Joint classification of actions with matrix completion

Sushma Bomma, Neil M. Robertson

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

Abstract

Action classification is one of the crucial research areas with multitude applications. It has witnessed significant developments over last decade. In this paper, we propose to jointly classify actions from more than a single class using Matrix completion. Matrix-completion methods can handle the deficiencies in data very effectively resulting in improved classification accuracy. Features and labels from data are concatenated to form a big matrix with unknown or missing entries in the place of test data labels. Matrix-completion methods fill up these entries using tools from convex optimization resulting in classification. We show that the proposed method achieves improved performance over the recent works on two human action datasets including most popular Weizmann dataset and recently released and more realistic UCF-101 dataset.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Image Processing (ICIP)
Subtitle of host publicationProceedings
PublisherIEEE
Pages2766-2770
Number of pages5
ISBN (Print)9781479983391
DOIs
Publication statusPublished - 2015
Event22nd IEEE International Conference on Image Processing 2015 - Quebec City, Canada
Duration: 27 Sep 201530 Sep 2015
Conference number: 22

Conference

Conference22nd IEEE International Conference on Image Processing 2015
Abbreviated titleICIP 2015
CountryCanada
CityQuebec City
Period27/09/1530/09/15

Fingerprint

Labels
Convex optimization

Keywords

  • Compressed Sensing
  • Convex Optimization
  • Human Action Classification/Recognition
  • Matrix Completion

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Bomma, S., & Robertson, N. M. (2015). Joint classification of actions with matrix completion. In 2015 IEEE International Conference on Image Processing (ICIP): Proceedings (pp. 2766-2770). [7351306] IEEE. https://doi.org/10.1109/ICIP.2015.7351306
Bomma, Sushma ; Robertson, Neil M. / Joint classification of actions with matrix completion. 2015 IEEE International Conference on Image Processing (ICIP): Proceedings. IEEE, 2015. pp. 2766-2770
@inproceedings{fc185e43c6884ce9b7f4d7dd41881526,
title = "Joint classification of actions with matrix completion",
abstract = "Action classification is one of the crucial research areas with multitude applications. It has witnessed significant developments over last decade. In this paper, we propose to jointly classify actions from more than a single class using Matrix completion. Matrix-completion methods can handle the deficiencies in data very effectively resulting in improved classification accuracy. Features and labels from data are concatenated to form a big matrix with unknown or missing entries in the place of test data labels. Matrix-completion methods fill up these entries using tools from convex optimization resulting in classification. We show that the proposed method achieves improved performance over the recent works on two human action datasets including most popular Weizmann dataset and recently released and more realistic UCF-101 dataset.",
keywords = "Compressed Sensing, Convex Optimization, Human Action Classification/Recognition, Matrix Completion",
author = "Sushma Bomma and Robertson, {Neil M.}",
year = "2015",
doi = "10.1109/ICIP.2015.7351306",
language = "English",
isbn = "9781479983391",
pages = "2766--2770",
booktitle = "2015 IEEE International Conference on Image Processing (ICIP)",
publisher = "IEEE",
address = "United States",

}

Bomma, S & Robertson, NM 2015, Joint classification of actions with matrix completion. in 2015 IEEE International Conference on Image Processing (ICIP): Proceedings., 7351306, IEEE, pp. 2766-2770, 22nd IEEE International Conference on Image Processing 2015, Quebec City, Canada, 27/09/15. https://doi.org/10.1109/ICIP.2015.7351306

Joint classification of actions with matrix completion. / Bomma, Sushma; Robertson, Neil M.

2015 IEEE International Conference on Image Processing (ICIP): Proceedings. IEEE, 2015. p. 2766-2770 7351306.

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

TY - GEN

T1 - Joint classification of actions with matrix completion

AU - Bomma, Sushma

AU - Robertson, Neil M.

PY - 2015

Y1 - 2015

N2 - Action classification is one of the crucial research areas with multitude applications. It has witnessed significant developments over last decade. In this paper, we propose to jointly classify actions from more than a single class using Matrix completion. Matrix-completion methods can handle the deficiencies in data very effectively resulting in improved classification accuracy. Features and labels from data are concatenated to form a big matrix with unknown or missing entries in the place of test data labels. Matrix-completion methods fill up these entries using tools from convex optimization resulting in classification. We show that the proposed method achieves improved performance over the recent works on two human action datasets including most popular Weizmann dataset and recently released and more realistic UCF-101 dataset.

AB - Action classification is one of the crucial research areas with multitude applications. It has witnessed significant developments over last decade. In this paper, we propose to jointly classify actions from more than a single class using Matrix completion. Matrix-completion methods can handle the deficiencies in data very effectively resulting in improved classification accuracy. Features and labels from data are concatenated to form a big matrix with unknown or missing entries in the place of test data labels. Matrix-completion methods fill up these entries using tools from convex optimization resulting in classification. We show that the proposed method achieves improved performance over the recent works on two human action datasets including most popular Weizmann dataset and recently released and more realistic UCF-101 dataset.

KW - Compressed Sensing

KW - Convex Optimization

KW - Human Action Classification/Recognition

KW - Matrix Completion

UR - http://www.scopus.com/inward/record.url?scp=84956630665&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351306

DO - 10.1109/ICIP.2015.7351306

M3 - Conference contribution

SN - 9781479983391

SP - 2766

EP - 2770

BT - 2015 IEEE International Conference on Image Processing (ICIP)

PB - IEEE

ER -

Bomma S, Robertson NM. Joint classification of actions with matrix completion. In 2015 IEEE International Conference on Image Processing (ICIP): Proceedings. IEEE. 2015. p. 2766-2770. 7351306 https://doi.org/10.1109/ICIP.2015.7351306