基本信息
汤晓鸥  男  博导  中国科学院深圳先进技术研究院
email: xo.tang@siat.ac.cn
address: 深圳市南山区学苑大道1068号
postalCode:

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

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

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
( 1 ) Method and device for image processing, electronic device, and storage medium, 2021, 第 4 作者, 专利号: US17086713

( 2 ) Time domain action detecting methods and system, electronic devices, and computer storage medium, 2021, 第 1 作者, 专利号: US10915741

出版信息

   
发表论文
(1) Interfacegan: Interpreting the disentangled face representation learned by gans, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 第 3 作者
(2) Interpreting the latent space of gans for semantic face editing, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, 第 3 作者
(3) emporal Action Detection with Structured Segment Networks, International Journal of Computer Vision, 2020, 第 5 作者
(4) Temporal Segment Networks for Action Recognition in Videos, IEEE Trans. Pattern Anal. Mach. Intell, 2019, 第 6 作者
(5) Deep Network Interpolation for Continuous Imagery Effect Transition, CVPR 2019, 2019, 第 4 作者
(6) DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images, CVPR 2019, 2019, 第 4 作者
(7) Switchable Whitening for Deep Representation Learning, ICCV 2019, 2019, 第 4 作者
(8) From Facial Expression Recognition to Interpersonal Relation Prediction, International Journal of Computer Vision, 2018, 第 4 作者
(9) Deep Learning Markov Random Field for Semantic Segmentation, IEEE Trans. Pattern Anal. Mach. Intell, 2018, 第 5 作者
(10) Faceness-Net: Face Detection through Deep Facial Part Responses, IEEE Trans. Pattern Anal. Mach. Intell, 2018, 第 4 作者
(11) Discriminative Sparse Neighbor Approximation for Imbalanced Learning, IEEE Trans. Neural Netw. Learning Syst, 2018, 第 3 作者
(12) Spatial as Deep: Spatial CNN for Traffic Scene Understanding, AAAI 2018, 2018, 第 5 作者
(13) Mix-and-Match Tuning for Self-Supervised Semantic Segmentation, AAAI 2018, 2018, 第 4 作者
(14) FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis, CVPR 2018, 2018, 第 5 作者
(15) Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net, ECCV 2018, 2018, 第 4 作者
(16) 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
(17) Pose-Robust Face Recognition via Deep Residual Equivariant Mapping, Computer Vision and Pattern Recognition 2018, 2018, 第 4 作者
(18) DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks, IEEE Trans. Pattern Anal. Mach. Intell, 2017, 其他(合作组作者)
(19) Image Aesthetic Assessment: An experimental survey, IEEE Signal Process. Mag, 2017, 第 3 作者
(20) Not All Pixels Are Equal:Difficulty-Aware Semantic Segmentation via Deep Layer Cascade, CVPR 2017, 2017, 第 5 作者
(21) ViP-CNN: Visual Phrase Guided Convolutional Neural Network, CVPR 2017, 2017, 第 4 作者
(22) Learning to Disambiguate by Asking Discriminative Questions, ICCV 2017, 2017, 第 3 作者
(23) Video Frame Synthesis Using Deep Voxel Flow, ICCV 2017, 2017, 第 3 作者
(24) Temporal Action Detection with Structured Segment Networks, ICCV 2017, 2017, 第 5 作者
(25) Bridging Music and Image via Cross-Modal Ranking Analysis, IEEE Trans. Multimedia, 2016, 第 4 作者
(26) MoFAP: A Multi-level Representation for Action Recognition, International Journal of Computer Vision, 2016, 第 3 作者
(27) Actionness Estimation Using Hybrid Fully Convolutional Networks, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2016, 第 3 作者
(28) WIDER FACE: A Face Detection Benchmark, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2016, 第 4 作者
(29) Unconstrained Face Alignment via Cascaded Compositional Learning, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2016, 第 4 作者
(30) Unsupervised Learning of Discriminative Attributes and Visual Representations, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2016, 第 3 作者
(31) Fashion Landmark Detection in the Wild, The 14th European Conference on Computer Vision(ECCV2016), 2016, 第 5 作者
(32) "Joint Face Representation Adaptation and Clustering in Videos", The 14th European Conference on Computer Vision, 2016, 第 4 作者
(33) Depth Map Super-Resolution by Deep Multi-Scale Guidance, The 14th European Conference on Computer Vision, 2016, 第 3 作者
(34) Deep Cascaded Bi-Network for Face Hallucination, The 14th European Conference on Computer Vision, 2016, 第 4 作者
(35) Deep Specialized Network for Illuminant Estimation, The 14th European Conference on Computer Vision, 2016, 第 3 作者
(36) Depth From Water Reflection, IEEE Transactions on Image Processing, 2015, 第 3 作者
(37) Recognize Complex Events From Static Images by Fusing Deep Channels, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2015, 第 4 作者
(38) Deeply Learned Face Representations Are Sparse, Selective, and Robust, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2015, 第 3 作者
(39) 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
(40) Face Alignment by Coarse-to-Fine Shape Searching, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2015, 第 4 作者
(41) Pedestrian Detection Aided by Deep Learning Semantic Tasks, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2015, 第 4 作者
(42) Pedestrian Detection Aided by Deep Learning Semantic Tasks, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2015, 第 4 作者
(43) Deep Learning Strong Parts for Pedestrian Detection, IEEE International Conference on Computer Vision (ICCV), 2015, 第 4 作者
(44) From Facial Parts Responses to Face Detection: A Deep Learning Approach, IEEE International Conference on Computer Vision (ICCV), 2015, 第 4 作者
(45) Hierarchical facial landmark localization via cascaded random binary patterns, Pattern Recognition, 2015, 第 5 作者
(46) 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
(47) Web Image Re-ranking Using Query-Specific Semantic Signatures, IEEE Trans on Pattern Analysis and Machine(PAMI), 2014, 第 4 作者
(48) Video Action Detection with Relational Dynamic-Poselets, Proc. European Conference Computer Vision ( ECCV), 2014, 2014, 第 3 作者
(49) Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees, Proc. European Conference Computer Vision ( ECCV), 2014, 2014, 第 3 作者
(50) Switchable Deep Network for Pedestrian Detection, IEEE Conference on Computer Vision and Pattern Recognition, 2014, 第 4 作者
(51) Deep Learning Face Representation from Predicting 10,000 Classes, IEEE Conference on Computer Vision and Pattern Recognition, 2014, 第 3 作者
(52) 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
(53) Deep Learning Face Representation by Joint Identification-Verification, The 28 Annual Conference on Neural Information Processing Systems (NIPS), 2014, 第 3 作者

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, 负责人, 地方任务, 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), 负责人, 地方任务, 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, 负责人, 国家任务, 2015-01--2018-12
( 4 ) 深圳市机器视觉与模式识别重点实验室, 负责人, 地方任务, 2012-07--2014-07
( 5 ) 基20150084非结构场景下机器人视觉感知关键技术的研究, 负责人, 地方任务, 2016-01--2018-12
( 6 ) SIAT-CHUK多媒体技术联合实验室, 参与, 中国科学院计划, 2019-01--2023-12
( 7 ) 视频监控和人脸识别技术研究, 参与, 企业委托, 2014-12--2019-12