Position: Home>About SCCE
Teacher Details
  • Personal Information
    Xucheng Yin

    Vice Dean

    Department:
    |Department of Computer Science and Technology|
    Professional Title:
    Professor  
    Position:
    Vice Dean
    Office:
    1002 of MEE Building
    Tel:
    E-Mail:
    xuchengyin@ustb.edu.cn
    Undergraduate Courses:
    Discrete mathematics; software engineering and curriculum design;
    Graduate Courses:
    Machine learning;Artificial Intelligence Frontier Technology
    Research Directions:
    Pattern recognition and computer vision; information retrieval and natural language processing; machine vision and intelligent robots
    Academic And Social Part-Time:
    IEEE Senior Member ACM Member; Secretary-General of Document Image Analysis and Recognition Committee of Chinese Society of Image and Graphics
  • Resume

    1995.09-2002.06 Beijing University of Science and Technology Bachelor, Master

    2002.07 – 2006.07 Hanwang Technology Co., Ltd. R & D Center R & D Engineer / Technical Manager

    2003.09-2006.07 Ph.D., Institute of Automation, Chinese Academy of Sciences

    2006.08-2008.06 Researcher, Information Technology Department, Fujitsu Research and Development Center

    2008.07-Today, engaged in teaching and scientific research in the Computer Department of Beijing University of Science and Technology

    2013.01-2014.01 Center for Intelligent Information Retrieval, School of Computer Science, University of Massachusetts Amherst, USA, Visiting Associate Professor

    2014.07 – 2014.08 Computer Vision Lab, School of Computer Science, University of MassachusettsAmherst, USA, Visiting Professor

    2016.07-2016.09 BioNLP Lab, Department of Quantitative Health Sciences, University of Massachusetts Medical School, USA, Visiting Professor

    For details, please refer to the laboratory (pattern recognition and artificial intelligence technology innovation laboratory) homepage (http://prir.ustb.edu.cn) and personal homepage (http://prir.ustb.edu.cn/yin/)

     

  • Representative Papers

    [J1] Xu-Cheng Yin (殷绪成), Xuwang Yin, Kaizhu Huang, and Hong-Wei Hao, Robust text detection in natural scene images, IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), vol. 36, no. 5, pp. 970-983, 2014. (SCI: 9.445)

    [J2] Xu-Cheng Yin (殷绪成), Wei-Yi Pei, Jun Zhang, and Hong-Wei Hao, Multi-orientation scene text detection with adaptive clustering, IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), vol. 37, no. 9, pp. 1930-1937, 2015. (SCI: 9.445)

    [J3] Shu Tian, Xu-Cheng Yin, Ya Su, and Hong-Wei Hao, “"A unified framework for tracking based text detection and recognition from web videos,” IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), vol. 37, no. 9, pp. 1930-1937, 2018. (SCI: 9.445)

    [J4] Xu-Cheng Yin (殷绪成), Ze-Yu Zuo, Shu Tian, and Cheng-Lin Liu, Text detection, tracking and recognition in video: A comprehensive survey, IEEE Trans. Image Processing (TIP), vol. 25, no. 6, pp. 2752-2773, 2016. (SCI: 3.735)

    [J5] Chun Yang, Xu-Cheng Yin* (殷绪成), Wei-Yi Pei, Shu Tian, Ze-Yu Zuo, Chao Zhu and Junchi Yan, Tracking based multi-orientation scene text detection: A unified framework with dynamic programming, IEEE Trans. Image Processing (TIP), published online, 2017. (SCI: 3.735)

    [J6] Xu-Cheng Yin (殷绪成), Kaizhu Huang, Chun Yang, and Hong-Wei Hao,  Convex ensemble learning with sparsity and diversity, Information Fusion, vol. 20, pp. 49-59, 2014. (SCI: 4.353)

    [J7] Ya Su, Xinbo Gao, and Xu-Cheng Yin (殷绪成), Fast alignment for sparse representation based face recognition, Pattern Recognition, vol. 68, pp. 211-221, 2017. (SCI: 3.399)

    [J8] Bo-Wen Zhang, Xu-Cheng Yin* (殷绪成), and Fang Zhou, A generic pseudo relevance feedback framework with heterogeneous social information, Information Sciences, vol. 367-368, pp. 909-926, 2016. (SCI: 3.364)

    [J9] Xu-Cheng Yin (殷绪成), Bo-Wen Zhang, Xiao-Ping Cui, Jiao Qu, Bin Geng, Fang Zhou, Li Song, and Hong-Wei Hao, IsART: A generic framework for searching books with social information, PLoS ONE, vol. 11, no. 2, pp. e0148479, 2016. (SCI: 3.057)

    [J10] Xu-Cheng Yin (殷绪成), Chun Yang, Wei-Yi Pei, Haixia Man, Jun Zhang, Erik Learned-Miller, and Hong Yu, DeTEXT: A database for evaluating text extraction from biomedical literature figures, PLoS ONE, vol. 10, no. 5, pp. e0126200, 2015. (SCI: 3.057)


