职 称: 副教授

学 位:博士

邮 箱:shfeng@bjtu.edu.cn

办公电话:

个人主页: sites.google.com/site/bjtufsh/

北京交通大学计算机与信息技术学院副教授,博士生导师,入选北京交通大学青年英才计划II类人选。2009年6月毕业于北京交通大学,获计算机应用技术专业博士学位。后进入北京交通大学信息与信号处理博士后科研流动站从事师资博士后研究工作。申请人攻读博士期间主要从事图像语义检索及自动标注相关研究,主要研究了基于视觉注意力机制的图像检索、自动语义标注等热点问题,完成了博士论文《面向感知的图像检索及自动标注算法研究》。博士后在站期间,继续研究图像标注及图像场景分类等相关课题,获得中国博士后科学基金面上项目1项(已结题),特别资助项目1项(已结题)。

目前主持包括国家自然科学基金面上项目、北京市自然科学基金面上项目等在内的多项省部级以上课题。 在国际学术刊物和国际会议上累计发表各类研究论文30余篇,其中在IEEE Trans on Image Processing, IEEE Trans on Multimedia, Signal Processing, Pattern Recognition, JVCIR, Neurocomputing, Expert Systems with Applications,IEICE Trans on Info & Sys, Chinese Journal of Electronics,电子学报 等国内外学术期刊及ACM Multimedia, ECCV, ACM CIVR等国际会议上发表论文近20篇,申请国家发明专利1项,软件著作权2项。2013年10月至2014年10月,受国家留学基金委资助,在 Department of Computer Science and Engineering, Michigan State University进行学术访问。

大规模图像及视频语义内容理解;

机器学习及在多媒体信息处理中的应用;

代表性论文:

Peer Reviewed Journal Publications:

[new] Songhe Feng, Congyan Lang. Graph Regularized Low-rank Feature Mapping for Multi-label Learning with Application to Image Annotation. Multidimensional Systems and Signal Processing, 2017, Accepted.

[new] Songhe Feng, Congyan Lang, Jiashi Feng, Jiebo Luo. Human Facial Age Estimation by Cost-Sensitive Label Ranking and Trace Norm Regularization. IEEE Trans. On Multimedia, 2017, Page19(1), 136 - 148, 2017.

[new] Yanan Dong, Congyan Lang, Songhe Feng*(corresponding author). General structured sparse learning for human facial age estimation. Multimedia Systems, 2017.

[new] 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), 1190-1200, 2016.

[1] Tao Wang, Haibin Ling, Congyan Lang, Songhe Feng. Symmetry-Aware Graph Matching, Pattern Recognition, 6(60), 657-668, 2016.

[2] Zhu Teng, Tao Wang, Feng Liu, Dong-Joong Kang, Congyan Lang, Songhe Feng. From sample selection to model update: A robust online visual tracking algorithm against drifting. Neurocomputing, 173(3). 1221-1234, 2016.

[3] Songhe Feng, Zheyun Feng, Rong Jin. Learning to rank image tags with limited training examples. IEEE Trans on Image Processing, 2015.

[4] Tao Wang, Hua Yang, Congyan Lang, Songhe Feng. An error-tolerant approximate matching algorithm for labeled combinatorial maps. Neurocomputing, 156(25). 211-220, 2015.

[5] 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.

[6] 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.

[7] Congyan Lang, Songhe Feng. Supervised sparse patch coding towards misalignment-robust face recognition. Journal of Visual Communication and Image Representation 24(2), pp.103-110, 2013.

[8] Congyan Lang, Songhe Feng. A unified supervised codebook learning framework for classification. Neurocomputing, 77(1). 281-288, 2012.

[9] Songhe Feng, Hong Bao. Combining visual attention model with multi-instance learning for tag ranking. Neurocomputing, 74. 3619-3627, 2011.

[10] Xu Yang, De Xu, Songhe Feng, Yingjun Tang, Shuoyan Liu. Scene Categorization with Classified Codebook Model. IEICE Trans. On Info. & Sys. Vol.E94-D, No. 6, Jun.2011.

[11] Hong Bao, Songhe Feng, De Xu, Shuoyan Liu. A Novel Saliency based Graph Learning Framework With Application to CBIR, IEICE Trans. On Info. & Sys. Vol.E94-D, No. 6, Jun.2011.

