Learn More
—Coclustering heterogeneous data has attracted extensive attention recently due to its high impact on various important applications, such us text mining, image retrieval, and bioinformatics. However, data coclustering without any prior knowledge or background information is still a challenging problem. In this paper, we propose a Semisupervised(More)
Existing saliency detection methods are mainly formulated as computational models in a bottom-up fashion with either a local or a global view. Local methods [2, 3], which compute center-surround differences in a local context to capture the regions locally standing out from their surroundings, often lack global information and tend to highlight the(More)
In most cases authors are permitted to post their version of the article (e.g. in Word or Tex form) to their personal website or institutional repository. Authors requiring further information regarding Elsevier's archiving and manuscript policies are encouraged to visit: Keywords: Stability analysis Multiple-bottleneck networks AIMD/RED system Lyapunov(More)
We propose a new approach for general object tracking with fully convolutional neural network. Instead of treating convolutional neural network (CNN) as a black-box feature extractor, we conduct in-depth study on the properties of C-NN features offline pre-trained on massive image data and classification task on ImageNet. The discoveries motivate the design(More)
This paper details Cengage Learning's submissions for this year's TREC medical track. The techniques we used fall roughly into two categories: information extraction and query expansion. From both the queries and the medical reports, we extracted limiting attributes, such as age, race, and gender, and labeled terms appearing in the Unified Medical Language(More)
In most cases authors are permitted to post their version of the article (e.g. in Word or Tex form) to their personal website or institutional repository. Authors requiring further information regarding Elsevier's archiving and manuscript policies are encouraged to visit: Abstract In this paper, we systematically study the stability of a class of(More)
—Service-Oriented Architecture (SOA) introduces a new paradigm where data, service, and the service composition logic are decoupled in an open environment. Software systems are built and evolved online by dynamic discovering and binding to the open services accessible through standard protocols. It requires new reliability modeling techniques to facilitate(More)
Spectral clustering is a well-known graph-theoretic approach of finding natural groupings in a given dataset, and has been broadly used in image segmentation. Nowadays, High-Definition (HD) images are widely used in television broadcasting and movies. Segmenting these high resolution images presents a grand challenge to the current spectral clustering(More)
Colorectal cancer (CRC) is deadly if not found early. Any protocols developed for screening and surveillance and any policy decisions regarding the availability of CRC resources should consider the nature of the disease and its impact over time on costs and quality-adjusted life years in a population. Simulation models can provide a flexible representation(More)