Browsing by Author "Li, Xuelong"

UTSePress Research/Manakin Repository

Search UTSePress Research

Browse

My Account

Browsing by Author "Li, Xuelong"

Sort by: Order: Results:

  • Tao, Dacheng; Tang, Xiaoou; Li, Xuelong; Wu, Xindong (IEEE Computer Soc, 2006)
    Relevance feedback schemes based on support vector machines (SVM) have been widely used in content-based image retrieval (CBIR). However, the performance of SVM-based relevance feedback is often poor when the number of ...
  • Gao, Xinbo; Fu, Rong; Li, Xuelong; Tao, Dacheng; Zhang, Beichen; Yang, Huigen (Academic Press Inc Elsevier Science, 2011)
    The proportion of aurora to the field-of-view in temporal series of all-sky images is an important index to investigate the evolvement of aurora. To obtain such an index, a crucial phase is to segment the aurora from the ...
  • Li, Na; Chen, Chun; Wang, Qiang; Song, Mingli; Tao, Dacheng; Li, Xuelong (Elsevier Science Bv, 2008)
    With the popularity of cameras and rapid development of computer vision technology, vision-based HCI is attracting extensive interests. In this paper, we present a system for controlling avatars by natural body movement ...
  • Tao, Dacheng; Song, Mingli; Li, Xuelong; Shen, Jialie; Sun, Jimeng; Wu, Xindong; Faloutsos, Christos; Maybank, Stephen (IEEE-Inst Electrical Electronics Engineers Inc, 2008)
    Effectively modeling a collection of three-dimensional (3-D) faces is an important task in various applications, especially facial expression-driven ones, e.g., expression generation, retargeting, and synthesis. These 3-D ...
  • Yuan, Yuan; Li, Xuelong; Pang, Yanwei; Lu, Xin; Tao, Dacheng (IEEE-Inst Electrical Electronics Engineers Inc, 2009)
    This paper presents a fast part-based subspace selection algorithm, termed the binary sparse nonnegative matrix factorization (B-SNMF). Both the training process and the testing process of B-SNMF are much faster than those ...
  • Pang, Yanwei; Tao, Dacheng; Yuan, Yuan; Li, Xuelong (IEEE-Inst Electrical Electronics Engineers Inc, 2008)
    Fast training and testing procedures are crucial in biometrics recognition research. Conventional algorithms, e.g., principal component, analysis (PCA), fail to efficiently work on large-scale and high-resolution image ...
  • Huang, Kaiqi; Tao, Dacheng; Yuan, Yuan; Li, Xuelong; Tan, Tieniu (IEEE-Inst Electrical Electronics Engineers Inc, 2011)
    Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly ...
  • Mu, Yang; Tao, Dacheng; Li, Xuelong; Murtagh, Fionn (Springer, 2009)
    According to the research results reported in the past decades, it is well acknowledged that face recognition is not a trivial task. With the development of electronic devices, we are gradually revealing the secret of ...
  • Xiao, Bing; Gao, Xinbo; Tao, Dacheng; Li, Xuelong (Elsevier Sci Ltd, 2013)
    Face recognition is one of the biometric identification methods with the highest potential. The existing face recognition algorithms relying on the texture information of face images are affected greatly by the variation ...
  • Yan, Jq; Tao, Dacheng; Tian, Cn; Gao, Xinbo; Li, Xuelong (IEEE, 2010)
    Text detection and recognition for images in multimedia messaging service is a very important task. Since Chinese characters are composed of four kinds of strokes, i.e., horizontal line, top-down vertical line, left-downward ...
  • He, Lihuo; Wang, Dongxue; Li, Xuelong; Tao, Dacheng; Gao, Xinbo; Fei, Gao (Springer, 2012)
    Developing reduced reference image quality assessment (RR-IQA) plays a vital role in dealing with the prediction of the visual quality of distorted images. However, most of existing methods fail to take color information ...
  • Song, Mingli; Tao, Dacheng; Chen, Chun; Li, Xuelong; Chen, Chang Wen (IEEE Computer Soc, 2010)
    Both commercial and scientific applications often need to transform color images into gray-scale images, e. g., to reduce the publication cost in printing color images or to help color blind people see visual cues of color ...
  • Gao, Xinbo; Xiao, Bing; Tao, Dacheng; Li, Xuelong (Springer, 2009)
    Graph edit distance (GED) is widely applied to similarity measurement of graphs in inexact graph matching. Due to the difficulty of defining cost functions reasonably, we do research oil two GED algorithms without cost ...
  • Deng, Cheng; Gao, Xinbo; Tao, Dacheng; Li, Xuelong (IEEE, 2007)
    In this paper, we present a robust approach of digital watermarking embedding and retrieval for digital images. This new approach works in special domain and it has two major steps: (1) to extract affine co-variant regions, ...
  • Tao, Dacheng; Tang, Xiaoou; Li, Xuelong; Rui, Yong (IEEE-Inst Electrical Electronics Engineers Inc, 2006)
    In recent years, a variety of relevance feedback (RF) schemes have been developed to improve the performance of content-based image retrieval (CBIR). Given user feedback information, the key to a RF scheme is how to select ...
  • Gao, Xinbo; Yang, Yimin; Tao, Dacheng; Li, Xuelong (Academic Press Inc Elsevier Science, 2009)
    This paper presents a novel framework for effective video semantic analysis. This framework has two major components, namely, optical flow tensor (OFF) and hidden Markov models (HMMs). OFT and HMMs are employed because: ...
  • Zhang, Tianhao; Huang, Kaiqi; Li, Xuelong; Yang, Jie; Tao, Dacheng (IEEE-Inst Electrical Electronics Engineers Inc, 2010)
    Orthogonal neighborhood-preserving projection (ONPP) is a recently developed orthogonal linear algorithm for overcoming the out-of-sample problem existing in the well-known manifold learning algorithm, i.e., locally linear ...
  • Wang, Ying; Gao, Xinbo; Li, Xuelong; Tao, Dacheng; Wang, Bing (Springer-Verlag Berlin, 2009)
    Mass boundary segmentation plays an important role in computer aided diagnosis (CAD) system. Since the shape and boundary are crucial discriminant features in CAD, the active contour methods are more competitive in mass ...
  • Huang, Yz; Huang, Kaiqi; Wang, Ls; Tao, Dacheng; Tan, Tieniu; Li, Xuelong (IEEE, 2008)
    It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challenging databases. However, BIM has the following ...
  • Pang, Yanwei; Li, Xuelong; Yuan, Yuan; Tao, Dacheng; Pan, Jing (IEEE-Inst Electrical Electronics Engineers Inc, 2009)
    Subspace learning is the process of finding a proper feature subspace and then projecting high-dimensional data onto the learned low-dimensional subspace. The projection operation requires many floating-point multiplications ...