Nothing Special   »   [go: up one dir, main page]

skip to main content
10.1109/FG.2017.109guideproceedingsArticle/Chapter ViewAbstractPublication PagesConference Proceedingsacm-pubtype
research-article

Support Vector Regression of Sparse Dictionary-Based Features for View-Independent Action Unit Intensity Estimation

Published: 30 May 2017 Publication History

Abstract

In this paper, a robust system for viewindependent action unit intensity estimation is presented. Based on the theory of sparse coding, region-specific dictionaries are trained to approximate the characteristic of the individual action units. The system incorporates landmark detection, face alignment and contrast normalization to handle a large variety of different scenes. Coupled with head pose estimation, an ensemble of large margin classifiers is used to detect the individual action units. The experimental validation shows that our system is robust against pose variations and able to outperform the challenge baseline by more than 35%.

Index Terms

  1. Support Vector Regression of Sparse Dictionary-Based Features for View-Independent Action Unit Intensity Estimation
            Index terms have been assigned to the content through auto-classification.

            Recommendations

            Comments

            Please enable JavaScript to view thecomments powered by Disqus.

            Information & Contributors

            Information

            Published In

            cover image Guide Proceedings
            2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)
            May 2017
            999 pages

            Publisher

            IEEE Press

            Publication History

            Published: 30 May 2017

            Qualifiers

            • Research-article

            Contributors

            Other Metrics

            Bibliometrics & Citations

            Bibliometrics

            Article Metrics

            • 0
              Total Citations
            • 0
              Total Downloads
            • Downloads (Last 12 months)0
            • Downloads (Last 6 weeks)0
            Reflects downloads up to 02 Oct 2024

            Other Metrics

            Citations

            View Options

            View options

            Get Access

            Login options

            Media

            Figures

            Other

            Tables

            Share

            Share

            Share this Publication link

            Share on social media