基本信息
汤晓鸥男博导中国科学院深圳先进技术研究院
电子邮件： xo.tang@siat.ac.cn
通信地址： 深圳市南山区学苑大道1068号
邮政编码：
部门/实验室：数字所
研究领域

招生信息
招生专业081203-计算机应用技术
081203-计算机应用技术

招生方向多媒体、计算机视觉、模式识别及视频处理
多媒体、计算机视觉、模式识别及视频处理


教育背景1991-09--1996-09美国麻省理工学院博士
1990-09--1991-08美国罗彻斯特大学硕士
1986-09--1990-07中国科学技术大学学士

学历
学位

工作经历
工作简历2009-01~现在,中国科学院深圳先进技术研究院,研究员
2005-03~现在,香港中文大学,教授
2005-03~2008-01,微软亚洲研究院,视觉计算组主任
2003-01~2005-01,香港中文大学,副教授
1998-01~2003-01,香港中文大学,助理教授
1991-09~1996-09,美国麻省理工学院,博士
1990-09~1991-08,美国罗彻斯特大学,硕士
1986-09~1990-07,中国科学技术大学,学士

社会兼职

教授课程

专利与奖励
奖励信息（1） 论文Single image haze removal using darkchannel prior获世界计算机视觉三大顶级会议之一的CVPR 2009最佳论文奖(为亚洲论文首次获奖), 一等奖, 其他, 2009

专利成果

出版信息
发表论文（1）From Facial Expression Recognition to Interpersonal Relation Prediction,International Journal of Computer Vision,2018,第4作者
（2）Deep Learning Markov Random Field for Semantic Segmentation,IEEE Trans. Pattern Anal. Mach. Intell,2018,第5作者
（3）Faceness-Net: Face Detection through Deep Facial Part Responses,IEEE Trans. Pattern Anal. Mach. Intell,2018,第4作者
（4）Discriminative Sparse Neighbor Approximation for Imbalanced Learning,IEEE Trans. Neural Netw. Learning Syst,2018,第3作者
（5）Spatial as Deep: Spatial CNN for Traffic Scene Understanding,AAAI 2018,2018,第5作者
（6）Mix-and-Match Tuning for Self-Supervised Semantic Segmentation,AAAI 2018,2018,第4作者
（7）FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis,CVPR 2018,2018,第5作者
（8）Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net,ECCV 2018,2018,第4作者
（9）FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis,The IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2018,第5作者
（10）Pose-Robust Face Recognition via Deep Residual Equivariant Mapping,Computer Vision and Pattern Recognition 2018,2018,第4作者
（11）DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks,IEEE Trans. Pattern Anal. Mach. Intell,2017,第12作者
（12）Image Aesthetic Assessment: An experimental survey,IEEE Signal Process. Mag,2017,第3作者
（13）Not All Pixels Are Equal：Difficulty-Aware Semantic Segmentation via Deep Layer Cascade,CVPR 2017,2017,第5作者
（14）ViP-CNN: Visual Phrase Guided Convolutional Neural Network,CVPR 2017,2017,第4作者
（15）Learning to Disambiguate by Asking Discriminative Questions,ICCV 2017,2017,第3作者
（16）Video Frame Synthesis Using Deep Voxel Flow,ICCV 2017,2017,第3作者
（17）Temporal Action Detection with Structured Segment Networks,ICCV 2017,2017,第5作者
（18）Bridging Music and Image via Cross-Modal Ranking Analysis,IEEE Trans. Multimedia,2016,第4作者
（19）MoFAP: A Multi-level Representation for Action Recognition,International Journal of Computer Vision,2016,第3作者
（20）Actionness Estimation Using Hybrid Fully Convolutional Networks,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2016,第3作者
（21）WIDER FACE: A Face Detection Benchmark,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2016,第4作者
（22）Unconstrained Face Alignment via Cascaded Compositional Learning,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2016,第4作者
（23）Unsupervised Learning of Discriminative Attributes and Visual Representations,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2016,第3作者
（24）Fashion Landmark Detection in the Wild,The 14th European Conference on Computer Vision（ECCV2016）,2016,第5作者
（25）"Joint Face Representation Adaptation and Clustering in Videos",The 14th European Conference on Computer Vision,2016,第4作者
（26）Depth Map Super-Resolution by Deep Multi-Scale Guidance,The 14th European Conference on Computer Vision,2016,第3作者
（27）Deep Cascaded Bi-Network for Face Hallucination,The 14th European Conference on Computer Vision,2016,第4作者
（28）Deep Specialized Network for Illuminant Estimation,The 14th European Conference on Computer Vision,2016,第3作者
（29）Depth From Water Reflection,IEEE Transactions on Image Processing,2015,第3作者
（30）Recognize Complex Events From Static Images by Fusing Deep Channels,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（31）Deeply Learned Face Representations Are Sparse, Selective, and Robust,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2015,第3作者
（32）A Large-Scale Car Dataset for Fine-Grained Categorization and Verification,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（33）Face Alignment by Coarse-to-Fine Shape Searching,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（34）Pedestrian Detection Aided by Deep Learning Semantic Tasks,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（35）Pedestrian Detection Aided by Deep Learning Semantic Tasks,Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR),2015,第4作者
（36）Deep Learning Strong Parts for Pedestrian Detection,IEEE International Conference on Computer Vision (ICCV),2015,第4作者
（37）From Facial Parts Responses to Face Detection: A Deep Learning Approach,IEEE International Conference on Computer Vision (ICCV),2015,第4作者
（38）Hierarchical facial landmark localization via cascaded random binary patterns,Pattern Recognition,2015,第5作者
（39）Multi-view Facial Landmark Localization in RGB-D Images via Hierarchical Regression with Binary Patterns,IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2014,第4作者
（40）Web Image Re-ranking Using Query-Specific Semantic Signatures,IEEE Trans on Pattern Analysis and Machine(PAMI),2014,第4作者
（41）Video Action Detection with Relational Dynamic-Poselets,Proc. European Conference Computer Vision ( ECCV), 2014,2014,第3作者
（42）Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees,Proc. European Conference Computer Vision ( ECCV), 2014,2014,第3作者
（43）Switchable Deep Network for Pedestrian Detection,IEEE Conference on Computer Vision and Pattern Recognition,2014,第4作者
（44）Deep Learning Face Representation from Predicting 10,000 Classes,IEEE Conference on Computer Vision and Pattern Recognition,2014,第3作者
（45）Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations,The 28 Annual Conference on Neural Information Processing Systems (NIPS),2014,第4作者
（46）Deep Learning Face Representation by Joint Identification-Verification,The 28 Annual Conference on Neural Information Processing Systems (NIPS),2014,第3作者

发表著作

科研活动
科研项目（ 1 ） 广东省引进创新科研团队-机器人与智能信息技术创新科研团队, 主持,省级,2011-01--2015-12
（ 2 ） 机器人与智能信息技术创新科研团队（深圳市配套）, 主持,省级,2011-01--2015-12
（ 3 ） 面向互联网图像视频的鲁棒人脸分析与识别技术研究, 主持,国家级,2015-01--2018-12
（ 4 ） 深圳市机器视觉与模式识别重点实验室, 主持,省级,2012-07--2014-07
（ 5 ） 基**非结构场景下机器人视觉感知关键技术的研究, 主持,省级,2016-01--2018-12
（ 6 ） SIAT-CHUK多媒体技术联合实验室, 参与,部委级,2019-01--2023-12
（ 7 ） 视频监控和人脸识别技术研究, 参与,院级,2014-12--2019-12

参与会议

合作情况
项目协作单位

指导学生