Human action recognition by semilatent topic models.

Full Abstract

We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words" representation, where each frame corresponds to a "word." Our models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in our models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in our case. Our models have several advantages over other latent topic models used in visual recognition. First of all, the training is much easier due to the decoupling of the model parameters. Second, it alleviates the issue of how to choose the appropriate number of latent topics. Third, it achieves much better performance by utilizing the information provided by the class labels in the training set. We present action classification results on five different data sets. Our results are either comparable to, or significantly better than previously published results on these data sets.

Author information

Author/s: Wang, Yang (Y); Mori, Greg (G);

Affiliation: Simon Fraser University, Burnaby, Canada. ywang12(-atsign-)cs.sfu.ca

Journal and publication information

Publication Type: Journal Article; Research Support, Non-U.S. Gov't

Journal: IEEE transactions on pattern analysis and machine intelligence (IEEE Trans Pattern Anal Mach Intell), published in United States. (Language: eng)

Reference: 2009-Oct; vol 31 (issue 10) : pp 1762-74

Dates: Created 2009/08/21; Completed 2009/10/06;

PMID: 19696448, status: MEDLINE (last retrieval date: 10/6/2009, IMS Date: )

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

External Links for this article
(including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.