Continuous Conditional Neural Fields for Structured Regression

  • Tadas Baltrušaitis
  • Peter Robinson
  • Louis-Philippe Morency
Conference paper

DOI: 10.1007/978-3-319-10593-2_39

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8692)
Cite this paper as:
Baltrušaitis T., Robinson P., Morency LP. (2014) Continuous Conditional Neural Fields for Structured Regression. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8692. Springer, Cham

Abstract

An increasing number of computer vision and pattern recognition problems require structured regression techniques. Problems like human pose estimation, unsegmented action recognition, emotion prediction and facial landmark detection have temporal or spatial output dependencies that regular regression techniques do not capture. In this paper we present continuous conditional neural fields (CCNF) – a novel structured regression model that can learn non-linear input-output dependencies, and model temporal and spatial output relationships of varying length sequences. We propose two instances of our CCNF framework: Chain-CCNF for time series modelling, and Grid-CCNF for spatial relationship modelling. We evaluate our model on five public datasets spanning three different regression problems: facial landmark detection in the wild, emotion prediction in music and facial action unit recognition. Our CCNF model demonstrates state-of-the-art performance on all of the datasets used.

Keywords

Structured regression Landmark detection Face tracking 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-319-10593-2_39_MOESM1_ESM.pdf (208 kb)
Electronic Supplementary Material(208 KB)

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Tadas Baltrušaitis
    • 1
  • Peter Robinson
    • 1
  • Louis-Philippe Morency
    • 2
  1. 1.Computer LaboratoryUniversity of CambridgeUK
  2. 2.Institute for Creative TechnologiesUniversity of Southern CaliforniaUSA

Personalised recommendations