苏   丰   |   Feng   Su

博士, 副教授  |  Dr., Associate Professor

联系方式 | Contact

• 地址 | Address：
  WILLIAMHILL在线体育投注
  江苏省南京市栖霞区仙林大道163号
  School of Computer Science, Nanjing University
  163 Xianlin Road, Qixia District, Nanjing, Jiangsu Province, China
  
• 邮编 | Postcode：210023
• E-Mail：suf (at) nju (dot) edu (dot) cn

简历 | CV

1997年获得WILLIAMHILL在线体育投注计算机科学与技术专业学士学位，2002年获得WILLIAMHILL在线体育投注计算机应用技术专业工学博士学位。 分别于2000年和2002年在香港理工大学、微软亚洲研究院进行短期访问研究，2006年于法国从事图像处理博士后访问研究。 近年来在IEEE TPAMI、计算机学报、计算机研究与发展等国内外学术刊物和CVPR、ACM MM、ACM ICMR、IEEE ICME、ICASSP、ICPR、ICDAR、ACCV、BMVC、MMM等国际学术会议上发表论文40余篇。

Obtained a Bachelor degree in Computer Science and Technology from Nanjing University in 1997, and a Doctor degree in Computer Application Technology from Nanjing University in 2002. Conducted visiting research at Hong Kong PolyU (2000), MSRA (2002), and Supelec (2006). Published more than 40 papers on journals and conferences including IEEE TPAMI, CVPR, ACM MM, ACM ICMR, IEEE ICME, ICASSP, ICPR, ICDAR, ACCV, BMVC, and MMM.

课程教学 | Teaching

• 计算机系统基础（Introduction to Computer Systems）
• 计算机网络（Computer Network）
• ……

[校外访问]   [校内网]

研究方向 | Research

多媒体计算 | Multimedia Computing：

• 媒体内容标注与检索 | Media Content Annotation and Retrieval
  
• 音频/音乐/视频分割、分析、分类与处理 | Segmentation, Analysis, Classification, and Processing of Audio/Music/Video
  
• 多模态数据建模与处理：融合视频、音频、文本等多种模态数据或信息的多媒体内容建模、分析与应用 | Multimodal Data Modeling and Processing
  

计算机视觉与模式识别 | Computer Vision and Pattern Recognition：

• 自然场景图像文本信息提取 | Text Information Extraction from Natural Scene Images
  
• 文档图像处理与图形识别 | Document Image Processing and Graphic Recognition
  
  

