Abstract
We show how to create a music video automatically, using computable characteristics of the video and music to promote coherent matching. We analyze the flow of both music and video, and then segment them into sequences of near-uniform flow. We extract features from the both video and music segments, and then find matching pairs. The granularity of the matching process can be adapted by extending the segmentation process to several levels. Our approach drastically reduces the skill required to make simple music videos.
| Original language | English |
|---|---|
| Pages (from-to) | 197-214 |
| Number of pages | 18 |
| Journal | Multimedia Tools and Applications |
| Volume | 41 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 2009 Jan 1 |
All Science Journal Classification (ASJC) codes
- Software
- Media Technology
- Hardware and Architecture
- Computer Networks and Communications
Cite this
}
Automated music video generation using multi-level feature-based segmentation. / Yoon, Jong Chul; Lee, In Kwon; Byun, Siwoo.
In: Multimedia Tools and Applications, Vol. 41, No. 2, 01.01.2009, p. 197-214.Research output: Contribution to journal › Article
TY - JOUR
T1 - Automated music video generation using multi-level feature-based segmentation
AU - Yoon, Jong Chul
AU - Lee, In Kwon
AU - Byun, Siwoo
PY - 2009/1/1
Y1 - 2009/1/1
N2 - We show how to create a music video automatically, using computable characteristics of the video and music to promote coherent matching. We analyze the flow of both music and video, and then segment them into sequences of near-uniform flow. We extract features from the both video and music segments, and then find matching pairs. The granularity of the matching process can be adapted by extending the segmentation process to several levels. Our approach drastically reduces the skill required to make simple music videos.
AB - We show how to create a music video automatically, using computable characteristics of the video and music to promote coherent matching. We analyze the flow of both music and video, and then segment them into sequences of near-uniform flow. We extract features from the both video and music segments, and then find matching pairs. The granularity of the matching process can be adapted by extending the segmentation process to several levels. Our approach drastically reduces the skill required to make simple music videos.
UR - http://www.scopus.com/inward/record.url?scp=59849099844&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=59849099844&partnerID=8YFLogxK
U2 - 10.1007/s11042-008-0225-0
DO - 10.1007/s11042-008-0225-0
M3 - Article
AN - SCOPUS:59849099844
VL - 41
SP - 197
EP - 214
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
SN - 1380-7501
IS - 2
ER -