冯松鹤

基本信息

个人简介

       北京交通大学计算机与信息技术学院教授，博士生导师，入选首批北京交通大学青年英才培育计划，担任北京市信息服务工程市重点实验室学术委员会委员。主要研究领域为弱监督机器学习算法及其在图像语义理解中的应用。累计主持国家自然科学基金面上及青年项目3项，北京市自然科学基金面上项目2项，教育部博士点基金1项，中国博士后科学基金特别资助项目及面上项目各1项。在包括 IEEE Trans. on Pattern Analysis and Machine Intelligence, IEEE Trans. on Image Processing, IEEE Trans. on Knowledge and Data Engineering,  ACM Trans. on Knowledge Discovery from Data, IEEE Trans. on Multimedia, IEEE Trans. on Cybernetics, ACM Trans. on Intelligent Systems and Technology 等知名学术期刊以及 ACM SIGKDD, AAAI, IJCAI, ACM Multimedia, ICCV, ECCV, ECML-PKDD 等知名国际会议上累计发表各类研究论文近百篇。受国家留学基金委资助，分别于2014年及2017年在美国密歇根州立大学和德国德累斯顿工业大学任国家公派访问学者。

教育背景

• 2003.09 - 2009.01  北京交通大学，计算机应用技术，直博，博士 (导师：须 德 教授)；
  
• 1999.09 - 2003.07  北京交通大学，计算机科学与技术，学士；

工作经历

• 2017.12 - 至今          北京交通大学，计算机与信息技术学院，教授；
• 2017.09 - 2017.12   德累斯顿工业大学(德国)，访问学者；
• 2013.10 - 2014.10   密歇根州立大学(美国)，访问学者 (合作导师：Rong Jin)；
  
• 2012.12 - 2017.11  北京交通大学，计算机与信息技术学院，副教授；
• 2011.01 - 2012.11  北京交通大学，计算机与信息技术学院，讲师； 
• 2009.04 - 2010.12  北京交通大学，计算机与信息技术学院，师资博士后；

科研项目

       主持多项  国家自然科学基金项目 / 北京市自然科学基金项目 / 教育部博士点基金项目 / 博士后科学基金特别资助项目 / 基本科研业务费重点项目。 部分代表性主持科研项目列表如下：

• 基本科研业务费重点资助项目：面向图像语义理解的多视图学习算法关键技术研究，2022-2025，主持（在研）
• 国家自然科学基金面上项目：弱监督学习框架下大规模图像语义理解关键技术研究，2019-2022, 主持（已结题）
• 北京自然科学基金面上项目：弱监督多标记学习算法研究及应用，2020-2022, 主持（已结题）
• 基本科研业务费自由申报项目：2019-2021, 主持（已结题）
• 国家自然科学基金面上项目：2015-2018, 主持（已结题）
• 北京自然科学基金面上项目：2016-2018, 主持（已结题）
• 基本科研业务费自由申报项目：2014-2015, 主持（已结题）
• 基本科研业务费自由申报项目：2012-2013, 主持（已结题）
• 国家自然科学基金青年项目：2012-2014, 主持（已结题）
• 教育部博士点基金新教师类项目：2012-2014, 主持（已结题）
• 基本科研业务费自由申报项目：2010-2011, 主持（已结题）
• 中国博士后科学基金特别资助项目：2010-2011, 主持（已结题）
• 中国博士后科学基金面上资助项目：2009-2010, 主持（已结题）
• 国家自然科学基金面上项目：2010-2012, 合作单位主持（已结题）

研究生培养

近五年来，指导研究生累计获得 校级优秀博士论文 1人/次，校级优秀硕士论文 3人/次，院级优秀硕士论文 4人/次；

(A) 本人常年招收博士研究生(直博/硕博连读：每年1名；申请考核：每年1名)！欢迎数学 / 信息与计算科学 / 计算机科学与技术等专业同学邮件咨询！  

欢迎詹天佑学院的同学们联系！

(B) 本人常年招收硕士研究生(学术型：每年3-4名；专业型：每年1-2名)！欢迎 数学 / 信息与计算科学 / 计算机科学与技术相关专业的同学报考！      

2023级推免生已经结束，欢迎参加2023年研究生统考的同学们联系（2-3个名额）！

要求：1. 热爱科研，善于沟通与团队合作；

          2. 较为扎实的数学基础，英文读写能力，以及良好的编程能力；

          3. 有读博意愿的同学尽量选择报考学术型硕士研究生；

研究方向

• 理论层面：聚焦于弱监督机器学习算法研究，包括多标记学习(Multi-Label Learning)、偏标记学习(Partial-Label Learning)、多视图聚类(Multi-View Clustering)、多视图多标记分类(Multi-View Multi-Label Learning)等；
• 应用层面：聚焦于深度学习框架下的图像语义理解算法研究，包括但不限于：弱监督多标记图像分类(Multi-Label Image Classification)、小样本/零样本学习(Few-Shot/Zero-Shot Learning)等；

