计算机视觉、模式识别

欢迎对计算机视觉、模式识别感兴趣的同学报考，同时也希望报考的同学具备较好的数学基础与计算机编程能力。

081104-模式识别与智能系统

计算机视觉
模式识别

2016-10--中国科学院自动化研究所   研究员
2014-02--2015-02   美国加利福尼亚大学洛杉矶分校   访问学者
2011-10--2016-10   中国科学院自动化研究所   副研究员
2008-07--2011-10   中国科学院自动化研究所   助理研究员
2003-09--2008-06   中国科学院自动化研究所   博士
1999-09--2003-06   东北大学   学士

图像处理与计算机视觉
计算机视觉
计算机视觉 II
数值信号处理与分析

已指导学生

陈新泽  硕士研究生  081203-计算机应用技术  

徐梦洋  硕士研究生  085211-计算机技术  

牛李金梁  硕士研究生  081203-计算机应用技术  

陈豹  硕士研究生  081104-模式识别与智能系统  

邓爽  博士研究生  081104-模式识别与智能系统  

王东骥  硕士研究生  085211-计算机技术  

周正铭  硕士研究生  081104-模式识别与智能系统  

孙珈因  博士研究生  081104-模式识别与智能系统  

王芷熙  硕士研究生  085410-人工智能  

现指导学生

高梦宇  博士研究生  081104-模式识别与智能系统  

李嘉楠  博士研究生  081203-计算机应用技术  

刘雨臻  博士研究生  081104-模式识别与智能系统  

谭涛  博士研究生  081203-计算机应用技术  

张家诚  博士研究生  081203-计算机应用技术  

张礼霆  硕士研究生  081104-模式识别与智能系统  

徐时捷  博士研究生  081104-模式识别与智能系统  

王英琦  博士研究生  081104-模式识别与智能系统  

许一航  博士研究生  081203-计算机应用技术  

刘鲁阳  博士研究生  081104-模式识别与智能系统  

薛智文  博士研究生  081104-模式识别与智能系统  

2016 - 至今    中国科学院自动化研究所                  研究员

2011 - 2016    中国科学院自动化研究所                 副研究员

2014 - 2015   美国加利福尼亚大学洛杉矶分校       访问研究

2008 - 2011   中国科学院自动化研究所                  助理研究员 

2016-10~现在, 中国科学院自动化研究所, 研究员
2014-02~2015-02,美国加利福尼亚大学洛杉矶分校, 访问学者
2011-10~2016-10,中国科学院自动化研究所, 副研究员
2008-07~2011-10,中国科学院自动化研究所, 助理研究员

2023-08-30-今,电子与信息学报, 客座编辑
2021-05-25-今,雷达学报, 客座编辑
2018-12-31-今,Journal of Computer Science and Technology, Editorial Board of Young Scientists

   

