143 search results - page 17 / 29 » Localizing and segmenting text in images and videos |
ECCV
2006
Springer
15 years 1 months ago
2006
Springer
We present a novel method for the detection of motion boundaries in a video sequence based on differential properties of the spatio-temporal domain. Regarding the video sequence as...
JMIV
2006
14 years 9 months ago
2006
In this paper, we propose to focus on the segmentation of vectorial features (e.g. vector fields or color intensity) using region-based active contours. We search for a domain that...
CVPR
2008
IEEE
15 years 11 months ago
2008
IEEE
Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
TCSV
2008
14 years 9 months ago
2008
This paper presents a bottom-up approach that combines audio and video to simultaneously locate individual speakers in the video (2-D source localization) and segment their speech ...
ICPR
2002
IEEE
15 years 10 months ago
2002
IEEE
This paper describes an approach for video structuring and indexing. It relies on motion wavelet coefficients directly estimated from image sequence. These coefficients provide a ...