基本信息
阚美娜  女  博导  中国科学院计算技术研究所
电子邮件: kanmeina@ict.ac.cn
通信地址: 北京市海淀区科学院南路6号
邮政编码:

研究领域

计算机视觉与具身智能

教育背景

2007-08--2013-07   中国科学院大学   博士
2003-08--2007-07   山东大学   工学学士

工作经历

2023-09~至今,中国科学院计算技术研究所, 研究员

2015-09~2023-08,中国科学院计算技术研究所, 副研究员

2013-09~2015-08,中国科学院计算技术研究所, 助理研究员

2011-01~2011-09, 新加坡南洋理工大学

出版信息

   
发表论文
(1) A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction, International Conference on Learning Representations (ICLR), 2024, 第 2 作者
(2) HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, 第 2 作者
(3) Function-Consistent Feature Distillation, International Conference on Learning Representations (ICLR), 2023, 
(4) GAN with Multivariate Disentangling for Controllable Hair Editing, European Conference on Computer Vision (ECCV), 2022, 
(5) Personalized Convolution for Face Recognition, INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 
(6) EigenGAN: Layer-Wise Eigen-Learning for GANs, 2021, 
(7) Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation, 2020, 
(8) Unsupervised Domain Adaptation with Hierarchical Gradient Synchronization, 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, 
(9) Fully Learnable Group Convolution for Acceleration of Deep Neural Networks, 2019, 
(10) Face Recognition with Contrastive Convolution, COMPUTER VISION - ECCV 2018, PT IX, 2018, 
(11) Generative Adversarial Network with Spatial Attention for Face Attribute Editing, COMPUTER VISION - ECCV 2018, PT VI, 2018, 
(12) Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks, 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, 
(13) Duplex Generative Adversarial Network for Unsupervised Domain Adaptation, 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, 
(14) LDF-Net: Learning a Displacement Field Network for Face Recognition Across Pose, 2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017), 2017, 
(15) A Fully End-to-End Cascaded CNN for Facial Landmark Detection, 2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017), 2017, 
(16) Self-Error-Correcting Convolutional Neural Network for Learning with Noisy Labels, 2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017), 2017, 
(17) Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition, 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, 
(18) Noisy Face Image Sets Refining Collaborated with Discriminant Feature Space Learning, 2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017), 2017, 
(19) Occlusion-free Face Alignment: Deep Regression Networks Coupled with De-corrupt AutoEncoders, 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, 
(20) Multi-view Deep Network for Cross-view Classification, 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, 
(21) Multi-View Discriminant Analysis, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 
(22) AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation, 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW), 2015, 
(23) Topic-Aware Deep Auto-Encoders (TDA) for Face Alignment, COMPUTER VISION - ACCV 2014, PT III, 2015, 
(24) Leveraging Datasets with Varying Annotations for Face Alignment via Deep Regression Network, 2015IEEEINTERNATIONALCONFERENCEONCOMPUTERVISIONICCV, 2015, 
(25) Bi-shifting Auto-Encoder for Unsupervised Domain Adaptation, 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, 
(26) Stacked Progressive Auto-Encoders (SPAE) for Face Recognition Across Poses, 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, 
(27) Domain Adaptation for Face Recognition: Targetize Source Domain Bridged by Common Subspace, INTERNATIONAL JOURNAL OF COMPUTER VISION, 2014, 
(28) Semisupervised Hashing via Kernel Hyperplane Learning for Scalable Image Search, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2014, 
(29) Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment, COMPUTER VISION - ECCV 2014, PT II, 2014, 
(30) Adaptive discriminant learning for face recognition, PATTERN RECOGNITION, 2013, 
(31) Learning Prototype Hyperplanes for Face Verification in the Wild, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 
(32) Funnel-Structured Cascade for Multi-View Face Detection with Alignment-Awareness, 

科研活动

   
科研项目
( 1 ) 面向物体识别的迁移学习理论与方法研究, 负责人, 其他任务, 2014-01--2017-12
( 2 ) 人脸识别技术研究, 参与, 企业委托, 2016-05--2017-03
( 3 ) 深度学习技术研究, 参与, 企业委托, 2016-03--2017-03
( 4 ) 图像视频的群体数据协同结构化处理与表达, 参与, 其他任务, 2014-01--2018-12
( 5 ) 面向非完备标注场景的迁移学习研究, 负责人, 其他任务, 2018-01--2021-12
( 6 ) 多模态自适应选择的高鲁棒协同感知所内子课题, 负责人, 国家任务, 2018-05--2022-12
( 7 ) 基于动力学理论研究易推广的深度学习模型, 负责人, 国家任务, 2018-05--2022-04
( 8 ) 异质视觉模式表示与分类, 负责人, 国家任务, 2022-01--2024-12
( 9 ) 开放环境的可扩展感知与理解, 负责人, 研究所自选, 2022-07--2024-06

招生信息

计算机应用技术