[12] 冯松鹤,郎丛妍,须德。一种融合图学习与区域显著性分析的图像检索算法。电子学报,39(10), pp.2288-2294, 2011.

[13] Shuoyan Liu, De Xu, Songhe Feng. Region Contextual Visual Words for Scene Categorization. Expert Systems with Applications, 38(9), pp. 11591-11597, 2011.

[14] Shuoyan Liu, De Xu, Songhe Feng. Emotion categorization using affective pLSA model. Optical Engineering, 49(12), 2010.

[15] Songhe Feng, De Xu. Attention-driven Salient Edge(s) and Region(s) Extraction with Application to CBIR. Signal Processing, 90(1), pp.1-15, Jan.2010.

[16] 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.

[17] Shuoyan Liu, De Xu, Songhe Feng. Discriminating Semantic Visual Words for Scene Classification. IEICE Trans. on Information & System, 93-D(6): 1580-1588, 2010.

[18] Bing Li, De Xu, Weihua Xiong, Songhe Feng. Color Constancy using Achoromatic Surface. Color Research & Application, 2010, 35(4): 304-312.

[19] 刘硕研,须德,冯松鹤.一种基于上下文语义信息的图像块视觉单词生成算法.电子学报,2010.

[20] Bing Li, De Xu, Songhe Feng. Illumination-independent descriptors using color moment invariants. SPIE Optical Engineering. 48(2), 2009.

[21] Bing Li, De Xu, Songhe Feng. Illumination Estimation Based on Color Invariant. Chinese Journal of Electronics, 2009, 18(3): 431-434.

[22] Songhe Feng, De Xu, Bing Li. Automatic Region-based Image Annotation Using an Improved Multiple-Instance Learning Algorithm. Chinese Journal of Electronics, 17(1): 43-47. 2008.

[23] Songhe Feng, De Xu, Bing Li. Combining Attention Model with Hierarchical Graph Representation for Region-based Image Retrieval, IEICE Trans. On Info. & Sys. Vol.E91-D, Aug. 2008.

[24] Songhe Feng, De Xu. Automatic Image Annotation Using Semi-Supervised Multi-Instance Multi-Label Learning Algorithm. Chinese Journal of Electronics, 17(4): 602-606, 2008.

[25] Bing Li, De Xu, Moon Ho Lee, Songhe Feng. A Multi-Scale Adaptive Graey World Algorithm. IEICE Trans. on Information & System, 90-D(7): 1121-1124, 2007.

Peer Reviewed Conference Publications:

[1] Chenjing Yan, Congyan Lang, Songhe Feng. Facial Age Estimation Based on Structured Low-rank Representation. ACM Multimedia, 2015.

[2] Xiaoyuan Luo, Songhe Feng. A General Method for Sensitive Identification Detection in the Terrorist Video. ICIMCS, 2015.

[3] Dongmei He, Congyan Lang, Songhe Feng. Vehicle Detection and Classification Based on Convolutional Neural Network. ICIMCS, 2015.

[4] Zheyun Feng, Songhe Feng, Rong Jin, Anil K. Jain. Image Tag Completion by Noisy Matrix. ECCV, 2014.

[5]Jie Sun, Songhe Feng, Wen Wang, Congyan Lang: Personalized image recommendation and retrieval via latent SVM based model. ICIMCS, pp.223-226, 2013.

[6] Jun Wu, Yidong Li, Songhe Feng. A Self-immunizing Manifold Ranking for Image Retrieval. PAKDD, pp. 426-436, 2012.

[7] Wen Wang, Congyan Lang, Songhe Feng. Contextualizing Tag Ranking and Saliency Detection for Social Images. MMM, pp.428-435, 2012.

[8] Songhe Feng, Congyan Lang, Bing Li. Towards Relevance and Saliency Ranking of Image Tags. ACM Multimedia, pp.917-920, 2012.

[9] Bing Li, Songhe Feng, Weihua Xiong, Weiming Hu. Scaring or pleasing: exploit emotional impact of an image. ACM Multimedia,pp.1365-1366, 2012.

[10] Congyan Lang, Bin Cheng, Songhe Feng, Xiao-tong Yuan. Supervised Sparse Patch Coding Towards Misalignment-Robust Face Recognition. ICIG, pp. 599-604, 2011.