论文 | Publications

• Mingjun Li, Zeming Zhuang, Dingduo Zhong, Feng Su*. Diffusion-Based Scene Text Image Super-Resolution with Visual Style and Semantic Guidance. 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10602-10606, 2026.
• Mingjun Li, Zeming Zhuang, Feng Su*. Scene Text Image Super-Resolution with Visual Text Cues Transfer and Enhancement. 2025 IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6, 2025.
• Shuo Xu, Zeming Zhuang, Mingjun Li, Feng Su*. Arbitrary-Shaped Scene Text Recognition with Deformable Ensemble Attention. 27th International Conference on Pattern Recognition (ICPR 2024), Lecture Notes in Computer Science, vol 15331, pp. 237-253, 2025. (Best Scientific Paper Award)
• Mingjun Li, Zeming Zhuang, Shuo Xu, Feng Su*. MPGTSRN: Scene Text Image Super-Resolution Guided by Multiple Visual-Semantic Prompts. 27th International Conference on Pattern Recognition (ICPR 2024), Lecture Notes in Computer Science, vol 15332, pp. 316-331, 2025.
• Mingjun Li, Shuo Xu, Feng Su*. Learning and Fusing Multi-Scale Representations for Accurate Arbitrary-Shaped Scene Text Recognition. 2023 ACM International Conference on Multimedia Retrieval (ICMR), pp. 353-361, 2023.
• Long Chen, Feng Su*, Jiahao Shi, Ye Qian. Reading Arbitrary-Shaped Scene Text from Images Through Spline Regression and Rectification. 16th Asian Conference on Computer Vision (ACCV 2022), Lecture Notes in Computer Science, vol 13845, pp. 107-123, 2023.
• Long Chen, Feng Su*. Towards Robust Video Text Detection with Spatio-Temporal Attention Modeling and Text Cues Fusion. 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6, 2022.
• Long Chen, Jiahao Shi, Feng Su*. Robust Video Text Detection Through Parametric Shape Regression, Propagation and Fusion. 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6, 2021.
• Ye Qian, Long Chen, Feng Su*. An Adaptive Rectification Model for Arbitrary-Shaped Scene Text Recognition. 32nd British Machine Vision Conference (BMVC), pp. 1-13, 2021.
• Jiahao Shi, Long Chen, Feng Su*. Accurate Arbitrary-Shaped Scene Text Detection via Iterative Polynomial Parameter Regression. 15th Asian Conference on Computer Vision (ACCV 2020), Lecture Notes in Computer Science, vol 12624, pp. 241-256, 2020.
• Ye Qian, Yuyang Wang, Feng Su*. Robust Scene Text Recognition Through Adaptive Image Enhancement. 31st British Machine Vision Conference (BMVC), pp. 1-13, 2020.
• Lan Wang, Jiahao Shi, Yang Wang, Feng Su*. Video Text Detection by Attentive Spatiotemporal Fusion of Deep Convolutional Features. 27th ACM International Conference on Multimedia (MM’19), pp. 66-74, Nice, France, October 21–25, 2019.
• Qianqian Wang, Feng Su*, Yuyang Wang. A Hierarchical Attentive Deep Neural Network Model for Semantic Music Annotation Integrating Multiple Music Representations. 2019 International Conference on Multimedia Retrieval (ICMR 2019), pp. 150-158, Ottawa, Canada, June 10–13, 2019.
• Yuyang Wang, Feng Su*, Ye Qian. Text-Attentional Conditional Generative Adversarial Network for Super-Resolution of Text Images. 2019 IEEE International Conference on Multimedia and Expo (ICME 2019), pp. 1024-1029, Shanghai, China, July 8-12, 2019.
• Lan Wang, Yang Wang, Susu Shan, Feng Su*. Scene Text Detection and Tracking in Video with Background Cues. 2018 ACM on International Conference on Multimedia Retrieval (ICMR 2018), pp. 160-168, Yokohama, Japan, June 11-14, 2018.
• Qianqian Wang, Yu Xiong, Feng Su*. Semantic Music Annotation by Label-Specific Conditional Random Fields. ICPR 2018, pp. 2941-2946, Beijing, China, August 20-24, 2018.
• Feng Su*, Wenjun Ding, Lan Wang, Susu Shan, Hailiang Xu. Text Proposals Based on Windowed Maximally Stable Extremal Region for Scene Text Detection. ICDAR 2017, pp. 377-382, Kyoto, Japan, 9-15 November 2017.
• Wenjun Ding, Susu Shan, Feng Su*. Text Detection in Natural Scene Images by Hierarchical Localization and Growing of Textual Components. ICME 2017, pp. 775-780, Hong Kong, China, 10-14 July, 2017.
