Unsupervised learning of object features from video sequences

Marius Leordeanu, Robert Collins

Research output: Chapter in Book/Report/Conference proceedingConference contribution

26 Citations (Scopus)

Abstract

We develop an efficient algorithm for unsupervised learning of object models as constellations of features, from low resolution video sequences. The input images typically contain single or multiple objects that change in pose, scale and degree of occlusion. Also, the objects can move significantly between consecutive frames. The content of an input sequence is unlabeled so the learner has to cluster the data based on the data's implicit coherence over time and space. Our approach takes advantage of the dependent pairwise co-occurrences of objects' features within local neighborhoods vs. the independent behavior of unrelated features. We couple or decouple pairs of features based on a probabilistic interpretation of their pairwise statistics and then extract objects as connected components of features.

Original languageEnglish (US)
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PublisherIEEE Computer Society
Pages1142-1149
Number of pages8
VolumeI
ISBN (Print)0769523722, 9780769523729
DOIs
StatePublished - Jan 1 2005
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: Jun 20 2005Jun 25 2005

Other

Other2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
CountryUnited States
CitySan Diego, CA
Period6/20/056/25/05

Fingerprint

Unsupervised learning
Statistics

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Leordeanu, M., & Collins, R. (2005). Unsupervised learning of object features from video sequences. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 (Vol. I, pp. 1142-1149). [1467395] IEEE Computer Society. https://doi.org/10.1109/CVPR.2005.359
Leordeanu, Marius ; Collins, Robert. / Unsupervised learning of object features from video sequences. Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. Vol. I IEEE Computer Society, 2005. pp. 1142-1149
@inproceedings{ec652667b3e04c99b738edb1dcb5f138,
title = "Unsupervised learning of object features from video sequences",
abstract = "We develop an efficient algorithm for unsupervised learning of object models as constellations of features, from low resolution video sequences. The input images typically contain single or multiple objects that change in pose, scale and degree of occlusion. Also, the objects can move significantly between consecutive frames. The content of an input sequence is unlabeled so the learner has to cluster the data based on the data's implicit coherence over time and space. Our approach takes advantage of the dependent pairwise co-occurrences of objects' features within local neighborhoods vs. the independent behavior of unrelated features. We couple or decouple pairs of features based on a probabilistic interpretation of their pairwise statistics and then extract objects as connected components of features.",
author = "Marius Leordeanu and Robert Collins",
year = "2005",
month = "1",
day = "1",
doi = "10.1109/CVPR.2005.359",
language = "English (US)",
isbn = "0769523722",
volume = "I",
pages = "1142--1149",
booktitle = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",
publisher = "IEEE Computer Society",
address = "United States",

}

Leordeanu, M & Collins, R 2005, Unsupervised learning of object features from video sequences. in Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. vol. I, 1467395, IEEE Computer Society, pp. 1142-1149, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, San Diego, CA, United States, 6/20/05. https://doi.org/10.1109/CVPR.2005.359

Unsupervised learning of object features from video sequences. / Leordeanu, Marius; Collins, Robert.

Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. Vol. I IEEE Computer Society, 2005. p. 1142-1149 1467395.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Unsupervised learning of object features from video sequences

AU - Leordeanu, Marius

AU - Collins, Robert

PY - 2005/1/1

Y1 - 2005/1/1

N2 - We develop an efficient algorithm for unsupervised learning of object models as constellations of features, from low resolution video sequences. The input images typically contain single or multiple objects that change in pose, scale and degree of occlusion. Also, the objects can move significantly between consecutive frames. The content of an input sequence is unlabeled so the learner has to cluster the data based on the data's implicit coherence over time and space. Our approach takes advantage of the dependent pairwise co-occurrences of objects' features within local neighborhoods vs. the independent behavior of unrelated features. We couple or decouple pairs of features based on a probabilistic interpretation of their pairwise statistics and then extract objects as connected components of features.

AB - We develop an efficient algorithm for unsupervised learning of object models as constellations of features, from low resolution video sequences. The input images typically contain single or multiple objects that change in pose, scale and degree of occlusion. Also, the objects can move significantly between consecutive frames. The content of an input sequence is unlabeled so the learner has to cluster the data based on the data's implicit coherence over time and space. Our approach takes advantage of the dependent pairwise co-occurrences of objects' features within local neighborhoods vs. the independent behavior of unrelated features. We couple or decouple pairs of features based on a probabilistic interpretation of their pairwise statistics and then extract objects as connected components of features.

UR - http://www.scopus.com/inward/record.url?scp=33745146196&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745146196&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2005.359

DO - 10.1109/CVPR.2005.359

M3 - Conference contribution

AN - SCOPUS:33745146196

SN - 0769523722

SN - 9780769523729

VL - I

SP - 1142

EP - 1149

BT - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

PB - IEEE Computer Society

ER -

Leordeanu M, Collins R. Unsupervised learning of object features from video sequences. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. Vol. I. IEEE Computer Society. 2005. p. 1142-1149. 1467395 https://doi.org/10.1109/CVPR.2005.359