798 search results - page 83 / 160 » Learning to compress images and videos |
146
click to vote
Publication
We present an online learning approach for robustly combining unreliable
observations from a pedestrian detector to estimate the rough 3D scene geometry
from video sequences of a...
109
click to vote
IJCV
2008
15 years 1 months ago
2008
We present an unsupervised approach for learning a generative layered representation of a scene from a video for motion segmentation. The learnt model is a composition of layers, ...
114
click to vote
WIAMIS
2009
IEEE
15 years 8 months ago
2009
IEEE
Spatio-temporal interest region detectors can be used in the analysis of video to determine sparse, informative regions as candidates for feature extraction. In this paper we comp...
101
click to vote
ICIP
2003
IEEE
16 years 3 months ago
2003
IEEE
Video coding algorithms based on 3-D wavelet transforms exist which have a competitive rate-distortion performance and are very fast because motion compensation is not needed. The...
102
click to vote
ICIP
2002
IEEE
16 years 3 months ago
2002
IEEE
We present a new content-based approach to summarize instructional videos. We first redefine "scene" in instructional videos. Focusing on one dominant scene type, that o...