Scene segmentation in artistic archive documentaries

Authors:
Dalibor Mitrović;Stefan Hartlieb;Matthias Zeppelzauer;Maia Zaharieva
Affiliations:
Interactive Media Systems Group, Vienna University of Technology, Vienna, Austria;Interactive Media Systems Group, Vienna University of Technology, Vienna, Austria;Interactive Media Systems Group, Vienna University of Technology, Vienna, Austria;Interactive Media Systems Group, Vienna University of Technology, Vienna, Austria
Venue:
USAB'10 Proceedings of the 6th international conference on HCI in work and learning, life and leisure: workgroup human-computer interaction and usability engineering
Year:
2010

Citing 7
Cited 0

A feature-based algorithm for detecting and classifying scene breaks

Proceedings of the third ACM international conference on Multimedia
Segmentation of video by clustering and graph analysis

Computer Vision and Image Understanding
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A Shot Clustering Based Algorithm for Scene Segmentation

CISW '07 Proceedings of the 2007 International Conference on Computational Intelligence and Security Workshops
Systematic evaluation of logical story unit segmentation

IEEE Transactions on Multimedia
Detection and representation of scenes in videos

IEEE Transactions on Multimedia
Video scene segmentation using Markov chain Monte Carlo

IEEE Transactions on Multimedia

Quantified Score

Hi-index	0.01

Visualization

Abstract

Scene segmentation is a crucial task in the structural analysis of film. State-of-the-art scene segmentation algorithms usually target fiction films (e.g. Hollywood films). Documentaries (especially artistic archive documentaries) follow different montage rules than fiction films and consequently require specialized approaches for scene segmentation. We propose a scene segmentation algorithm targeted at artistic archive documentaries. We evaluate the performance of our technique with archive documentaries and contemporary movies and obtain satisfactory results in both domains.