Abstract. Human gait is an attractive modality for recognizing people at a distance. In this paper we adopt an appearance-basedapproach to the problem of gait recognition. The widt...
Amit A. Kale, Naresh P. Cuntoor, B. Yegnanarayana,...
We propose a method to visually summarize collections of networks on which a clustering of the vertices is given. Our method allows for efficient comparison of individual networks...
Applying personal keywords to images and video clips makes it possible to organize and retrieve them, as well as automatically create thematically related slideshows. MediaBrowser...
Steven M. Drucker, Curtis Wong, Asta Roseway, Stev...
This poster describes methods to enable intelligent access to multimodal information streams. We illustrate these methods in two integrated systems: the Broadcast News Editor (BNE...
Multiple-instance learning is a variation on supervised learning, where the task is to learn a concept given positive and negative bags of instances. Each bag may contain many ins...