A user-centered approach to rushes summarisation via highlight-detected keyframes

Authors:
Daragh Byrne;Peter Kehoe;Hyowon Lee;Ciarán Ó. Conaire;Alan F. Smeaton;Noel E. O'Connor;Gareth J.F. Jones
Affiliations:
Dublin City University, Dublin, Ireland;Dublin City University, Dublin, Ireland;Dublin City University, Dublin, Ireland;Dublin City University, Dublin, Ireland;Dublin City University, Dublin, Ireland;Dublin City University, Dublin, Ireland;Dublin City University, Dublin, Ireland
Venue:
Proceedings of the international workshop on TRECVID video summarization
Year:
2007

Citing 4
Cited 5

Issues in vision modeling for perceptual video quality assessment

Signal Processing
Extensible MPEG-4 textual format (XMT)

MULTIMEDIA '00 Proceedings of the 2000 ACM workshops on Multimedia
The trecvid 2007 BBC rushes summarization evaluation pilot

Proceedings of the international workshop on TRECVID video summarization
A Bayesian discriminating features method for face detection

IEEE Transactions on Pattern Analysis and Machine Intelligence

Dimensionality reduction for heterogeneous dataset in rushes editing

Pattern Recognition
Video rushes summarization utilizing retake characteristics

TVS '08 Proceedings of the 2nd ACM TRECVid Video Summarization Workshop
Automatic Summarization of Rushes Video Using Bipartite Graphs

SAMT '08 Proceedings of the 3rd International Conference on Semantic and Digital Media Technologies: Semantic Multimedia
A framework for video abstraction systems analysis and modelling from an operational point of view

Multimedia Tools and Applications
Automatic summarization of rushes video using bipartite graphs

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present our keyframe-based summary approach for BBC Rushes video as part of the TRECVid Summarisation benchmark evaluation carried out in 2007. We outline our approach to summarisation that uses video processing for feature extraction and is informed by human factors considerations for summary presentation. Based on the performance of our generated summaries as reported by NIST, we subsequently undertook detailed failure analysis of our approach. The findings of this investigation as well as recommendations for alterations to our keyframe-based summary generation method, and the evaluation methodology for Rushes summaries in general, are detailed within this paper.