Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    A Multi-level Progressive Rectification Mechanism for Irregular Scene Text Recognition

    Rectifying irregular texts into regular ones is a promising approach for improving scene text recognition systems. However, most existing methods only perform rectification at the image level once. This may be...

    Qianying Liao, Qingxiang Lin, Lianwen ** in Document Analysis and Recognition – ICDAR … (2021)

  2. No Access

    Chapter and Conference Paper

    Improving Machine Understanding of Human Intent in Charts

    Charts composed of images and text are a classical and compact method of displaying and comparing various data. Automated data extraction from charts is critical in the machine understanding and recognition of...

    Sihang Wu, Canyu **e, Yuhao Huang in Document Analysis and Recognition – ICDAR … (2021)

  3. No Access

    Chapter and Conference Paper

    High Performance Offline Handwritten Chinese Text Recognition with a New Data Preprocessing and Augmentation Pipeline

    Offline handwritten text recognition (HCTR) has been a long-standing research topic. To build robust and high-performance offline HCTR systems, it is natural to develop data preprocessing and augmentation tech...

    Canyu **e, Songxuan Lai, Qianying Liao, Lianwen ** in Document Analysis Systems (2020)

  4. Article

    Open Access

    Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review

    The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. A class of deep convolutional n...

    Tomaso Poggio, Hrushikesh Mhaskar in International Journal of Automation and Co… (2017)