You are in : Home » Results & submissions » Select UOA » 11 - Computer Science and Informatics » View submission: Kingston University » Outputs » Detail

Output details

11 - Computer Science and Informatics

Kingston University

Return to search Previous output Next output

Output 40 of 40 in the submission

Output title

View and Style-Independent Action Manifolds for Human Activity Recognition

Type

E - Conference contribution

DOI

10.1007/978-3-642-15567-3_40

Name of conference/published proceedings

11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part VI

Volume number

6316

Issue number

First page of article

547

ISSN of proceedings

1611-3349

Year of publication

2010

URL

Number of additional authors

Additional information

<23> This paper introduces a data driven manifold representation of (camera) view-independent actions, which is applied to human activity recognition. Not only are action descriptors automatically learned, but they are intuitive, view-independent and compact (each action is modelled within a single three dimensional space).

Interdisciplinary

Cross-referral requested

Research group

None

Citation count

Proposed double-weighted

Double-weighted statement

Reserve for a double-weighted output

Non-English

English abstract