Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners

Gilbert, Andrew, Illingworth, John and Bowden, Richard (2008) Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners In: ECCV 2008, 2008-10-12 - 2008-10-18, Marseille, France.

	Text Gilbert_ECCV08.pdf Restricted to Repository staff only Available under License : See the attached licence file. Download (3MB)
	Text (licence) SRI_deposit_agreement.pdf Restricted to Repository staff only Download (33kB)

Abstract

The use of sparse invariant features to recognise classes of actions or objects has become common in the literature. However, features are often ”engineered” to be both sparse and invariant to transformation and it is assumed that they provide the greatest discriminative information. To tackle activity recognition, we propose learning compound features that are assembled from simple 2D corners in both space and time. Each corner is encoded in relation to its neighbours and from an over complete set (in excess of 1 million possible features), compound features are extracted using data mining. The final classifier, consisting of sets of compound features, can then be applied to recognise and localise an activity in real-time while providing superior performance to other state-of-the-art approaches (including those based upon sparse feature detectors). Furthermore, the approach requires only weak supervision in the form of class labels for each training sequence. No ground truth position or temporal alignment is required during training.

Item Type:	Conference or Workshop Item (Conference Paper)
Divisions :	Surrey research (other units)
Authors :	Name Email ORCID Gilbert, Andrew A.Gilbert@surrey.ac.uk Illingworth, John J.Illingworth@surrey.ac.uk Bowden, Richard R.Bowden@surrey.ac.uk
Date :	2008
DOI :	10.1007/978-3-540-88682-2_18
Copyright Disclaimer :	Copyright Springer-Verlag 2008
Contributors :	Contribution Name Email ORCID http://www.loc.gov/loc.terms/relators/PBL Springer,
Related URLs :	Author
Depositing User :	Symplectic Elements
Date Deposited :	28 Mar 2017 14:42
Last Modified :	23 Jan 2020 12:46
URI:	http://epubs.surrey.ac.uk/id/eprint/531479

Actions (login required)

View Item

Downloads