招生专业

• 计算机科学与技术硕士
• 计算机技术硕士
• 软件工程硕士
• 人工智能硕士
• 网络与信息安全硕士
• 大数据技术与工程硕士
• 计算机科学与技术博士
• 计算机技术博士
• 人工智能博士

在读研究生

博士研究生:  

• 吴亚楠 (2019-，申请考核, IJCAI*1, AAAI*1)       

• 谷志斌 (2020-，申请考核, ACM TKDD*2, APIN*1) 

• 王   靖 (2022-，申请考核)

• 张   阳 (2023-，硕博连读)

硕士研究生:    

• 邓响 (国家奖学金，2020-, IEEE TMM*1 )  刘威 (国家奖学金，2020-, APIN*1)   胡睿婷 (2020-) 
• 王佳艺 (2021-)  孙伟华 (2021-)  张展 (2021-)  翁昊晚 (2021-)  郭彤 (2021-)  
• 季津天(2022-)  吴婷婷(2022-)   梁婧(2022-)  杨洪涛(2022-)  张仕瞳(2022-)

毕业研究生

博士：

• 2022：吕庚育 (校级优秀博士论文 | 知行奖学金, IEEE TKDE*1, IEEE TCYB*2, ACM TIST*3, AAAI*1, IJCAI*1, KDD*1) - 北京工业大学，副教授
• 2021：孙利娟 (IEEE TMM*1, AAAI*1, KAIS*1, APIN*1, NEUCOM*1, PAKDD*1) - 北京邮电大学 

硕士：

• 2022:   陆迅 (校级优秀硕士论文, ACM TKDD*2)；刘馨媛 (院级优秀硕士论文 | 国家奖学金)；王绍凯 (院级优秀硕士论文)；周彤；赵建国；任博伟
• 2021：李子薇 (院级优秀硕士论文 | 国家奖学金, IJCAI*1)； 孙悦 (国家奖学金, ECML-PKDD*1)
• 2020：李振东 (校级优秀硕士论文)；叶苹；刘燕；季玲玲；李艳青
• 2019：权洪林 (院级优秀硕士论文)；黄文英；黄维雪
• 2018：王晓莹 (校级优秀硕士论文)
• 2017：李敬伟；孙健                           
• 2016：罗骁原；邢妍妍；翟昱昊           
• 2014：谢延涛

论文/期刊

(^  和  #  分别表示作者均为本人指导的研究生和本科生， + 表示共同第一作者， *表示本人为通讯作者) 

News： 

• Bing Li, Haina Qin, Weihua Xiong, Yangxi Li, Songhe Feng, Weiming Hu, Steven Maybank. Ranking-based Color Constancy with Limited Training Samples. IEEE Trans. on Pattern Analysis and Machine Intelligence. (Minor Revision) 
• Yanan Wu^, Songhe Feng*. Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition. IEEE Trans. on Circuits and Systems for Video Technology. (Major Revision) 
• Yanan Wu^, Songhe Feng*. Transformer Driven Matching Selection Mechanism for Multi-Label Image Classification.  IEEE Trans. on Circuits and Systems for Video Technology. (Major Revision) 
• Zhibin Gu^, Songhe Feng*. Twin Tensor Learning for Consistency and Inconsistency: A Unified Affinity Learning Framework for Multi-View Clustering. (Submitted)
• Jintian Ji^, Songhe Feng*. Partition-Level Fusion Induced Multi-View Subspace Clustering with Tensorized $Gamma$-Rank Norm Minimization. (Submitted)  
• Gengyu Lyu^, Xiang Deng^, Songhe Feng*. L-VSM: Label Driven View-Specific Fusion for Multi-View Multi-Label Learning. 2022. (Submitted)  
• Xiang Deng^, Songhe Feng*. Addressing Multi-Label Learning with Missing Labels: from Sample Selection to Label Selection. 2022. (Submitted) 
• Jintian Ji^, Songhe Feng*. Multi-View Clustering based on Bipartite Graph Consistency Fusion. 2022. (Submitted)
• Zhibin Gu^, Songhe Feng*. ONESELF: One-Step Graph-based Multi-View Clustering via Early Fusion. 2022. (Submitted)
• Zihao Zhou#, Shaoqi Zhang#, Songhe Feng*. One-Step Graph-based Incomplete Multi-View Clustering. 2022. (Submitted)  