[11] Songhe Feng, Congyan Lang, De Xu. Beyond Tag Relevance: Integrating Visual Attention Model and Multi-Instance Learning for Tag Saliency Ranking. ACM CIVR, pp.288-295, 2010.

[12] Songhe Feng, Congyan Lang, De Xu. Localized Content-based Image Retrieval Using Saliency-based Graph Learning Framework. In: Proc. of Int. Conf. on Signal Processing (ICSP), Beijing, Oct.2010.

[13] Congyan Lang, Songhe Feng. Saliency detection by non-linear intensity mapping in images. In: Conf. on Signal Processing (ICSP), Beijing, China, pp. 1025-1028, Oct.2010.

[14] Bing Li, De Xu, Songhe Feng, Fangshi Wang. Visual Perception Theory Guided Depth Motion Estimation. MMM, pp. 198-206, 2007.

[15] Songhe Feng, De Xu. Locating salient edges for CBIR based on visual attention model. In: Proc. of Int. Conf. on Natural Computation (ICNC), Xi’an, China, Sep.2006, LNCS 4221, 261-264, 2006.

[16] Songhe Feng, De Xu. A Novel Graph Kernel Based SVM Algorithm for Image Semantic Retrieval. In: Proc. of Int. Symp. on Neural Networks (ISNN), Chengdu, China, May 2006, LNCS 3972, 589-594, 2006.

[17] Songhe Feng, De Xu. A Novel Region-based Image Retrieval Algorithm Using Selective Visual Attention Model. In: Proc. of Int. Conf. on Advanced Concepts for Intelligent Vision Systems (ACIVS), Antwerp, Belgium, Sep. 2005, LNCS 3708, 235-242, 2005.

国家发明专利及软件著作权

1. 冯松鹤;一种基于视觉注意力模型的图像语义检索方法。国家发明专利申请号:200910011164.0.

2. 冯松鹤, 郎丛妍;2011SRBJ3835 融合用户反馈的区域级图像检索软件V1.0

3. 冯松鹤, 郎丛妍;2011SRBJ3834 融合颜色词描述的自动图像标注软件V1.0


代表性著作:

科研项目:

主持的科研项目:

1. 北京市自然科学基金面上项目:基于上下文语义的社群图像语义理解关键技术研究, 2016-2018.

2. 国家自然科学基金面上项目:海量社群图像语义理解关键技术研究,2015--2018.

3. 国家自然科学基金青年基金:基于视觉认知理论的图像层次化语义理解研究, 2012-2014.

4. 基本科研业务费:基于上下文的图像语义理解关键技术研究,2014--2015.

5. 其它部市:社群图像语义理解,2013--2014.

6. 国家自然科学基金:基于上下文感知的互联网社群图像语义理解,2013--2016.

7. 人才基金:基于Web图像搜索和视觉注意力机制的标签排序算法研究,2012--2014

8. 博士点基金:面向视觉感知的图像层次化语义理解研究,2012---2014.

9. 其它:基于多示例多标记学习的图像自动标注及分类算法研究,2012-2013.

10. 基本科研业务费:海量图像语义标注及情感分类算法研究,2011-2014.

11. 其它部市:基于视觉认知理论的图像语义标注及多标记排序算法研究,2010-2012.

12. 教育部:基于视觉认知理论的图像层次化语义理解研究,2010--2011.

13. 国家自然科学基金“面上”:基于视觉感知的中国书画图像语义自动分类研究,2010--2012-

14. 基本科研业务费:基于视知觉的图像层次化语义标注算法研究,2009-2012.

15. 其它部市:基于颜色认知的图像层次化语义标注算法研究,2010-2011.


获奖情况:

[1] 入选2015-2017年度北京交通大学青年英才计划II类;

[2] 2011年度,北京交通大学握奇奖教金;

[3] 2010年度,计算机与信息技术学院教学基本功比赛一等奖;

None
院内链接: 高速铁路网络管理研究中心 交通数据分析与挖掘实验室 信息安全系 信息科学研究所 计算机实验教学中心 基础教学基地 网络科学与智能系统研究所 信息通信网络研究所

北京交通大学计算机与信息技术学院

地址:北京市海淀区上园村3号北京交通大学第九教学楼 邮编:100044

Copyright @ 2015 北京交通大学 计算机与信息技术学院 All Rights Reserved 信息系统备案号:13022701