Compared to other approaches that analyze object trajectories, we propose to detect anomalous video events at three levels considering spatiotemporal context of video objects, i.e...
Fan Jiang, Junsong Yuan, Sotirios A. Tsaftaris, Ag...
We present a novel framework for multiple object tracking in which the problems of object detection and data association are expressed by a single objective function. The framewor...
Zheng Wu, Ashwin Thangali, Stan Sclaroff, Margrit ...
Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
Different from familiar clustering objects, text documents have sparse data spaces. A common way of representing a document is as a bag of its component words, but the semantic re...
: Feature point FP detection is an important pre-processing step in image registration, data fusion, object recognition and in many other tasks. This paper deals with multiframe FP...