基本信息



刘静 研究员中科院自动化研究所
国家优秀青年科学基金获得者


电子邮件： jliu@nlpr.ia.ac.cn
通信地址： 北京海淀中关村东路95号智能化大厦1302
邮政编码： 100190



部门/实验室：模式识别国家重点实验室
研究领域
图像分析、理解与检索；移动媒体计算与应用；深度学习算法


招生信息
招生专业081104-模式识别与智能系统
081203-计算机应用技术

招生方向
网络图像分析、理解与检索
基于深度学习的目标分类、检测与分割
图像文本描述与视觉问答

招生要求专业背景不限，但需对科研怀有强烈的兴趣，具有良好的数学基础、编程能力以及自主学习能力。
由于招生数量有限，希望提前与我联系。
另招收少量实习生，要求计算机相关专业的在读本科或研究生，具有较强的编程能力，实习期半年以上者优先。

教育背景 2004-09--2008-01 中国科学院自动化研究所 博士
2001-09--2004-06 山东大学 硕士
1997-09--2001-06 山东大学 本科


工作经历2015-11--至今 中国科学院自动化研究所 模式识别国家重点实验室研究员
2010-11--2015-10 中国科学院自动化研究所 模式识别国家重点实验室副研究员
2008-01--2010-10 中国科学院自动化研究所 模式识别国家重点实验室 助理研究员



