馮松鶴:人物經歷,研究方向,主講課程,學術成果,科研項目,發表論文,專利申請,社會

基本介紹

中文名：馮松鶴
國籍：中國
民族：漢
畢業院校：北京交通大學
學位/學歷：博士
職業：教師
專業方向：機器學習與認知計算;人工智慧及套用;計算機技術
職務：北京交通大學博士生導師
職稱：北京交通大學教授

人物經歷,研究方向,主講課程,學術成果,科研項目,發表論文,專利申請,社會兼職,榮譽獎項,

人物經歷

北京交通大學計算機與信息技術學院教授，博士生導師，入選首批北京交通大學青年英才培育計畫，擔任北京市信息服務工程北京市重點實驗室學術委員會委員。於2003年及2009年畢業於北京交通大學，分獲計算機科學與技術專業學士學位及計算機套用技術專業博士學位。主要研究領域為弱監督機器學習算法及其在圖像語義理解中的套用。累計主持國家自然科學基金面上及青年項目3項，北京市自然科學基金面上項目2項，教育部博士點基金1項，中國博士後科學基金特別資助項目及面上項目各1項。在包括 IEEE Trans. on PAMI, IEEE Trans. on Image Processing, IEEE Trans. on Knowledge and Data Engineering, IEEE Trans. on Multimedia, IEEE Trans. on Cybernetics 等知名學術期刊以及 ACM SIGKDD, AAAI, IJCAI, ACM Multimedia, ICCV, ECCV, ECML-PKDD 等知名國際會議上累計發表各類研究論文60餘篇。並擔任包括 AAAI, IJCAI 等國際頂級會議的程式委員會成員。受國家留學基金委資助，分別於2014年及2017年在美國密西根州立大學和德國德勒斯登工業大學任國家公派訪問學者。

研究方向

理論層面：聚焦於弱監督機器學習算法研究，包括多標記學習(Multi-Label Learning)、偏標記學習(Partial-Label Learning)、多視圖學習(Multi-View Learning)等；
套用層面：聚焦於深度學習框架下的圖像語義理解算法研究，包括但不限於：多標記圖像分類(Multi-Label Image Classification)、通用目標檢測(Object Detection)、行人再識別(Person Re-Identification)等；

主講課程

承擔本科生課程

C語言程式設計；
JAVA語言程式設計；
機器視覺基礎 (本科生課程)；

承擔研究生課程

Introduction to Machine Vision (For International Graduate Students);
視覺認知計算與圖像語義計算 (博士生課程)；
機器視覺基礎 (碩士生課程)；

學術成果

科研項目

主持多項國家自然科學基金項目 / 北京市自然科學基金項目 / 教育部博士點基金項目 / 中國博士後科學基金面上項目及特別資助項目 / 中央高校基本科研業務費項目 / 北京市重點實驗室開放課題項目等。

發表論文

( ^表示作者均為本人指導的研究生，*表示本人為通訊作者)

2021:

Lijuan Sun^, Songhe Feng*. Global-Local Label Correlation for Partial Multi-Label Learning. IEEE Trans. on Multimedia, 2021. (Accepted, CCF B類)
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類)
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類)
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類)
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, 2021. (CCF C類)
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, 2021. (Early Access)

2020:

Gengyu Lyu^, Songhe Feng. Partial Multi-Label Learning via Probabilistic Graph Matching Mechanism. ACM SIGKDD, pp. 105-113, 2020. (Research Track, CCF A類)
Ziwei Li^, Gengyu Lyu^, Songhe Feng*. Partial Multi-Label Learning via Multi-Subspace Representation. IJCAI, pp. 2612-2618, 2020. (CCF A類)
Gengyu Lyu^,Songhe Feng*. A Self-paced Regularization Framework for Partial-Label Learning. IEEE Trans. on Cybernetics. (CCF B類, Early Access)
Lijuan Sun^, Songhe Feng*. Partial Multi-Label Learning with Noisy Side Information. Knowledge and Information Systems. (CCF B類, Early Access)
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, 2020. (CCF B類)
Yue Sun^, Gengyu Lyu^, Songhe Feng*. Partial Label Learning via Subspace Representation and Global Disambiguation, ECML-PKDD, 2020. (CCF B類)
Lijuan Sun^, Gengyu Lyu^, Songhe Feng*. Beyond Missing: Weakly-Supervised Multi-Label Learning with Incomplete and Noisy Labels, Applied Intelligence. (CCF C類, Early Access)
Yanan Wu^, Songhe Feng*. L4Net: An Anchor-Free Generic Object Detector with Attention Mechanism for Autonomous Driving. IET Computer Vision. (CCF C類, Early Access)
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. (CCF C類)
Gengyu Lyu^, Songhe Feng*. Partial Label Learning via Low-Rank Representation and Label Propagation. Soft Computing, pp. 5165-5176, 2020. (CCF C類)
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. (CCF C類)
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類)
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類)
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. (CCF C類)
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)

2019:

