Active transfer learning for multi-view head-pose classification

Yan Yan, Ramanathan Subramanian, Oswald Lanz, Nicu Sebe

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

13 Citations (Scopus)

Abstract

This paper describes an active transfer learning technique for multi-view head-pose classification. We combine transfer learning with active learning, where an active learner asks the domain expert to label the few most informative target samples for transfer learning. Employing adaptive multiple-kernel learning for head-pose classification from four low-resolution views, we show how active sampling enables more efficient learning with few examples. Experimental results confirm that active transfer learning produces 10% higher pose-classification accuracy over several competing transfer learning approaches.

Original languageEnglish
Title of host publication Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
Pages1168-1171
Number of pages4
Publication statusPublished - 2012
Externally publishedYes
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: 11 Nov 201215 Nov 2012

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference21st International Conference on Pattern Recognition, ICPR 2012
Country/TerritoryJapan
CityTsukuba
Period11/11/1215/11/12

Fingerprint

Dive into the research topics of 'Active transfer learning for multi-view head-pose classification'. Together they form a unique fingerprint.

Cite this