We address the problem of classifying scenes from feature films into semantic categories and propose a robust framework for this problem. We propose that the Finite State Machines ...
The structure of hypersurfaces corresponding to different spatio-temporal patterns is considered, and in particular representations based on geometrical invariants, such as the Ri...
Abstract. This paper extends the recovery of structure and motion to image sequences with several independently moving objects. The motion, structure, and camera calibration are al...
Abstract. This paper presents a new method for extracting semantic information from basketball video. Our approach consists of three stages: shot and scene boundary detection, scen...
Song Liu, Haoran Yi, Liang-Tien Chia, Deepu Rajan,...
Semantic search attempts to go beyond the current state of the art in information access by addressing information needs on the semantic level, i.e. considering the meaning of user...