2023:

• Yanan Wu^, Tengfei Liang+, Songhe Feng*. MetaZSCIL: A Meta-Learning Approach for Generalized Zero-Shot Class Incremental Learning. AAAI, 2023. (CCF A类)
• Gengyu Lyu^, Songhe Feng*. Redundant Label Learning via Subspace Representation and Global Disambiguation. ACM Trans. on Intelligent Systems and Technology, 14(1), pp. 1-19, 2023.

2022:

• Gengyu Lyu^, Yanan Wu^, Songhe Feng*. Deep Graph Matching for Partial Label Learning. IJCAI, pp. 3306-3312, 2022. (CCF A类)
• Gengyu Lyu^, Xiang Deng^, Yanan Wu^, Songhe Feng*. Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning. AAAI, pp. 7647-7654, 2022. (CCF A类)
• Gengyu Lyu^, Songhe Feng*. Prior Knowledge Constrained Adaptive Graph Framework for Partial Label Learning. ACM Trans. on Intelligent Systems and Technology, 2022. (Early Access)
• Zhibin Gu^, Songhe Feng*. ONION: Joint Unsupervised Feature Selection and Robust Subspace Extraction for Graph-based Multi-View Clustering. ACM Trans. on Knowledge Discovery from Data, 2022. (CCF B类，Early Access)   
• Xun Lu^, Songhe Feng*. Distance-Preserving Embedding Bipartite Graph Multi-View Learning with Application to Multi-Label Classification. ACM Trans. on Knowledge Discovery from Data. 2022. (CCF B类, Early Access)  
• Xun Lu^, Songhe Feng*.  Structure Diversity-Induced Anchor Graph Fusion for Multi-View Clustering. ACM Trans. on Knowledge Discovery from Data. 2022. (CCF B类, Early Access) 
• Zhibin Gu^, Songhe Feng*. Individuality Meets Commonality: A Unified Graph Learning Framework for Multi-View Clustering. ACM Trans. on Knowledge Discovery from Data. 2022. (CCF B类, Early Access)
• Xiang Deng^, Songhe Feng*. Beyond Word Embeddings: Heterogeneous Prior Knowledge Driven Multi-Label Image Classification. IEEE Trans. on Multimedia, 2022. (CCF B类, Early Access)
• Lijuan Sun^, Songhe Feng*. Global-Local Label Correlation for Partial Multi-Label Learning. IEEE Trans. on Multimedia, 24(2), pp. 581-593, 2022. (CCF B类)
• Gengyu Lyu^, Songhe Feng*. A Self-paced Regularization Framework for Partial-Label Learning. IEEE Trans. on Cybernetics, 52(2), pp. 899-911, 2022. (CCF B类) 
• Gengyu Lyu^, Songhe Feng*. Prior Knowledge Regularized Self-Representation Model for Partial Multi-Label Learning. IEEE Trans. on Cybernetics. (CCF B类, Early Access)
• Zhibin Gu^, Hongzhe Liu*, Songhe Feng*. Diversity Induced Consensus and Structured Graph Learning for Multi-View Clustering. Applied Intelligence, 2022. (Early Access)   
• Wei Liu^, Jiazheng Yuan*, Gengyu Lyu^, Songhe Feng*.  Label Driven Latent Subspace Learning for Multi-View Multi-Label Classification. Applied Intelligence, 2022. (Early Access)   
• Shaokai Wang^, Mingxuan Xia#, Zilong Wang#, Gengyu Lyu^, Songhe Feng*. Partial Label Learning with Noisy Side Information. Applied Intelligence, 52(11), pp. 12382-12396, 2022. 
• Xinyuan Liu^, Lijuan Sun^, Songhe Feng*. Incomplete Multi-View Partial Multi-Label Learning. Applied Intelligence, 52(3), pp. 3289-3302, 2022.
• Jianguo Zhao^, Gengyu Lyu^, Songhe Feng*. Linear Neighborhood Reconstruction Constrained Latent Subspace Discovery for Incomplete Multi-View Clustering. Applied Intelligence, 52(1), pp. 982-993, 2022.
• Tengfei Liang, Yi Jin, Wu Liu, Songhe Feng, Tao Wang, Yidong Li. Keypoint-Guided Modality-Invariant Discriminative Learning for Visible-Infrared Person Re-Identification. ACM Multimedia, 2022. (CCF A类) 
• Gongpei Zhao, Tao Wang, Yidong Li, Yi Jin, Congyan Lang, Songhe Feng. Neighborhood Pattern is Crucial for Graph Convolutional Networks Performing Node Classification. IEEE Trans. on Neural Networks and Learning System. 2022. (CCF B类, Early Access)
• Zheming Xu, Lili Wei, Congyan Lang, Songhe Feng, Tao Wang, Adrian G. Bors, Hongzhe Liu. SSR-Net: A Spatial Structural Relation Network for Vehicle Re-Identification. ACM Trans. on Multimedia Computing, Communication, and Applications. 2022. (CCF B类, Accepted)
• Liqian Liang, Congyan Lang, Zun Li, Jian Zhao, Tao Wang, Songhe Feng. Seeing Crucial Parts: Vehicle Model Verification via A Discriminative Representation Model. ACM Trans. on Multimedia Computing, Communication, and Applications, 18(1), pp. 1-22, 2022. (CCF B类) 
• Zun Li, Congyan Lang, Liqian Liang, Jian Zhao, Songhe Feng, Qibin Hou, Jiashi Feng. Dense Attentive Feature Enhancement for Salient Object Detection. IEEE Trans. on Circuits and Systems for Video Technology, 32(12), pp. 8128-8141, 2022. (CCF B类)  
• Yutong Gao, Liqian Liang, Congyan Lang, Songhe Feng, Yidong Li, Yunchao Wei. Clicking Matters: Towards Interactive Human Parsing. IEEE Trans. on Multimedia. (CCF B类, Early Access)
• Lili Wei, Congyan Lang, Liqian Liang, Songhe Feng, Tao Wang, Shidi Chen. Weakly-Supervised Video Object Segmentation via Dual-Attention Cross-Branch Fusion. ACM Trans. on Intelligent Systems and Technology, 13(3), pp.1-20, 2022 . 
• Xiuting You, He Liu, Tao Wang, Songhe Feng, Congyan Lang. Object Detection by Crossing Relational Reasoning based on Graph Neural Network. Machine Vision and Applications, 2022. 
• Shi Qiu, Yi Jin, Songhe Feng, Tao Zhou, Yidong Li. Dwarfism Computer-Aided Diagnosis Algorithm based on Multimodal Pyradiomics. Information Fusion, pp. 137-145, 2022. 
• Ruijie Zhao, Congyan Lang, Zun Li, Liqian Liang, Lili Wei, Songhe Feng, Tao Wang. Pedestrain Attribute Recognition based on Attribute Correlation. Multimedia System, pp. 1069-1081, 2022. 
• Yichen Zhu, Lili Wei, Congyan Lang, Siyu Li, Songhe Feng, Yidong Li. Fine-Grained Facial Expression Recognition via Relational Reasoning and Hierarchical Relation Optimization. Pattern Recognition Letters, 2022.

