Enhancing Action Recognition by Cross-Domain Dictionary Learning

Zhu, Fan and Shao, Ling (2013) Enhancing Action Recognition by Cross-Domain Dictionary Learning. In: British Machine Vision Conference 2013, 9th - 13th September 2013, Bristol, UK.

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.5244/C.27.52

Abstract

We present a novel cross-dataset action recognition framework that utilizes relevant actions from other visual domains as auxiliary knowledge for enhancing the learning system in the target domain. The data distribution of relevant actions from a source dataset is adapted to match the data distribution of actions in the target dataset via a cross-domain discriminative dictionary learning method, through which a reconstructive, discriminative and domain-adaptive dictionary-pair can be learned. Using selected categories from the HMDB51 dataset as the source domain actions, the proposed framework achieves outstanding performance on the UCF YouTube dataset.

Item Type: Conference or Workshop Item (Paper)
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 16 Jun 2015 11:33
Last Modified: 10 Aug 2015 11:08
URI: http://nrl.northumbria.ac.uk/id/eprint/22941

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics


Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence