Qingli Ma

Learn More
The change of illumination problem is still a challenging and difficult problem in face recognition under complex illumination condition. There were many proposals that dealing with illumination problem in face recognition in the past decade. In this paper, we classify the existing methods into three main categories and introduce the representative(More)
Full-Batch update and mini-batch update are two most widely used algorithms in back-propagation(BP) neural network, to deal with the huge training time and computation cost in the learning process. Parallel computing can improve the computation efficiency and have implemented these two algorithms on Mapreduce framework. In this paper, we implement these two(More)
When and why people change their cell phones are important issues in mobile communications industry because it will impact greatly on the marketing strategy and revenue estimation for both telecommunication operators and manufactures. In this paper, we evaluate the key features that affect the mobile phone changing based on statistical data of mobile users(More)
University of Chinese Academy of Sciences (UCAS) participated in the first task, namely temporally-anchored ad hoc retrieval in Microblog track, aiming to efficiently and effectively retrieve tweets. Based on the conventional application of learning to rank, we incorporated a machine learning approach, such as logistic regression for selecting high-quality(More)
A model of web data gathering and processing on Tibetan and Uyghur language is introduced in this paper, including page crawler, content extraction, word segmentation and frequency statistics and display. Firstly, It extracts the website's templates and use the template to extract the content and title of the web page, then the software transforms the HTML(More)
  • 1