（1） Causality-guided Prompt Learning for Vision-language Models via Visual Granulation, International Conference on Computer Vision (ICCV), 2025, 第 2 作者  通讯作者
（2） Towards Semi-supervised Dual-modal Semantic Segmentation, IEEE TRANSACTIONS ON MULTIMEDIA, 2025, 第 1 作者  通讯作者
（3） A Survey on Self-supervised Monocular Depth Estimation Based on Deep Neural Networks, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2025, 第 1 作者  通讯作者
（4） Recursive Counterfactual Deconfounding for image recognition, KNOWLEDGE-BASED SYSTEMS, 2025, 第 4 作者  通讯作者
（5） ONDA-Pose: Occlusion-Aware Neural Domain Adaptation for Self-Supervised 6D Object Pose Estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025, 第 2 作者  通讯作者
（6） Self-Assembled Generative Framework for Generalized Zero-Shot Learning, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2025, 第 2 作者  通讯作者
（7） Self-supervised monocular depth learning from unknown cameras: Leveraging the power of raw data, Image and Vision Computing, 2025, 第 6 作者  通讯作者
（8） EquiPose: Exploiting Equivariance for Relative Camera Pose Estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025, 第 2 作者  通讯作者
（9） Multi-Scale Spatio-Temporal Attention Network for Epileptic Seizure Prediction, IEEE Journal of Biomedical and Health Informatics, 2025, 第 1 作者
（10） Rectified self-supervised monocular depth estimation loss for nighttime and dynamic scenes, ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 第 7 作者  通讯作者
（11） Conditional feature generation for transductive open-set recognition via dual-space consistent sampling, PATTERN RECOGNITION, 2024, 第 2 作者  通讯作者
（12） Adaptive Conditional Denoising Diffusion Model with Hybrid Affinity Regularizer for Generalized Zero-shot Learning, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 第 2 作者  通讯作者
（13） Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024, 第 2 作者  通讯作者
（14） LASS3D: Language-Assisted Semi-Supervised 3D Semantic Segmentation with Progressive Unreliable Data Exploitation, European Conference on Computer Vision (ECCV), 2024, 第 2 作者  通讯作者
（15） Cayley Rotation Averaging: Multiple Camera Averaging Under the Cayley Framework, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 第 1 作者  通讯作者
（16） Exploiting SAR visual semantics in TomoSAR for 3D modeling of buildings, NATIONAL SCIENCE OPEN, 2024, 第 4 作者
（17） Efficient Region-Based 3-D Urban Building Reconstruction From TomoSAR Images, IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 第 3 作者  通讯作者
（18） 利用全局仿射模型进行卫星图像快速三维重建, Fast 3D reconstruction of satellite images via the Global Affine Model, 遥感学报, 2024, 第 3 作者
（19） Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local Descriptors, International Journal of Computer Vision, 2024, 第 2 作者  通讯作者
（20） SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 第 2 作者  通讯作者
（21） Distilled Heterogeneous Feature Alignment Network for SAR Image Semantic Segmentation, IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 第 4 作者  通讯作者
（22） Hierarchical Attention Network for Open-Set Fine-Grained Image Recognition, IEEE Transactions on Circuits and Systems for Video Technology, 2023, 第 3 作者  通讯作者
（23） Ship Instance Segmentation Based on Rotated Bounding Boxes for SAR Images, REMOTE SENSING, 2023, 第 3 作者
（24） ASPPR:active single-image piecewise planar 3D reconstruction based on geometric priors, ASPPR: active single-image piecewise planar 3D reconstruction based on geometric priors, SCIENCE CHINA-INFORMATION SCIENCES, 2023, 第 2 作者  通讯作者
（25） Open-set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 第 2 作者  通讯作者
（26） Single-image piecewise planar reconstruction of urban buildings based on geometric priors, ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2023, 第 2 作者  通讯作者
（27） MoEP-AE: Autoencoding Mixtures of Exponential Power Distributions for Open-Set Recognition, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 第 3 作者  通讯作者
（28） Chromosome classification via deep learning and its application to patients with structural abnormalities of chromosomes, MEDICAL ENGINEERING AND PHYSICS, 2023, 第 3 作者
（29） Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth Estimation, IEEE International Conference on Computer Vision (ICCV), 2023, 第 2 作者  通讯作者
（30） SAR-to-Optical Image Translation with Hierarchical Latent Features, IEEE Transactions on Geoscience and Remote Sensing, 2022, 第 4 作者  通讯作者
（31） SCE-Net: Self- and Cross-Enhancement Network for Single-View Height Estimation and Semantic Segmentation, REMOTE SENSING, 2022, 第 2 作者  通讯作者
（32） Learning Occlusion-Aware Coarse-to-Fine Depth Map for Self-supervised Monocular Depth Estimation, ACM International Conference on Multimedia (MM), 2022, 第 2 作者  通讯作者
（33） Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds, IEEE International Conference on Robotics and Automation (ICRA), 2022, 第 2 作者  通讯作者
（34） SG-SRNs: Superpixel-Guided Scene Representation Networks, IEEE SIGNAL PROCESSING LETTERS, 2022, 第 3 作者
（35） Pursuing 3D Scene Structures with Optical Satellite Images from Affine Reconstruction to Euclidean Reconstruction, IEEE Transactions on Geoscience and Remote Sensing, 2022, 第 6 作者  通讯作者
（36） Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation, European Conference on Computer Vision (ECCV), 2022, 第 2 作者  通讯作者
（37） Robust Camera Translation Estimation via Rank Enforcement, IEEE TRANSACTIONS ON CYBERNETICS, 2022, 第 1 作者  通讯作者
