Learning and inferring human actions with temporal pyramid features based on conditional random fields

Shih Yao Lin, Yen Yu Lin, Chu Song Chen, Yi Ping Hung

Research output: Chapter in Book/Report/Conference proceedingChapter

4 Scopus citations

Abstract

Finding an effective way to represent human actions is yet an open problem because it usually requires taking evidences extracted from various temporal resolutions into account. A conventional way of representing an action employs tem-porally ordered fine-grained movements, e.g., key poses or subtle motions. Many existing approaches model actions by directly learning the transitional relationships between those fine-grained features. Yet, an action data may have many similar observations with occasional and irregular changes, which make commonly used fine-grained features less reli-able. This paper presents a set of temporal pyramid features that enriches action representation with various levels of se-mantic granularities. For learning and inferring the proposed pyramid features, we adopt a discriminative model with latent variables to capture the hidden dynamics in each layer of the pyramid. Our method is evaluated on a Tai-Chi Chun dataset and a daily activities dataset. Both of them are collected by us. Experimental results demonstrate that our approach achieves more favorable performance than existing methods.
Original languageAmerican English
Title of host publication2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2617-2621
Number of pages5
ISBN (Print)9781509041176
DOIs
StatePublished - 16 Jun 2017

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Keywords

  • conditional random fields
  • human action recognition
  • temporal pyramid representation

Cite this

Lin, S. Y., Lin, Y. Y., Chen, C. S., & Hung, Y. P. (2017). Learning and inferring human actions with temporal pyramid features based on conditional random fields. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2617-2621). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952630