Variational transform invariant mixture of probabilistic PCA

Jilin Tu, Yun Fu, Alexandar Ivanovic, Thomas S. Huang, Fei Fei Li

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

Abstract

In many video-based object recognition applications, the object appearances are acquired by visual tracking or detection and are inconsistent due to misalignments. We believe the misalignments can be removed if we can reduce the inconsistency in the object appearances caused by mis-alignments through clustering the objects in appearance, space and time domain simultaneously. We therefore propose to learn Transform Invariant Mixtures of Probabilistic PCA (TIMPPCA) model from the data while at the same time eliminating the misalignments. The model is formulated in a generative framework, and the misalignments are considered as hidden variables in the model. Variational EM update rules are then derived based on Variational Message Passing (VMP) techniques. The proposed TIMP-PCA is applied to improve head pose estimation performance and to detect the change of attention focus in meeting room video for meeting room video indexing/retrieval and achieves promising performance.

Original languageEnglish (US)
Title of host publication2008 IEEE Workshop on Applications of Computer Vision, WACV
DOIs
StatePublished - 2008
Event2008 IEEE Workshop on Applications of Computer Vision, WACV - Copper Mountain, CO, United States
Duration: Jan 7 2008Jan 9 2008

Publication series

Name2008 IEEE Workshop on Applications of Computer Vision, WACV

Other

Other2008 IEEE Workshop on Applications of Computer Vision, WACV
Country/TerritoryUnited States
CityCopper Mountain, CO
Period1/7/081/9/08

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Variational transform invariant mixture of probabilistic PCA'. Together they form a unique fingerprint.

Cite this