基本信息
张燕明 中国科学院自动化研究所
电子邮件: ymzhang@nlpr.ia.ac.cn
通信地址: 中关村东路95号智能化大厦
邮政编码: 100090
电子邮件: ymzhang@nlpr.ia.ac.cn
通信地址: 中关村东路95号智能化大厦
邮政编码: 100090
研究领域
机器学习、人工智能方法及其在文档分析与识别、计算机视觉等领域中的应用。主要研究内容包括:结构预测方法,图神经网络,概率图模型及其在文档版面分析、工程图纸分析、草图分析、数学公式/流程图/表格识别、文字生成等问题中的应用。相关研究成果发表在CVPR, ICLR, NeurIPS, TPAMI, TNNLS, TMM等重要学术刊物上,其中包括ICDAR2025 best paper, ACPR2021 best student paper。
招生信息
欢迎热爱科研,具有扎实数理和编程基础的同学联系我。
招生专业
081104-模式识别与智能系统
招生方向
结构预测、关系推理及其在文档分析中的应用机器学习与模式识别
教育背景和工作经历
2017-11--中国科学院自动化研究所 副研究员2016-04--2017-05 Georgia Institute of Technology, USA 国家公派访问学者 (with Prof. Le Song)2011-09--2017-10 中国科学院自动化研究所 助理研究员2009-09--2010-01 香港科技大学 访问学生 (with Prof. Dit-Yan Yeung)2005-09--2011-06 中国科学院自动化研究所 博士 (模式识别与智能系统,导师:刘成林)2000-09--2004-06 北京邮电大学 学士(计算机科学与技术)
教学情况
2023秋季,研究生课程,《模式识别》,中国科学院大学(雁栖湖)
2024秋季,研究生课程,《模式识别》,中国科学院大学(雁栖湖)
2025秋季,研究生课程,《模式识别》,中国科学院大学(雁栖湖)
出版信息
代表性论文
(1) Learning to Generate Stylized Handwritten Text via a Unified Representation of Style, Content, and Noise, International Conference on Learning Representations, 2026, 第 2 作者(2) End-to-End Hyper-Relational Information Extraction for Engineering Diagrams via Dynamically Tokenized Relation Transformer, IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026, 第 2 作者(3) 基于视觉的人体动作质量评价研究综述, 自动化学报, 2025, 第 2 作者(4) Template-Guided Cascaded Diffusion for Stylized Handwritten Chinese Text-Line Generation, International Conference on Document Analysis and Recognition, 2025, 第 3 作者 通讯作者(5) Air Quality Prediction with A Meteorology-Guided Modality-Decoupled Spatio-Temporal Network, IEEE Transactions on Artificial Intelligence, 2025, 第 2 作者(6) Decoupling Layout from Glyph in Online Chinese Handwriting Generations, International Conference on Learning Representations, 2025, 第 2 作者(7) STAFNet: Spatiotemporal-Aware Fusion Network for Air Quality Prediction, International Conference on Pattern Recognition, 2024, 第 2 作者(8) Transformer-Based Stroke Relation Encoding for Online Handwriting and Sketches, Pattern Recognition, 2024, 第 2 作者 通讯作者(9) Streaming Stroke Classification of Online Handwriting, IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023, 第 2 作者(10) DyGAT: Dynamic stroke classification of online handwritten documents and sketches, Pattern Recognition, 2023, 第 2 作者 通讯作者(11) Diff-Writer: A Diffusion Model-Based Stylized Online Handwritten Chinese Character Generator, International Conference on Neural Information Processing, 2023, 第 2 作者(12) Instance GNN: A Learning Framework for Joint Symbol Segmentation and Recognition in Online Handwritten Diagrams, IEEE Transactions on Multimedia, 2022, 第 2 作者(13) Region ensemble network for MCI conversion prediction with a relation regularized loss, International Conference on Medical Image Computing and Computer-Assisted Intervention, 2021, 第 2 作者(14) Graph-to-graph: Towards accurate and interpretable online handwritten mathematical expression recognition, AAAI Conference on Artificial Intelligence, 2021, 第 3 作者(15) Joint stroke classification and text line grouping in online handwritten documents with edge pooling attention networks, Pattern Recognition, 2021, 第 2 作者(16) Online Semi-Supervised Learning with Learning Vector Quantization, Neurocomputing, 2020, 第 2 作者(17) Handwritten Mathematical Expression Recognition via Paired Adversarial Learning, International Journal of Computer Vision, 2020, 第 3 作者(18) Multi-view Semi-supervised 3D Whole Brain Segmentation with a Self-ensemble Network, International Conference on Medical Image Computing and Computer-Assisted Intervention, 2019, 第 2 作者(19) Drawing and Recognizing Chinese Characters with Recurrent Neural Network., IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 第 3 作者(20) Recurrent Hidden Semi-Markov Model, International Conference on Learning Representations, 2017, 第 3 作者(21) Deep Hyperspherical Learning, Advances in Neural Information Processing Systems, 2017, 第 2 作者(22) Adaptive spatial pooling for image classification, Pattern Recognition, 2016, 第 2 作者(23) Large-scale graph-based semi-supervised learning via tree Laplacian solver, AAAI Conference on Artificial Intelligence, 2016, 第 1 作者(24) MTC: A Fast and Robust Graph-Based Transductive Learning Method., IEEE Transactions on Neural Networks and Learning Systems, 2015, 第 1 作者(25) Learning locality preserving graph from data., IEEE Transactions on Cybernetics, 2014, 第 1 作者(26) Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition, Pattern Recognition, 2014, 第 2 作者(27) Approximate kNN graph construction with locality sensitive hashing, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2013, 第 1 作者(28) Fast and robust graph-based transductive learning via minimum tree cut, IEEE International Conference on Data Mining, 2011, 第 1 作者(29) Subspace Regularization: A New Semi-supervised Learning Method, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2009, 第 1 作者
指导学生
已指导学生
杨宇婷 硕士研究生 081203-计算机应用技术
刘靖宇 硕士研究生 085400-电子信息
任敏思 硕士研究生 081104-模式识别与智能系统
杨鑫 硕士研究生 085404-计算机技术
现指导学生
王鸿烈 硕士研究生 081104-模式识别与智能系统
高铭辰 硕士研究生 085410-人工智能