Learning sufficient representation for spatio-temporal deep network using information filter

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

Abstract

This article introduced an improved spatio - temporal deep network based on information filter method for learning sufficient representation. The proposed method aims to improve feature learning capability while modeling spatial and temporal dependencies. Experiments on pattern recognition are conducted to validate the effectiveness of the proposed method.

Original languageEnglish
Title of host publication2014 IEEE/SICE International Symposium on System Integration, SII 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages655-658
Number of pages4
ISBN (Electronic)9781479969449
DOIs
Publication statusPublished - 30 Jan 2014
Event7th IEEE/SICE International Symposium on System Integration, SII 2014 - Tokyo, Japan
Duration: 13 Dec 201415 Dec 2014

Publication series

Name2014 IEEE/SICE International Symposium on System Integration, SII 2014

Other

Other7th IEEE/SICE International Symposium on System Integration, SII 2014
CountryJapan
CityTokyo
Period13/12/1415/12/14

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Networks and Communications
  • Information Systems

Cite this

Hu, Y., Neoh, D. T. H., Sahari, K. S. M., & Loo, C. K. (2014). Learning sufficient representation for spatio-temporal deep network using information filter. In 2014 IEEE/SICE International Symposium on System Integration, SII 2014 (pp. 655-658). [7028116] (2014 IEEE/SICE International Symposium on System Integration, SII 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SII.2014.7028116