Abstract | ||
---|---|---|
A bag-of-regions (BoR) representation of a video sequence is a spatio-temporal tessellation for use in high-level applications such as video classifications and action recognitions. We obtain a BoR representation of a video sequence by extracting regions that exist in the majority of its frames and largely correspond to a single object. First, the significant regions are obtained using unsupervised frame segmentation based on the JSEG method. A tracking algorithm for splitting and merging the regions is then used to generate a relational graph of all regions in the segmented sequence. Finally, we perform a connectivity analysis on this graph to select the most significant regions, which are then used to create a high-level representation of the video sequence. We evaluated our representation using a SVM classifier for the video classification and achieved about 85 % average precision using the UCF50 dataset. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/s11042-015-2876-y | Multimedia Tools and Applications |
Keywords | Field | DocType |
Video segmentation,Region tracking,Bag-of-regions,Video classification | Graph,Computer vision,Block-matching algorithm,Pattern recognition,Segmentation,Computer science,Artificial intelligence,Tessellation,Svm classifier,Merge (version control) | Journal |
Volume | Issue | ISSN |
75 | 5 | 1380-7501 |
Citations | PageRank | References |
1 | 0.34 | 34 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Min-Kook Choi | 1 | 19 | 3.47 |
Ziyu Wang | 2 | 372 | 23.71 |
Hyun-Gyu Lee | 3 | 21 | 5.77 |
Sangchul Lee | 4 | 27 | 8.35 |