Boosting-based transfer learning for multi-view head-pose classification from surveillance videos

Radu L. Vieriu, Anoop K. Rajagopal, Ramanathan Subramanian, Oswald Lanz, Elisa Ricci, Nicu Sebe, Kalpathi Ramakrishnan

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

5 Citations (Scopus)

Abstract

This work proposes a boosting-based transfer learning approach for head-pose classification from multiple, low-resolution views. Head-pose classification performance is adversely affected when the source (training) and target (test) data arise from different distributions (due to change in face appearance, lighting, etc). Under such conditions, we employ Xferboost, a Logitboost-based transfer learning framework that integrates knowledge from a few labeled target samples with the source model to effectively minimize misclassifications on the target data. Experiments confirm that the Xferboost framework can improve classification performance by up to 6%, when knowledge is transferred between the CLEAR and FBK four-view headpose datasets.

Original languageEnglish
Title of host publicationProceedings of the 20th European Signal Processing Conference, EUSIPCO 2012
EditorsBéatrice Pesquet-Popescu, Corneliu Burileanu
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages649-653
Number of pages5
ISBN (Print)9781467310680
Publication statusPublished - 2012
Externally publishedYes
Event20th European Signal Processing Conference, EUSIPCO 2012 - Bucharest, Romania
Duration: 27 Aug 201231 Aug 2012

Publication series

NameEuropean Signal Processing Conference
ISSN (Print)2219-5491

Conference

Conference20th European Signal Processing Conference, EUSIPCO 2012
Country/TerritoryRomania
CityBucharest
Period27/08/1231/08/12

Fingerprint

Dive into the research topics of 'Boosting-based transfer learning for multi-view head-pose classification from surveillance videos'. Together they form a unique fingerprint.

Cite this