Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Pedestrian Detection in Crowded Scenes
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Movie/Script: Alignment and Parsing of Video and Text Transcription
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part IV
Data Mining and Knowledge Discovery
Hi-index | 0.00 |
Continuity errors occur in many movies and television series, in spite of careful checking by those employed to minimise them. In this work we develop a scheme for automatically detecting these errors and producing a ranked list of the most likely inconsistencies, working from a commercial DVD release. We use the editing structure of the movie to detect pairs of shots within a scene that might have arisen from different takes, and thus are possible candidates for continuity errors. These pairs are then registered and examined for differences that lack an obvious cause -- suppressing changes arising from humans and other moving objects by using upper body detectors and trackers. The result is a ranked list of possible continuity errors for the movie. We show discovered errors for a number of feature length movies including relatively recent releases, such as 'Love Actually' (Curtis, 2003) and classics, such as 'Pretty Woman' (Marshall, 1990). We discover mistakes that have previously been missed in the listings for these movies on such websites as moviemistakes.com.