Yuxiang Xie

  • Citations Per Year
Learn More
The long term evolution of UMTS, UTRA LTE, can facilitate high user data rates using OFDMA combined with MIMO (multiple input multiple output) techniques. In this paper, we focus on the uplink virtual MIMO capacity and its pairing algorithms. In the uplink for LTE, the power and complexity for the terminal circuit design is critical, so LTE using a(More)
Local image feature description is a basic research in the field of computer vision and it is also a hotspot in the community. The paper depicts the development history of local feature description in decades. Then based on the strategy of feature pooling, it classifies feature description methods into three types: histogram based method, feature comparison(More)
Automatic image scene detection is a crucial step for various tasks in computer vision. Current scene detection methods are often computationally expensive for use in real-time image classification. In this paper, a novel and efficient scene detection method based on local invariant features is presented. First, the SIFT feature detector and descriptor has(More)
Cartoon image annotation and retrieval is critical for cartoonists to effectively and efficiently make cartoons by reusing existing cartoon data. To successfully achieve these tasks, it is essential to build an abundant cartoon database first and then annotate and retrieve them efficiently. This paper studies and realizes a cartoon images annotation and(More)
A multi-level structure of video contents is introduced and a novel mechanism of hierarchically indexing sports video using multi-modal cues is proposed. Firstly, video is indexed with information from video and audio individually. Video is segmented into physical shots based on visual features, and then identified as syntactic shots on the middle level(More)
BACKGROUND The capacity of electronic health record (EHR) data to guide targeted surveillance in chronic kidney disease (CKD) is unclear. We sought to leverage EHR data for predicting risk of progressing from CKD to end-stage renal disease (ESRD) to help inform surveillance of CKD among vulnerable patients from the healthcare safety-net. METHODS We(More)
Automatic movie summarization based on the visual-audio features is introduced. The importance evaluation model for video clips chooses face detection and atwitter shot detection as the basis. Against the difficult of movie's speech endpoint detection, speech endpoint detection based on subtitles of movie is introduced, which can help detect the captions'(More)
Video summary is important for users to quickly understand the video content. In this paper, first, some selection principles of video content and an importance evaluation model of movie summary are analyzed. Then, a movie summary generation system which includes three subsystems such as video management and retrieval subsystem, video clips selection(More)