Shot classification using domain specific features for movie management

Authors:
Muhammad Abul Hasan;Min Xu;Xiangjian He;Ling Chen
Affiliations:
Centre for Innovation in IT Services and Applications (iNEXT), University of Technology, Sydney, NSW, Australia;Centre for Innovation in IT Services and Applications (iNEXT), University of Technology, Sydney, NSW, Australia;Centre for Innovation in IT Services and Applications (iNEXT), University of Technology, Sydney, NSW, Australia;Centre for Quantum Computation and Intelligent Systems (QCIS), University of Technology, Sydney, NSW, Australia
Venue:
DASFAA'12 Proceedings of the 17th international conference on Database Systems for Advanced Applications - Volume Part II
Year:
2012

Citing 2
Cited 0

Vector Boosting for Rotation Invariant Multi-View Face Detection

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Context saliency based image summarization

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo

Quantified Score

Hi-index	0.00

Visualization

Abstract

Among many video types, movie content indexing and retrieval is a significantly challenging task because of the wide variety of shooting techniques and the broad range of genres. A movie consists of a series of video shots. Managing a movie at shot level provides a feasible way for movie understanding and summarization. Consequently, an effective shot classification is greatly desired for advanced movie management. In this demo, we explore novel domain specific features for effective shot classification. Experimental results show that the proposed method classifies movie shots from wide range of movie genres with improved accuracy compared to existing work.