Abstract | ||
---|---|---|
The ever increasing volume of video content has created profound challenges for developing efficient video summarization (VS) techniques to access the data. Recent developments on sparse dictionary selection have demonstrated promising results for VS, however, the convex relaxation based solution cannot ensure the sparsity of the dictionary directly and it selects keyframes in a local point of view. In this paper, an L2,0 constrained sparse dictionary selection model is proposed to reformulate the problem of VS. In addition, a simultaneous orthogonal matching pursuit (SOMP) based method is proposed to obtain an approximate solution for the proposed model without smoothing the penalty function, and thus selects keyframes in a global point of view. In order to allow for intuitive and flexible configuration of VS process, a percentage of residuals (POR) criterion is also developed to produce video summaries in different lengths. Experimental results demonstrate that our proposed method outperforms the state-of-the-art. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICME.2014.6890179 | ICME |
Keywords | DocType | Citations |
video signal processing,image matching,dictionary selection,0 constrained sparse dictionary selection model,video summarization,video content,keyframe extraction,convex programming,POR,SOMP,VS techniques,simultaneous orthogonal matching pursuit,convex relaxation,sparsity,percentage of residuals,L2,video summation | Conference | 1 |
PageRank | References | Authors |
0.35 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shaohui Mei | 1 | 198 | 21.09 |
Genliang Guan | 2 | 180 | 8.23 |
Zhiyong Wang | 3 | 550 | 51.76 |
Mingyi He | 4 | 378 | 31.66 |
Xian-Sheng Hua | 5 | 6566 | 328.17 |
David Dagan Feng | 6 | 3329 | 413.76 |