Shiguang Shan, Xilin Chen. Generative Adversarial Network with Spatial Attention for Face Attribute Editing. European Conference on Computer Vision (ECCV), 2018.