Bayesian tensor approach for 3-D face modeling

Dacheng Tao*, Mingli Song, Xuelong Li, Jialie Shen, Jimeng Sun, Xindong Wu, Christos Faloutsos, Stephen J. Maybank

*Corresponding author for this work

Research output: Contribution to journalArticle

94 Citations (Scopus)

Abstract

Effectively modeling a collection of three-dimensional (3-D) faces is an important task in various applications, especially facial expression-driven ones, e.g., expression generation, retargeting, and synthesis. These 3-D faces naturally form a set of second-order tensors-one modality for identity and the other for expression. The number of these second-order tensors is three times of that of the vertices for 3-D face modeling. As for algorithms, Bayesian data modeling, which is a natural data analysis tool, has been widely applied with great success; however, it works only for vector data. Therefore, there is a gap between tensor-based representation and vector-based data analysis tools. Aiming at bridging this gap and generalizing conventional statistical tools over tensors, this paper proposes a decoupled probabilistic algorithm, which is named Bayesian tensor analysis (BTA). Theoretically, BTA can automatically and suitably determine dimensionality for different modalities of tensor data. With BTA, a collection of 3-D faces can be well modeled. Empirical studies on expression retargeting also justify the advantages of BTA.

Original languageEnglish
Article number4633660
Pages (from-to)1397-1410
Number of pages14
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume18
Issue number10
DOIs
Publication statusPublished - 01 Oct 2008
Externally publishedYes

Keywords

  • 3-D face
  • Bayesian inference
  • Bayesian tensor analysis
  • Face expression synthesis

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Bayesian tensor approach for 3-D face modeling'. Together they form a unique fingerprint.

Cite this