    [C1] Shu Tian, Wei-Yi Pei, Ze-Yu Zuo, and Xu-Cheng Yin* (殷绪成), Scene text detection in video by learning locally and globally, Proceedings of 25th International Joint Conference on Artificial Intelligence (IJCAI16), 2016. (CCF A)

    [C2] Bo-Wen Zhang, Xu-Cheng Yin* (殷绪成), Fang Zhou, and Jianlin Jin, Building your own reading list anytime via embedding relevance, quality, timeliness and diversity, Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval (ACM SIGIR’17), 2017. (CCF A)

    [C3] Xu-Cheng Yin (殷绪成), Xuwang Yin, Kaizhu Huang, and Hong-Wei Hao, Accurate and robust text detection: a step-in for text retrieval in natural scene images, Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval (ACM SIGIR’13), 2013. (CCF A)

    [C4] Bo-Wen Zhang, Xu-Cheng Yin* (殷绪成), Xiao-Ping Cui, Jiao Qu, Bin Geng, Fang Zhou, Li Song, and Hong-Wei Hao, Social book search reranking with generalized content-based filtering, Proceedings of the 21st International ACM Conference on Information and Knowledge Management (ACM CIKM’14), 2014. (CCF B)

    [C5] Junchi Yan, Xu-Cheng Yin (殷绪成), Weiyao Lin, Cheng Deng, Hongyuan Zha, and Xiaokang Yang, A short survey of recent advances in graph matching, Proceedings of ACM International Conference on Multimedia Retrieval (ACM ICMR16), 2016. (CCF B)

    [C6] Ze-Yu Zuo, Shu Tian, Wei-Yi Pei, and Xu-Cheng Yin* (殷绪成), Multi-strategy tracking based text detection in scene videos, Proceedings of 13th International Conference on Document Analysis and Recognition (ICDAR'15), 2015. (CCF C)

    [C7] Yan Yan, Xu-Cheng Yin* (殷绪成), Hong-Wei Hao, etc., Sorting-based dynamic classifier ensemble selection, Proceedings of 12th International Conference on Document Analysis and Recognition (ICDAR'13), 2013. (CCF C)

    [C8] Xu-Cheng Yin (殷绪成), Hong-Wei Hao, Jun Sun, and Satoshi Naoi, Robust vanishing point detection for MobileCam-based documents, Proceedings of 11th International Conference on Document Analysis and Recognition (ICDAR'11), 2011. (CCF C)

    [C9] Xu-Cheng Yin (殷绪成), Hong-Wei Hao, Jun Sun, and Satoshi Naoi, Rejection strategies with multiple classifiers for handwritten character recognition, Proceedings of 10th International Conference on Document Analysis and Recognition (ICDAR'09), 2009. (CCF C)

    [C10] Xu-Cheng Yin (殷绪成), Jun Sun, Katsuhito Fujimoto, Yusaku Fujii, Koji Kurokawa, Hiroaki Takebe, and Satoshi Naoi, A multi-stage strategy to perspective rectification for mobile phone camera-based document images, Proceedings of 9th International Conference on Document Analysis and Recognition (ICDAR'07), 2007. (CCF C)

     

  • Research Performance

    Horizontal projects:

    (1) "Study on the Detection and Recognition of Text in Online Scenes / Online Advertising Pictures" (2016 ~ 2019, Tencent Technology Cooperation Project, person in charge)

    (2) "Analysis and Recognition Technology of Complex English Documents in the Education Industry" (2014 ~ 2015, Cooperative Project of Xunfei Research Institute of HKUST, principal)

    (3) "Natural scene text detection engine and application technology" (2014, Samsung Electronics China Research Institute cooperation project, person in charge)

    Vertical projects:

    (1) "Natural scene text recognition technology combining feedforward and feedback mechanism" (2015 ~ 2018, National Natural Science Foundation of China, person in charge)

    (2) "Extraction of a large number of complex document image information based on probability graph model" (2012 ~ 2014, National Natural Science Foundation of China, person in charge)

     

  • Get Rewards/Patents

    2018 Appraisal of the scientific and technological achievements of the Chinese Society of Image and Graphics: "Text recognition technology and application of large-scale network images" (the overall international advanced, text detection technology is internationally leading)

    Champion of "Challenge on COCO-Text" in the 2017 International Document Analysis and Recognition Conference Technical Competition;

    The 2015 International Document Analysis and Recognition Conference Technical Competition "Natural Scene Text End-to-End Recognition", "Network Picture Text End-to-End Recognition" and "Video Text Detection and Extraction" four champions

    Three winners of the 2013 International Document Analysis and Recognition Conference Technology Contest "Natural Scene Text Detection", "Network Picture Text Detection" and "Network Picture Text Extraction";

    2015, 2016, 2017 International Biomedical Semantic Retrieval and Question Answering Technology Challenge Platform BioASQ Challenge Biomedical Semantic AQ multiple task evaluation first;

     

    Ranked first in the "Social Book Search Suggestion Task" task of CLEF international information retrieval technology evaluation in 2014 and 2016;

    First Prize of Beijing Science and Technology Progress Award in 2005;

    2006 Fujitsu Research and Development Center Excellent Invention Award;

    2006 Fujitsu Research Institute President Award;

    2007 Fujitsu Research Institute President Award