论文发表
发表论文（1）Improving visual question answering using dropout and enhanced question encoder,Pattern Recognition,2019,通讯作者
（2）BTDP: Toward Sparse Fusion with Block Term Decomposition Pooling for Visual Question Answering,ACM Transactions on Multimedia Computing, Communications and Applications,2019,通讯作者
（3）Dual Attention Network for Scene Segmentation,CVPR,2019,通讯作者
（4）Multi-StyleGAN: Multi-Style Image Captioning from Non-Parallel Data using GANs and Back-Translation,CVPR,2019,通讯作者
（5）Densely Connected Attention Flow for Visual Question Answering,IJCAI,2019,通讯作者
（6）Enhancing Visual Question Answering Using Dropout,ACM Multimedia,2018,第2作者
（7）Answer Distillation for Visual Question Answering,Asian Conference on Computer Vision,2018,第2作者
（8）Collaborative Deconvolutional Neural Networks for Joint Depth Estimation and Semantic Segmentation,IEEE transactions on neural networks and learning systems,2018,第1作者
（9）Hierarchically Supervised Deconvolutional Network for Semantic Video Segmentation,Pattern Recognition,2017,通讯作者
（10）Sketch-based Image Retrieval using Generative Adversarial Networks,ACM Multimedia,2017,第2作者
（11）Densely connected deconvolutional network for semantic segmentation,ICIP,2017,第2作者
（12）Objectness-aware Semantic Segmentation,ACM Multimedia,2016,第2作者
（13）Object-aware Deep Network for Commodity Image Retrieval,International Conference on Multimedia Retrieval,2016,第2作者
（14）Multimedia News Summarization in Search,ACM TIST,2016,通讯作者
（15）Chat with illustration,Multimedia System,2016,通讯作者
（16）Fine-grained image classification via low-rank sparse coding with general and class-specific codebooks,IEEE transactions on neural networks and learning systems,2016,第3作者
（17）Domain-Sensitive Recommendation with User-Item Subgroup Analysis,IEEE Transactions on Knowledge Data Engineering,2016,第1作者
（18）Object co-segmentation via salient and common regions discovery,Neurocomputing,2016,通讯作者
（19）Partially Shared Latent Factor Learning with Multi-View Data,IEEE Transactions on Neural Networks and Learning Systems,2015,第1作者
（20）Detection guided deconvolutional network for hierarchical feature learning,Pattern Recognition,2015,第1作者
（21）Weakly Supervised RBM for Semantic Segmentation,International Joint Conference on Artificial Intelligence,2015,第2作者
（22）Color Names Learning Using Convolutional Neural Networks,International Conference on Image Processing,2015,第2作者
（23）Weakly-Supervised Image Semantic Segmentation via Joint Dual Clustering and Dictionary Learning,International Conference on Image Processing,2015,第2作者
（24）Exclusive Constrained Discriminative Learning for Weakly-Supervised Semantic Segmentation,ACM Multimedia,2015,第2作者
（25）Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural Networks,ACM Multimedia,2015,第2作者
（26）Robust Structured Subspace Learning for Data Representation,IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,通讯作者
（27）Learning Representative and Discriminative Image Representation by Deep Appearance and Spatial Coding,Computer Vision and Image Understanding,2015,通讯作者
（28）Object Co-segmentation via Salient and Common Regions Discovery,Neurocomputing,2015,通讯作者
（29）Boosted MIML method for weakly-supervised image semantic segmentation,Multimedia Tools Application,2015,通讯作者
（30）Personalized Geo-Specific Tag Recommendation for Photos on Social Websites,IEEE Transactions on Multimedia,2014,第1作者
（31）Learning a Representative and Discriminative Part Model with Deep Convolutional Features for Scene Recognition,ACCV,2014,第2作者
（32）Image Representation Learning by Deep Appearance and Spatial Coding,ACCV,2014,第2作者
（33）Learning Low-Rank Representations with Classwise Block-Diagonal Structure for Robust Face Recognition,AAAI,2014,第2作者
（34）Labeling Complicated Objects: Multi-View Multi-Instance Multi-Label Learning,AAAI,2014,第3作者
（35）Sparse semantic metric learning for image retrieval,Multimedia System,2014,第1作者
（36）Semi-supervised Unified Latent Factor learning with multi-view data,Machine Vision Application,2014,通讯作者
（37）Learning Robust Face Representation With Classwise Block-Diagonal Structure,IEEE Transactions on Information Forensics and Security,2014,通讯作者
（38）Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection,IEEE Transactions on Knowledge Data Engineering,2014,通讯作者
（39）Adaptive spatial partition learning for image classification,Neurocomputing,2014,通讯作者
（40）Projective Matrix Factorization with unified embedding for social image tagging,Computer Vision and Image Understanding,2014,通讯作者
（41）Image classification by non-negative sparse coding, correlation constrained low-rank and sparse decomposition,Computer Vision and Image Understanding,2014,通讯作者
（42）Key observation selection-based effective video synopsis for camera network,Machine Vision Application,2014,通讯作者
（43）Sparse representation for robust abnormality detection in crowded scenes,Pattern Recognition,2014,通讯作者
（44）Object Co-segmentation via Discriminative Low rank Matrix Recovery,ACM Multimedia,2013,第2作者
（45）Weakly-Supervised Dual Clustering for Image Semantic Segmentation,IEEE Computer Vision and Pattern Recognition,2013,第2作者
（46）Correlation Consistency Constrained Probabilistic Matrix Factorization for Social Tag Refinement,Neurocomputing,2012,第1作者
（47）User-aware Image Tag Refinement via Ternary Semantic Analysis,IEEE Transactions on Multimedia,2012,通讯作者
（48）Boosting Sparsity Constrained Bi-Linear Model for Object Recognition,IEEE Multimedia,2012,通讯作者
（49）Noisy Tag Alignment with Image Regions ,IEEE International Conference on Multimedia and Expo.,2012,第2作者
（50）Unsupervised Feature Selection Using Nonnegative Spectral Analysis ,Association for the Advancement of Artificial Intelligence,2012,第2作者
（51）Correlation Mining for News Retrieval,Chapter 33 for the book titled as Social Networks: Computational Aspects and Mining,2012,第1作者
（52）Nonlinear Matrix Factorization with Unified Embedding for Social Tag Relevance Learning ,Neurocomputing ,2012,通讯作者
（53）One Step Beyond Bags of Features: Visual Categorization Using Components,IEEE International Conference on Image Processing ,2011,第1作者
（54）Boosted Exemplar Learning for Action Recognition and Annotation,IEEE Transactions on Circuits and Systems for Video Technology,2011,通讯作者
（55）Image Classification by Non-Negative Sparse Coding, Low-Rank and Sparse Decomposition,IEEE Computer Vision and Pattern Recognition,2011,第2作者
（56）User-aware Image Tag Refinement via Ternary Analysis,ACM Multimedia Conference,2011,第2作者
（57）Descriptive Local Feature Groups for Image Classification,IEEE International Conference on Image Processing,2011,第2作者
（58）Cross-media retrieval: state-of-the-art and open issues,International Journal of Multimedia Intelligence and Security,2010,第1作者
（59）Image Annotation Using Multi-Correlation Probabilistic Matrix Factorization,ACM Multimedia Conference,2010,第2作者
（60）Multi-Modal Multi-Correlation Person-Centric News Retrieval,ACM Conference on Information and Knowledge Management,2010,第2作者
（61）Image Classification Using Spatial Pyramid Coding and Visual Word Reweighting,Asian Conference on Computer Vision,2010,第2作者
（62）A Graph-Based Image Annotation Framework,Pattern Recognition Letters,2009,第1作者
（63）Image Annotation via Multi-Graph Learning,Pattern Recognition,2009,第1作者
（64）Web Image Retrieval via Learning Semantics of Query Image,IEEE International Conference on Multimedia and Expo.,2009,第2作者
（65）Category sensitive codebook construction for object category recognition,IEEE International Conference on Image Processing ,2009,第2作者
（66）基于图学习的自动图像标注,计算机学报,2008,通讯作者


更多详细内容请参见所在研究团队介绍、个人主页与谷歌学术主页。