Lijuan Sun^, Songhe Feng*. Partial Multi-Label Learning by Low-Rank and Sparse Decomposition. AAAI, 2019. (CCF A類)
Tao Wang, Haibin Ling, Congyan Lang, Songhe Feng, Xiaohui Hou. Deformable Surface Tracking by Graph Matching. ICCV, 2019. (CCF A類)
Xiaoying Wang^, Songhe Feng*. Semi-Supervised Dual Low-Rank Feature Mapping for Multi-Label Image Annotation. Multimedia Tools and Applications, 78(10), pp. 13149-13168, 2019. (CCF C類)
Lijuan Sun^, Songhe Feng*. Robust Semi-Supervised Multi-Label Learning by Triple Low-Rank Regularization. PAKDD, 2019. (CCF C類)
Zun Li, Congyan Lang, Jiashi Feng, Yidong Li, Tao Wang, Songhe Feng. Co-Saliency Detection with Graph Matching. ACM Trans. on Intelligent System and Technology, 10(3), 22:1-22:22,2019.
Yanan Dong, Congyan Lang, Songhe Feng*. General Structured Sparse Learning for Human Facial Age Estimation. Multimedia Systems, 25(1), pp. 49-57, 2019. (CCF C類)
Mengxia Yin, Congyan Lang, Zun Li, Songhe Feng, Tao Wang. Recurrent Convolutional Network for Video-based Smoke Detection. Multimedia Tools and Applications, 78(1), pp. 237-256, 2019. (CCF C類)
Bingqian Geng, Congyan Lang, Junliang Xing, Songhe Feng. MFAD: A Multi-modality Face Anti-spoofing Dataset. PRICAI, 2019. (CCF C類)
Ping Ye^, Songhe Feng*. Robust Multi-Label Learning with Corrputed Features and Incomplete Labels. CAC, 2019.

2018:

Tao Wang, Haibin Ling, Congyan Lang, Songhe Feng. Graph Matching with Adaptive and Branching Path Following. IEEE Trans. on Pattern Analysis and Machine Intelligence, 40(12), pp. 2853-2867, 2018. (CCF A類)
Songhe Feng, Congyan Lang. Graph Regularized Low-rank Feature Mapping for Multi-label Learning with Application to Image Annotation. Multidimensional Systems and Signal Processing, 29, pp. 1351-1372, 2018. (CCF C類)
Wenying Huang^, Songhe Feng*. Partial Label Learning via Low-rank Representation and Label Propagation. ICIMCS, 2018.
Tao Wang, Haibin Ling, Congyan Lang, Songhe Feng. Constrained Confidence Matching for Planar Object Tracking. ICRA, 2018. (CCF B類)
Zun Li, Congyan Lang, Songhe Feng, Tao Wang. Saliency Ranker: A New Salient Object Detection Method. Journal of Visual Communication and Image Representation, 50(1), pp. 16-26, 2018. (CCF C類)
Jun Zhou, Tao Wang, Congyan Lang, Songhe Feng. A Novel Hypergraph Matching Algorithm based on Tensor Refining. Journal of Visual Communication and Image Representation, 57, pp. 69-75, 2018. (CCF C類)
Shaoyan Xu, Tao Wang, Congyan Lang, Songhe Feng, Yi Jin. Graph-based Visual Odometry for VSLAM. Industrial Robot, 2018.

2017：

Songhe Feng, Congyan Lang, Jiashi Feng, Tao Wang, Jiebo Luo. Human Facial Age Estimation by Cost-Sensitive Label Ranking and Trace Norm Regularization. IEEE Trans. on Multimedia, 19(1), pp. 136-148, 2017. (CCF B類)
Zhu Teng, Junliang Xing, Qiang Wang, Congyan Lang, Songhe Feng, Yi Jin. Robust Object Tracking Based on Temporal and Spatial Deep Networks. ICCV, 2017. (CCF A類)

2016：

Congyan Lang, Jiashi Feng, Songhe Feng, Jingdong Wang, Shuicheng Yan. Dual Low-Rank Pursuit: Learning Salient Features for Saliency Detection. IEEE Trans. On Neural Networks and Learning Systems, 27(6), pp. 1190-1200, 2016. (CCF B類)
Tao Wang, Haibin Ling, Congyan Lang, Songhe Feng. Symmetry-Aware Graph Matching. Pattern Recognition, 60, pp. 657-668, 2016. (CCF B類)
Jingwei Li^, Songhe Feng*. Graph Regularized Low-rank Feature Learning for Robust Multi-Label Image Annotation. ICSP, 2016.