（38） Real-Time Localization and Matching of Corneal Reflections for Eye Gaze Estimation via a Lightweight Network, The Ninth International Symposium of Chinese CHI, 2021, 第 2 作者  通讯作者
（39） An Iterative Co-Training Transductive Framework for Zero Shot Learning, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 第 3 作者  通讯作者
（40） Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector, KNOWLEDGE-BASED SYSTEMS, 2021, 第 2 作者  通讯作者
（41） Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation, IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2021, 第 3 作者  通讯作者
（42） Multi-Depth Convolution Network with Shallow-Deep Feature Integration for Semantic Labeling in Remote Sensing Images, IEEE Geoscience and Remote Sensing Letters, 2021, 第 2 作者  通讯作者
（43） SARMV3D-1.0： SAR微波视觉三维成像数据集, SARMV3D-1.0: Synthetic Aperture Radar Microwave Vision 3D Imaging Dataset, 雷达学报, 2021, 第 10 作者
（44） Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021, 第 2 作者  通讯作者
（45） Gated Feature Aggregation for Height Estimation from Single Aerial Images, IEEE Geoscience and Remote Sensing Letters, 2021, 第 2 作者  通讯作者
（46） GA-NET: Global Attention Network for Point Cloud Semantic Segmentation, IEEE SIGNAL PROCESSING LETTERS, 2021, 第 2 作者  通讯作者
（47） SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation, The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, 第 2 作者  通讯作者
（48） Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature, AAAI, 2020, 第 2 作者  通讯作者
（49） 一种基于双目视觉的卫星相对位姿测量方法, A Binocular Method for Measuring Relative Poses of Satellites, 空间控制技术与应用, 2020, 第 3 作者
（50） Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN), FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2020, 第 1 作者
（51） Face-sketch learning with human sketch-drawing order enforcement, Face-sketch learning with human sketch-drawing order enforcement, SCIENCE CHINA-INFORMATION SCIENCES, 2020, 第 7 作者  通讯作者
（52） Latent-Smoothness Nonrigid Structure From Motion by Revisiting Multilinear Factorization, IEEE TRANSACTIONS ON CYBERNETICS, 2019, 第 1 作者  通讯作者
（53） Learning stratified 3D reconstruction, SCIENCE CHINA-INFORMATION SCIENCES, 2018, 第 1 作者
（54） Deep Disentangling Siamese Network for Frontal Face Synthesis Under Neutral Illumination, IEEE SIGNAL PROCESSING LETTERS, 2018, 第 3 作者  通讯作者
（55） Statistics of Visual Responses to Image Object Stimuli from Primate AIT Neurons to DNN Neurons, NEURAL COMPUTATION, 2018, 第 1 作者  通讯作者
（56） Commentary: Using goal-driven deep learning models to understand sensory cortex., FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2018, 第 1 作者
（57） Two-Stream Deep Correlation Network for Frontal Face Recovery, IEEE SIGNAL PROCESSING LETTERS, 2017, 第 2 作者  通讯作者
（58） Comparison of IT Neural Response Statistics with Simulations, FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2017, 第 1 作者
（59） Physiognomy: Personality traits prediction by learning, INTERNATIONAL JOURNAL OF AUTOMATION AND COMPUTING, 2017, 第 3 作者  通讯作者
（60） Fast depth extraction from a single image, INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2016, 第 2 作者  通讯作者
（61） Sequential Factorization for Nonrigid Structure from Motion via LBFGS, PROCEEDINGS OF INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, 2016, 第 1 作者  通讯作者
（62） Pursuing face identity from view-specific representation to view-invariant representation, PROCEEDINGS OF INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2016, 第 2 作者  通讯作者
（63） Sequential Factorization for Nonrigid Structure from Motion via LBFGS, 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, 第 1 作者  通讯作者
（64） 从单幅图像学习场景深度信息固有的歧义性, 中国科学: 信息科学, 2016, 第 2 作者
（65） PURSUING FACE IDENTITY FROM VIEW-SPECIFIC REPRESENTATION TO VIEW-INVARIANT REPRESENTATION, 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, 第 2 作者  通讯作者
（66） BIOLOGICALLY INSPIRED DEEP STEREO MODEL, 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2015, 第 3 作者
（67） 含缺失成分的矩阵的广义低秩逼近及其在图像处理中的应用, Generalized Low-rank Approximations of Matrices with Missing Components and its Applications in Image Processing, 计算机辅助设计与图形学学报, 2015, 第 2 作者  通讯作者
（68） Euclidean upgrading from segment lengths: DLT-like algorithm and its variants, IMAGE AND VISION COMPUTING, 2014, 第 2 作者
（69） Effects of Exogenous Methyl Jasmonate on the Biosynthesis of Shikonin Derivatives in Callus Tissues of Arnebia euchroma, APPLIED BIOCHEMISTRY AND BIOTECHNOLOGY, 2014, 第 3 作者
（70） Suboptimal Solutions to the Algebraic-Error Line Triangulation, JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2014, 第 4 作者
（71） Two-dimensional relaxed representation, NEUROCOMPUTING, 2013, 第 1 作者  通讯作者
（72） Smooth incomplete matrix factorization and its applications in image/video denoising, NEUROCOMPUTING, 2013, 第 1 作者  通讯作者
（73） Automatic real-time SLAM relocalization based on a hierarchical bipartite graph model, SCIENCE CHINA Information Sciences, 2012, 第 1 作者  通讯作者
（74） Weighted Similarity-Invariant Linear Algorithm for Camera Calibration With Rotating 1-D Objects, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2012, 第 2 作者
（75） 基于视频的实时自动人体高度测量, Video-based Real-time Automatic Measurement for the Height of Human Body, 自动化学报, 2009, 第 1 作者
（76） Pointwise Motion Image (PMI): A Novel Motion Representation and Its Applications to Abnormality Detection and Behavior Recognition, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2009, 第 1 作者  通讯作者