Complexity-aware assignment of latent values in discriminative models for accurate gesture recognition

Manoel Horta Ribeiro, Bruno Teixeira, Antonio Otavio Fernandes, Wagner Meira, Erickson R. Nascimento

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

Abstract

Many of the state-of-the-art algorithms for gesture recognition are based on Conditional Random Fields (CRFs). Successful approaches, such as the Latent-Dynamic CRFs, extend the CRF by incorporating latent variables, whose values are mapped to the values of the labels. In this paper we propose a novel methodology to set the latent values according to the gesture complexity. We use an heuristic that iterates through the samples associated with each label value, estimating their complexity. We then use it to assign the latent values to the label values. We evaluate our method on the task of recognizing human gestures from video streams. The experiments were performed in binary datasets, generated by grouping different labels. Our results demonstrate that our approach outperforms the arbitrary one in many cases, increasing the accuracy by up to 10%.

Original languageEnglish (US)
Title of host publicationProceedings - 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages378-385
Number of pages8
ISBN (Electronic)9781509035687
DOIs
StatePublished - Jan 10 2017
Externally publishedYes
Event29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016 - Sao Jose dos Campos, Sao Paulo, Brazil
Duration: Oct 4 2016Oct 7 2016

Publication series

NameProceedings - 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016

Conference

Conference29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016
Country/TerritoryBrazil
CitySao Jose dos Campos, Sao Paulo
Period10/4/1610/7/16

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Keywords

  • activity recognition
  • conditional random fields
  • discriminative models
  • gesture recognition

Fingerprint

Dive into the research topics of 'Complexity-aware assignment of latent values in discriminative models for accurate gesture recognition'. Together they form a unique fingerprint.

Cite this