Name
Abstract | ||
|---|---|---|
Video summary is an active research field to help users to grasp a whole video's content for efficient browsing and editing. In this paper, we describe our THU-Intel rushes summarization system in TRECVID2008. In our approach, we first extract low-level audiovisual features and parse the video into shots, sub-shots and 1-second video clips. Then we remove junk video clips with color-bar, near uniform-color and clapboard frames etc. To select video clips with main objects and events, we evaluate each clip's representative score by multimodal features of color, edge, motion, and audio etc. Finally, we construct the rushes video summary by iteratively selecting the most representative video clips and removing similar ones. Extensive experiments are carried out on 40 testing rushes videos. Good results demonstrate the effectiveness of the proposed method. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1145/1463563.1463586 | TVS |
Keywords | Field | DocType |
representative score,video summarization,ransac,camera motion estimation,junk clip removing,clapboard detection,indexation,factor analysis | Reference frame,Automatic summarization,Block-matching algorithm,Computer science,TRECVID,Search engine indexing,Speech recognition,Video tracking,Key frame,Video compression picture types | Conference |
Citations | PageRank | References |
5 | 0.48 | 23 |
Authors | ||
10 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tao Wang | 1 | 238 | 23.70 |
| Shangping Feng | 2 | 5 | 0.48 |
| Patricia P. Wang | 3 | 25 | 3.79 |
| Wei Hu | 4 | 182 | 14.17 |
| Shuang Zhang | 5 | 6 | 0.83 |
| Wei Zhang | 6 | 5 | 0.48 |
| Yangzhou Du | 7 | 169 | 13.85 |
| Jianguo Li | 8 | 377 | 35.38 |
| Jianmin Li | 9 | 731 | 68.51 |
| Yimin Zhang | 10 | 359 | 28.66 |