• Yu Xiong, Feng Su*, Qianqian Wang. Automatic Music Mood Classification by Learning Cross-Media Relevance Between Audio and Lyrics. ICME 2017, pp. 961-966, Hong Kong, China, 10-14 July 2017.
• Feng Su* and Hao Xue. Graph-Based Multimodal Music Mood Classification in Discriminative Latent Space. MMM 2017, pp. 152-163, Reykjavik, Iceland, 4-6 January 2017.
• Susu Shan, Hailiang Xu, Feng Su*. A New Method for Spatiotemporal Textual Saliency Detection in Video. ICPR 2016, pp. 3240-3245, Cancun, Mexico, Dec. 4-8, 2016.
• Feng Su* and Like Xue. Graph Learning on K Nearest Neighbours for Automatic Image Annotation. ICMR 2015, pp. 403-410, Jun. 23-26, 2015.
• Hailiang Xu and Feng Su*. Robust Seed Localization and Growing with Deep Convolutional Features for Scene Text Detection. ICMR 2015, pp. 387-394, Jun. 23-26, 2015.
• Hailiang Xu and Feng Su*. A Robust Hierarchical Detection Method for Scene Text Based on Convolutional Neural Networks. ICME 2015, pp. 1-6, Jun.29-Jul.3, 2015.
• Feng Su* and Hailiang Xu. Robust seed-based stroke width transform for text detection in natural images. ICDAR 2015, pp. 916-920, Aug. 23-26, 2015.
• Hao Xue, Like Xue, Feng Su*. Multimodal Music Mood Classification by Fusion of Audio and Lyrics. MMM 2015, pp. 26–37，Jan. 5-7, 2015.
• Like Xue and Feng Su*. Auditory Scene Classification with Deep Belief Network. MMM 2015, pp. 348–359，Jan.5-7, 2015.
• Feng Su. Auditory Scene Analysis and Recognition with LDA Topic Model. ICME 2014, 1-6, August 25-28, 2014.
• Hailiang Xu, Like Xue, Feng Su*. Scene Text Detection Based on Robust Stroke Width Transform and Deep Belief Network. ACCV 2014, Singapore, Oct.29-Nov.5, 2014.
• Feng Su* and Tong Lu. Discriminative Weighting and Subspace Learning for Ensemble Symbol Recognition. ICDAR 2013, 1088-1092, Washington DC, USA, August, 2013.
• Feng Su*, Li Yang, Tong Lu. Ensemble Symbol Recognition with Hough Forest. ICPR 2012, pp.1659-1662, Tsukuba, Japan, Nov. 11-15, 2012.
• Li Yang and Feng Su*. Auditory Context Classification Using Random Forests. 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp.2349-2352, Kyoto, Japan, Mar. 25-30, 2012.
• Feng Su*, Li Yang, Tong Lu, Gongyou Wang. Environmental Sound Classification for Scene Recognition Using Local Discriminant Bases and HMM. 2011 ACM International Conference on Multimedia (MM’11), pages 1389-1392, Scottsdale, USA, 2011.
• Feng Su*, Tong Lu, Ruoyu Yang. Symbol Recognition By Multiresolution Shape Context Matching. 11th International Conference on Document Analysis and Recognition (ICDAR 2011), pages 1319-1323, Beijing, China, Sep. 18-21, 2011.
• Feng Su*, Tong Lu, Ruoyu Yang. Symbol Recognition Combining Vectorial and Pixel-Level Features for Line Drawings. In Proc. 20th International Conference on Pattern Recognition (ICPR 2010), pages 1892-1895, Turkey, 2010.
• Feng Su*, Ali M.-Djafari. Bayesian Separation of Document Images with Hidden Markov Model. 2nd International Conference on Computer Vision Theory and Applications, pp. 151-156, 2007.
• Feng Su*, Jiqiang Song, Shijie Cai. A Vectorization System for Architecture Engineering Drawings. Graphics Recognition - Ten Years Review and Future Perspectives, GREC 2005, LNCS 3926, pp. 11-22, 2006.
• Tong Lu, Chiew-Lan Tai, Feng Su, Shijie Cai. A New Recognition Model for Electronic Architectural Drawings. Computer-Aided Design, 37:1053–1069, 2005.
• Jiqiang Song, Feng Su, Chiew-Lan Tai, Shijie Cai. An Object Oriented Progressive-Simplification Based Vectorization System for Engineering Drawings: Model, Algorithm and Performance. IEEE Trans. Pattern Analysis and Machine Intelligence, 24(8):1048-1060, 2002.
• Feng Su, Jiqiang Song, Chiew-Lan Tai, Shijie Cai. Dimension Recognition and Geometry Reconstruction in Vectorization of Engineering Drawings. 2001 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 710-716, 2001.
• Jiqiang Song, Feng Su, Jibing Chen, Chiew-Lan Tai, Shijie Cai. Line Net Global Vectorization: An Algorithm and Its Performance Evaluation. 2000 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 383-388, 2000.
• ...