Abstract | ||
---|---|---|
We introduce and address the problem of video object cosegmentation, which concerns the task of segmenting the common object in a pair of video sequences. We present a new algorithm that works on super-voxels in videos to solve this task. The algorithm computes i the intra-video relative motion derived from dense optical flow and ii) the inter-video co-features based on Gaussian mixture models. The experimental results show that, by integrating the intra-video and inter-video information, our algorithm is able to obtain better results of segmenting video objects. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2393347.2396317 | ACM Multimedia 2001 |
Keywords | Field | DocType |
video object cosegmentation,gaussian mixture model,video object,better result,common object,inter-video information,new algorithm,dense optical flow,intra-video relative motion,video sequence,gmm,motion,graph cut,video | Cut,Computer vision,Block-matching algorithm,Pattern recognition,Computer science,Relative motion,Video tracking,Artificial intelligence,Optical flow,Mixture model | Conference |
Citations | PageRank | References |
12 | 0.67 | 17 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ding-Jie Chen | 1 | 31 | 6.70 |
Hwann-Tzong Chen | 2 | 826 | 52.13 |
Long-Wen Chang | 3 | 532 | 51.82 |