Abstract | ||
---|---|---|
We develop a generative probabilistic model for temporally consistent super pixels in video sequences. In contrast to supermodel methods, object parts in different frames are tracked by the same temporal super pixel. We explicitly model flow between frames with a bilateral Gaussian process and use this information to propagate super pixels in an online fashion. We consider four novel metrics to quantify performance of a temporal super pixel representation and demonstrate superior performance when compared to supermodel methods. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CVPR.2013.267 | CVPR |
Keywords | Field | DocType |
Gaussian processes,image representation,image sequences,video signal processing,bilateral Gaussian process,generative probabilistic model,object parts,supervoxel methods,temporal superpixels,video representation,video sequences,oversegmentation,superpixels,supervoxels,tracking,video segmentation | Computer vision,Pattern recognition,Computer science,Image representation,Gaussian process,Pixel,Statistical model,Artificial intelligence,Generative grammar | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
78 | 1.59 | 25 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jason Chang | 1 | 133 | 6.75 |
Donglai Wei | 2 | 200 | 11.80 |
John W. Fisher III | 3 | 878 | 74.44 |