2015：

Songhe Feng, Zheyun Feng, Rong Jin. Learning to Rank Image Tags with Limited Training Examples. IEEE Trans. on Image Processing, 24(4), pp. 1223-1234, 2015. (CCF A類)
Chenjing Yan, Congyan Lang, Songhe Feng. Facial Age Estimation Based on Structured Low-rank Representation. ACM Multimedia, 2015. (CCF A類)
Xiaoyuan Luo^, Songhe Feng*. A General Method for Sensitive Identification Detection in the Terrorist Video. ICIMCS, 2015.
Tao Wang, Hua Yang, Congyan Lang, Songhe Feng. An Error-Tolerant Approximate Matching Algorithm for Labeled Combinational Maps. Neurocomputing, 156(25). pp. 211-220, 2015. (CCF C類)

2014：

Zheyun Feng, Songhe Feng, Rong Jin, A. K. Jain. Image Tag Completion by Noisy Matrix Recovery. ECCV, 2014. (CCF B類)
Songhe Feng, Weihua Xiong. Hierarchical Sparse Representation based Multi-Instance Semi-Supervised Learning with Application to Image Categorization. Signal Processing, 94(1), pp.595-607, 2014. (CCF C類)

2013:

Songhe Feng, Congyan Lang. Adaptive All-Season Image Tag Ranking by Saliency-Driven Image Pre-Classification. Journal of Visual Communication and Image Representation, 24(7), pp.1031-1039. 2013. (CCF C類)
Congyan Lang, Songhe Feng. Supervised Sparse Patch Coding Towards Misalignment-Robust Face Recognition. Journal of Visual Communication and Image Representation, 24(2): 103-110, 2013. (CCF C類)

2012:

Songhe Feng, Congyan Lang, Bing Li. Towards Relevance and Saliency Ranking of Image Tags. ACM Multimedia, 2012. (CCF A類)
Bing Li, Songhe Feng. Scaring or Pleasing: Exploit Emotional Impact of an Image. ACM Multimedia, 2012. (CCF A類 )

2011:

Songhe Feng, Hong Bao. Combining Visual Attention Model with Multi-instance Learning for Tag Ranking. Neurocomputing, 74(2011). pp. 3619-3627. (CCF C類)
Songhe Feng, Congyan Lang. Combining Graph Learning and Region Saliency Analysis for Content-based Image Retrieval. Chinese Journal of Electronics, 39(10), pp. 2287-2294, 2011. (In Chinese)
Shuoyan Liu, De Xu, Songhe Feng. Region Contextual Visual Words for Scene Classification. Expert Systems with Applications, 11591-11597, 2011. (CCF C類)
Hong Bao, Songhe Feng. A Novel Saliency-based Graph Learning Framework with Application to CBIR. IEICE Trans. on Information System, 94(6), pp. 1353-1356, 2011.

2010:

Songhe Feng, De Xu. Transductive Multi-Instance Multi-Label Learning Algorithm with Application to Automatic Image Annotation. Expert Systems with Applications, 37(1), pp. 661-670, Jan.2010. ( CCF C類)
Songhe Feng, De Xu. Attention-driven Salient Edge(s) and Region(s) Extraction with Application to CBIR. Signal Processing, 90(1), pp.1-15, 2010. (CCF C類)
Songhe Feng, Congyan Lang, De Xu. Beyond Tag Relevance: Integrating Visual Attention Model and Multi-Instance Learning for Tag Saliency Ranking. ACM CIVR, 2010. (CCF B類)Shuoyan Liu, De Xu, Songhe Feng. Discriminating Semantic Visual Words for Scene Classification. IEICE Trans. on Information System, 93(6), pp. 1580-1588, 2010.

Earlier:

Songhe Feng, De Xu. Combining Attention Model with Hierarichical Graph Representation for Region-based Image Retrieval. IEICE Trans. on Information System, 91(8), pp. 2203-2206, 2008.
Songhe Feng, De Xu. Automatic Image Annotation Using An Improved Multiple-Instance Learning Algorithm. Chinese Journal of Electronics, 17(1), pp. 43-47,2008.
Songhe Feng, De Xu. A Novel Graph Kernel Based SVM Algorithm for Image Semantic Retrieval. ISNN, 2016.
Songhe Feng, De Xu. Locating Salient Edges for CBIR Based on Visual Attention Model. ICNC, 2006.
Songhe Feng, De Xu. A Novel Region-based Image Retrieval Algorithm Using Selective Visual Attention Model. ACIVS, 2005.

專利申請

基於多子空間表示的偏多標記學習算法；專利號：202010412162.1；
基於全局和局部標記關係的偏多標記學習算法；專利號：202010411579.6；
特徵信息存在噪聲的偏多標記學習算法；專利號：202010411580.9；
基於噪聲容忍的偏多標記算法；專利號：202010412161.7；
基於子空間表示和全局標記消歧的偏標記學習算法；專利號：202010397386.X；

社會兼職

北京市信息服務工程北京市重點實驗室第三屆學術委員會委員(2020-2022)；
Program Committee Member: AAAI(2019, 2020, 2021), IJCAI(2019, 2020);
Journal Reviewer for : IEEE Trans. on PAMI, IEEE Trans. on Image Processing, IEEE Trans. on Multimedia, IEEE Trans. on NNLS, IEEE Trans. on Cybernetics, IEEE Trans. on Big Data；

榮譽獎項

2020年度，北京交通大學教書育人先進個人；
2015年度，北京交通大學青年英才計畫II類人選；
2011年度，北京交通大學握奇獎教金；
2010年度，北京交通大學計算機學院教學基本功比賽一等獎；

馮松鶴