|
Creating Summaries from User Videos*
Michael Gygli1, 2, Helmut Grabner1, 2, Hayko Riemenschneider1, and Luc Van Gool1, 3
1Computer Vision Laboratory, ETH Zurich, Switzerland
gygli@vision.ee.ethz.ch
2upicto GmbH, Zurich, Switzerland
3K.U. Leuven, Belgium
Abstract. This paper proposes a novel approach and a new benchmark for video summarization. Thereby we focus on user videos, which are raw videos containing a set of interesting events. Our method starts by segmenting the video by using a novel “superframe” segmentation, tailored to raw videos. Then, we estimate visual interestingness per superframe using a set of low-, mid- and high-level features. Based on this scoring, we select an optimal subset of superframes to create an informative and interesting summary. The introduced benchmark comes with multiple human created summaries, which were acquired in a controlled psychological experiment. This data paves the way to evaluate summarization methods objectively and to get new insights in video summarization. When evaluating our method, we find that it generates high-quality results, comparable to manual, human-created summaries.
Keywords: Video analysis, video summarization, temporal segmentation
Electronic Supplementary Material:
- Electronic Supplementary Material (MP4 7,642 KB)
- Electronic Supplementary Material (PDF 531 KB)
- Electronic Supplementary Material (AVI 953 KB)
- Electronic Supplementary Material (AVI 1,014 KB)
- Electronic Supplementary Material (AVI 602 KB)
- Electronic Supplementary Material (AVI 594 KB)
- Electronic Supplementary Material (AVI 988 KB)
- Electronic Supplementary Material (AVI 910 KB)
- Electronic Supplementary Material (AVI 1,159 KB)
- Electronic Supplementary Material (AVI 1,920 KB)
- Electronic Supplementary Material (AVI 538 KB)
- Electronic Supplementary Material (AVI 1,203 KB)
- Electronic Supplementary Material (AVI 2,286 KB)
- Electronic Supplementary Material (AVI 315 KB)
- Electronic Supplementary Material (AVI 234 KB)
- Electronic Supplementary Material (AVI 597 KB)
- Electronic Supplementary Material (AVI 1,134 KB)
- Electronic Supplementary Material (AVI 1,766 KB)
- Electronic Supplementary Material (AVI 619 KB)
- Electronic Supplementary Material (AVI 509 KB)
- Electronic Supplementary Material (AVI 679 KB)
- Electronic Supplementary Material (AVI 1,388 KB)
- Electronic Supplementary Material (AVI 452 KB)
- Electronic Supplementary Material (AVI 470 KB)
- Electronic Supplementary Material (AVI 972 KB)
- Electronic Supplementary Material (AVI 2,081 KB)
- Electronic Supplementary Material (AVI 1,091 KB)
LNCS 8695, p. 505 ff. Full article in PDF | BibTeX
lncs@springer.com
© Springer International Publishing Switzerland 2014
|