2021:

• Yanan Wu^, He Liu+, Songhe Feng*. GM-MLIC: Graph Matching based Multi-Label Image Classification. IJCAI, pp. 1179-1185, 2021. (CCF A类)   
• Gengyu Lyu^, Songhe Feng*. GM-PLL: Graph Matching based Partial Label Learning.  IEEE Trans. on Knowledge and Data Engineering, 33(2), pp. 521-535, 2021. (CCF A类)
• Lijuan Sun^, Songhe Feng*. Partial Multi-Label Learning with Noisy Side Information. Knowledge and Information Systems, 63(2), pp. 541-564, 2021. (CCF B类)
• Gengyu Lyu^, Songhe Feng*. Noisy Label Tolerance: A New Perspective of Partial Multi-Label Learning. Information Sciences, 543(1), pp. 454-466, 2021. (CCF B类)
• Lijuan Sun^, Gengyu Lyu^, Songhe Feng*. Beyond Missing: Weakly-Supervised Multi-Label Learning with Incomplete and Noisy Labels, Applied Intelligence, 51(3), pp. 1552-1564, 2021. 
• Yanan Wu^, Songhe Feng*. L4Net: An Anchor-Free Generic Object Detector with Attention Mechanism for Autonomous Driving. IET Computer Vision, 15(1), pp. 36-46, 2021. 
• Tong Zhou^, Songhe Feng*. Multiple Semantic Embedding with Graph Convolutional Networks for Multi-Label Image Classification. PRCV, 2021. 
• Liqian Liang, Congyan Lang, Yidong Li, Songhe Feng, Jian Zhao. Fine-Grained Facial Expression Recognition in the Wild. IEEE Trans. on Information Forensics and Security, 16(1), pp. 482-494, 2021. (CCF A类) 
• Min Wang, Congyan Lang, Liqian Liang, Songhe Feng, Tao Wang, Yutong Gao. Fine-Grained Semantic Image Synthesis with Object Attention Generative Adversarial Network. ACM Trans. on Intelligent Systems and Technology, 12(5), pp. 1-18, 2021.  
• Min Wang, Congyan Lang, Songhe Feng, Tao Wang, Yi Jin, Yidong Li. Text to Photo-Realistic Image Synthesis via Chained Deep Recurrent Generative Adversarial Network. Journal of Visual Communication ans Image Representation, 74(1), 2021. 
• Min Wang, Congyan Lang, Liqian Liang, Gengyu Lyu, Songhe Feng, Tao Wang. Class-balanced Text to Image Synthesis with Attentive Generative Adversarial Network. IEEE Multimedia, 28(3), pp. 21-31, 2021.

