There has been significant recent interest in sparse metric learning (SML) in which we simultaneously learn both a good distance metric and a low-dimensional representation. Unfor...
A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different predictio...
Abstract—The shifted delta cepstrum (SDC) is a widely used feature extraction for language recognition (LRE). With a high context width due to incorporation of multiple frames, S...
Weiqiang Zhang, Liang He, Yan Deng, Jia Liu, M. T....
Depending on network conditions, a communication network could be overloaded when media are transmitted. Research has been carried out to lessen network overloading, such as by fi...
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task a...