Breakout Session Report: Spatiotemporal Grouping

Boyer, Kim L.; Fagerström, Daniel; Kubovy, Michael; Johansen, Peter; Sarkar, Sudeep

doi:10.1007/978-1-4615-4413-5_4

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The successes of pairwise grouping have been slow to carry over to the case of spatiotemporal data. 4 Indeed, the conclusions of a recent panel discussion on spatiotemporal grouping [8] are that approaches in which the image sequence is treated as a multidimensional volume in x; y; t 4. Some preliminary steps in this direction were made by [29].…”

Section: Spatio-temporal Segmentationmentioning

confidence: 99%

Spectral grouping using the nystrom method

Fowlkes

Belongie

Chung

et al. 2004

IEEE Trans. Pattern Anal. Machine Intell.

1,155

857

View full text Add to dashboard Cite

Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation. However, due to the computational demands of these approaches, applications to large problems such as spatiotemporal data and high resolution imagery have been slow to appear. The contribution of this paper is a method that substantially reduces the computational requirements of grouping algorithms based on spectral partitioning making it feasible to apply them to very large grouping problems. Our approach is based on a technique for the numerical solution of eigenfunction problems known as the Nyström method. This method allows one to extrapolate the complete grouping solution using only a small number of samples. In doing so, we leverage the fact that there are far fewer coherent groups in a scene than pixels.

show abstract

Section: Spatio-temporal Segmentationmentioning

confidence: 99%

Spectral grouping using the nystrom method

Fowlkes

Belongie

Chung

et al. 2004

IEEE Trans. Pattern Anal. Machine Intell.

1,155

857

View full text Add to dashboard Cite

show abstract

“…Unfortunately such successes have been slow to carry over to the case of spatiotemporal data. * Indeed, the conclusions of a recent panel discussion on spatiotemporal grouping [5] are that approaches in which the image sequence is treated as a multidimensional volume in 2, y, t hold the greatest promise, but that efforts along these lines have been hampered largely by computational demands. The contribution of this paper is aimed directly at ameliorating this computational burden, thus making it feasible to extend the ideas of powerful pairwise grouping methods to the domain of video.…”

Section: Introductionmentioning

confidence: 99%

Efficient spatiotemporal grouping using the Nystrom method

Fowlkes

Belongie

Malik

Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001

View full text Add to dashboard Cite

Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation, but due to the computational demands, applications of such methods to spatiotemporal data have been slow to appear. For even a short video sequence, the set of all pairwise voxel similarities is a huge quantity of data: one second of a 256 x 384 sequence captured at 3oHz entails on the order of 1013 pairwise similarities. The contribution of this paper is a method that substantially reduces the computational requirements of grouping algorithms based on spectral partitioning, making it feasible to apply them to very large spatiotemporal grouping problems. Our approach is based on a technique for the numerical solution of eigenfunction prob-lems known as the Nystrom method. This method allows extrapolation of the complete grouping solution using only a small number of "typical '' samples. In doing so, we successfully exploit the fact that there are far fewer coherent groups in an image sequence than pixels.'Some preliminary steps in this direction were made by [NI.

show abstract

Breakout Session Report: Spatiotemporal Grouping

Cited by 2 publications

References 0 publications

Spectral grouping using the nystrom method

Spectral grouping using the nystrom method

Efficient spatiotemporal grouping using the Nystrom method

Contact Info

Product

Resources

About