2020: 

• Gengyu Lyu^, Songhe Feng. Partial Multi-Label Learning via Probabilistic Graph Matching Mechanism. ACM SIGKDD, pp. 105-113, 2020. (Research Track, CCF A类)
• Ziwei Li^, Gengyu Lyu^, Songhe Feng*. Partial Multi-Label Learning via Multi-Subspace Representation. IJCAI, pp. 2612-2618, 2020. (CCF A类) 
• Gengyu Lyu^, Songhe Feng*. HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-Rank Regularization. ACM Trans. on Intelligent Systems and Technology, 11(3), 34: 1-34:19, 2020. 
• Gengyu Lyu^, Songhe Feng*. Partial Label Learning via Self-Paced Curriculum Learning, ECML-PKDD, pp. 489-505, 2020. (CCF B类)     
• Yue Sun^, Gengyu Lyu^, Songhe Feng*. Partial Label Learning via Subspace Representation and Global Disambiguation, ECML-PKDD, pp. 439-454, 2020. (CCF B类) 
• Lijuan Sun^, Ping Ye^, Gengyu Lyu^, Songhe Feng*. Weakly-Supervised Multi-Label Learning with Noisy Features and Incomplete Labels. Neurocomputing, 413(6), pp. 61-71, 2020.
• Gengyu Lyu^, Songhe Feng*. Partial Label Learning via Low-Rank Representation and Label Propagation. Soft Computing, pp. 5165-5176, 2020. 
• Honglin Quan^, Songhe Feng*. Improving Person Re-identification via Attribute-identity Representation and Visual Attention Mechanism. Multimedia Tools and Applications, 79(11-12), pp. 7259-7278, 2020. 
• Min Wang, Congyan Lang, Liqian Liang, Yutong Gao, Songhe Feng, Tao Wang. End-to-End Text-to-Image Synthesis with Spatial Constraints. ACM Trans. on Intelligent Systems and Technology, 11(4): 47:1-47:19, 2020.
• Min Wang, Congyan Lang, Liqian Liang, Gengyu Lyu, Songhe Feng, Tao Wang. Attentive Generative Adversarial Network to Bridge Multi-Domain Gap for Image Synthesis. ICME, pp, 1-6, 2020. (CCF B类)
• Zhongyi Li, Yi Ji, Yidong Li, Congyan Lang, Songhe Feng, Tao Wang.  Learning Part-Alignment Feature for Person Re-Identification with Spatial Temporal based Re-ranking Method. World Wide Web, 23(3), pp. 1907-1923, 2020. (CCF B类)  
• Zhenxing Zheng, Zhendong Li, Gaoyun An, Songhe Feng. Subgraph and Object Context-Masked Network for Scene Graph Generation. IET Computer Vision, 14(7), pp. 546-553, 2020. 
• Yingxia Jia, Congyan Lang, Songhe Feng. A Semantic Segmentation Method of Traffic Scene Based on Categries-Aware Domain Adaption. Journal of Computer Research and Development, 2020. (In Chinese)  
  
• Zheming Xu, Lili Wei, Congyan Lang, Songhe Feng, Tao Wang, Adrian G Bors. HSS-GCN: A Hierarchical Spatial Structure Graph Convolutional Network for Vehicle Re-Identification. ICPR, 2020.