Joint classification of actions with matrix completion

Sushma Bomma, Neil M. Robertson

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

4 Citations (Scopus)


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
Number of pages5
ISBN (Print)9781479983391
Publication statusPublished - 2015
Event22nd IEEE International Conference on Image Processing 2015 - Quebec City, Canada
Duration: 27 Sept 201530 Sept 2015
Conference number: 22


Conference22nd IEEE International Conference on Image Processing 2015
Abbreviated titleICIP 2015
CityQuebec City


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

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing


Dive into the research topics of 'Joint classification of actions with matrix completion'. Together they form a unique fingerprint.

Cite this