We propose a neural network based method for organizing images for content-based image retrieval. We use spectral histogram features, the histograms of filtered images to capture...
Near-duplicate keyframe retrieval is a critical task for video similarity measure, video threading and tracking. In this paper, instead of using expensive point-to-point matching ...
Automatic image annotation is a promising solution to enable more effective image retrieval by keywords. Traditionally, statistical models for image auto-annotation predicate each...
Yong Ge, Richang Hong, Zhiwei Gu, Rong Zhang, Xiuq...
This paper presents a new two-stage approach to impulse noise removal for color image. The first step is the impulse detection, in which the so-called Rank-Ordered Absolute Diffe...
This paper proposes a novel framework to index and retrieve audio content from broadcast database that contains both speech and music. In this framework, we model the acoustic eve...
The high performance of the conventional spatio-temporal image noise reduction filers comes at the cost of high computationally intensity. In this paper, a motion adaptive spatio-...
In this work, we investigate the routing problems ofminimizing the number ofdistinct transmission mediums or carrier domains for multimedia communications. We consider the problem...
Mismatch between training and testing data is a major error source for both Automatic Speech Recognition (ASR) and Automatic Speaker Identification (ASI). In this paper, we first ...
Xi Zhou, Yun Fu, Ming Liu, Mark Hasegawa-Johnson, ...
In this paper, the recognition of the visual focus of attention (VFOA) of meeting participants (as defined by their eye gaze direction) from their head pose is addressed. To this ...
Geometry-controlled image warping performs well in exhibiting shape variations but bad in exhibiting wrinkle such as fossette. Successfully applied in expression cloning, Expressi...