We investigate the challenging issue of joint audio-visual analysis of generic videos targeting at semantic concept detection. We propose to extract a novel representation, the Sh...
Wei Jiang, Courtenay V. Cotton, Shih-Fu Chang, Dan...
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
Abhinav Gupta, Trista Chen, Francine Chen, Don Kim...
In this paper we extend Active Monte Carlo Recognition (AMCR), a recently proposed framework for object recognition. The approach is based on the analogy between mobile robot loca...
In this paper, we report our experiments in the TREC 2008 Relevance Feedback Track. Our main goal is to study a novel problem in feedback, i.e., optimization of the balance of the...
Abstract. This paper presents an exemplar-based approach to detecting and localizing human actions, such as running, cycling, and swinging, in realistic videos with dynamic backgro...