Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Structuring home video by snippet detection and pattern parsing
Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval
Using cross-media correlation for scene detection in travel videos
Proceedings of the ACM International Conference on Image and Video Retrieval
Aesthetics-based automatic home video skimming system
MMM'08 Proceedings of the 14th international conference on Advances in multimedia modeling
Finding structure in home videos by probabilistic hierarchical clustering
IEEE Transactions on Circuits and Systems for Video Technology
Optimization-based automated home video editing system
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
This paper presents how cross-media correlation facilitates summarization of photos and videos captured in journeys. Correlation between photos and videos comes from similar content captured in the same temporal order. We transform photos and videos into sequences of visual word histograms, and adopt approximate sequence matching to find correlation. To summarize photos and videos, we propose that the characteristics of correlated photos can be utilized in selecting important video segments into video summaries, and on the other hand, the characteristics of correlated video segments can be utilized in selecting important photos. Experimental results demonstrate that the proposed summarization methods well take advantage of the correlation.