Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 208

The DOI matches its Crossref record.

Smoothness in layers: Motion segmentation using nonparametric mixture estimation

Weiss, Y.·2002·Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Abstract

Grouping based on common motion, or "common fate" provides a powerful cue for segmenting image sequences. Recently a number of algorithms have been developed that successfully perform motion segmentation by assuming that the motion of each group can be described by a low dimensional parametric model (e.g. affine). Typically the assumption is that motion segments correspond to planar patches in 3D undergoing rigid motion. Here we develop an alternative approach, where the motion of each group is described by a smooth dense flow field and the stability of the estimation is ensured by means of a prior distribution on the class of flow fields. We present a variant of the EM algorithm that can segment image sequences by fitting multiple smooth flow fields to the spatiotemporal data. Using the method of Green's functions, we show how the estimation of a single smooth flow field can be performed in closed form, thus making the multiple model estimation computationally feasible. Furthermore, the number of models is estimated automatically using similar methods to those used in the parametric approach. We illustrate the algorithm's performance on synthetic and real image sequences.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.1997.609375

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

No references could be resolved yet.

Research works printed but not linked: 21

  1. 10.1109/CVPR.1993.341161 · DOI · Paper page
  2. 10.1109/83.265979 · DOI
  3. 10.1109/CVPR.1993.341169 · doi:10.1109/cvpr.1993.341169
  4. 10.1109/21.156583 · doi:10.1109/21.156583
  5. 10.1038/317314a0 · DOI · Paper page
  6. 10.1109/CVPR.1991.139707 · DOI · Paper page
  7. strang, 1986, Introduction to Applied Mathematics
  8. 10.1109/ICCV.1995.466862 · DOI
  9. 10.1109/TPAMI.1986.4767807 · DOI · Paper page
  10. wang, 1994, Representing moving images with layers. IEEE Transactions on Image Processing Special Issue, Image Sequence Compression, 3, 625
  11. dempster, 1977, Maximum likelihood from incomplete data via the EM algorithm, J R Statist Soc B, 39, 1
  12. 10.1109/WVM.1991.212810 · doi:10.1109/wvm.1991.212810
  13. girasi, 1993, Priors stabilizers and basis functions From regularization to radial tensor and additive splines
  14. 10.1109/TPAMI.1984.4767596 · DOI · Paper page
  15. 10.1109/ICPR.1994.576427 · DOI
  16. 10.1016/0004-3702(81)90024-2 · DOI · Paper page
  17. bergen, 1992, Hierarchial model-based motion estimation, Proc Second European Conf on Comput Vision, 237
  18. 10.1109/ICCV.1995.466859 · DOI
  19. 10.1109/CVPR.1992.223272 · doi:10.1109/cvpr.1992.223272
  20. 10.1109/CVPR.1996.517092 · DOI · Paper page
  21. 10.1007/BF00126430 · DOI · Paper page

Cited by

See all 208

Metadata

Authors
Weiss, Y.
Venue
Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Published
2002-11-22
Pages
520-526
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2097099938
Cited by
208
References
0
FWCI
17.09
Type
conference paper
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Smoothness in layers: Motion segmentation using nonparametric mixture estimation. https://app.cochat.ai/papers/10.1109/cvpr.1997.609375
The paper
Weiss, Y. (2002). Smoothness in layers: Motion segmentation using nonparametric mixture estimation. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.1997.609375

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.