Jeni, L;
Lőrincz, A;
Szabo, Z;
Cohn, J;
Kanade, T;
(2014)
Spatio-temporal event classification using time-series kernel based structured sparsity.
In: Fleet, D and Pajdla, T and Schiele, B and Tuytelaars, T, (eds.)
Computer Vision – ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV.
(pp. pp. 135-150).
Springer International Publishing: Switzerland.
![[thumbnail of jeni14spatio.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/text.png) |
Text
jeni14spatio.pdf Available under License : See the attached licence file. Download (774kB) |
Preview |
Text
jeni14spatio_supplementary_material1.pdf Available under License : See the attached licence file. Download (263kB) |
|
Text
jeni14spatio_supplementary_material2.mp4 Available under License : See the attached licence file. Download (16MB) |
Preview |
Text
Szabo_jeni14spatio_poster.pdf Download (3MB) | Preview |
Abstract
In many behavioral domains, such as facial expression and gesture, sparse structure is prevalent. This sparsity would be well suited for event detection but for one problem. Features typically are confounded by alignment error in space and time. As a consequence, high-dimensional representations such as SIFT and Gabor features have been favored despite their much greater computational cost and potential loss of information. We propose a Kernel Structured Sparsity (KSS) method that can handle both the temporal alignment problem and the structured sparse reconstruction within a common framework, and it can rely on simple features. We characterize spatio-temporal events as time-series of motion patterns and by utilizing time-series kernels we apply standard structured-sparse coding techniques to tackle this important problem. We evaluated the KSS method using both gesture and facial expression datasets that include spontaneous behavior and differ in degree of difficulty and type of ground truth coding. KSS outperformed both sparse and non-sparse methods that utilize complex image features and their temporal extensions. In the case of early facial event classification KSS had 10% higher accuracy as measured by F1 score over kernel SVM methods.
| Type: | Proceedings paper |
|---|---|
| Title: | Spatio-temporal event classification using time-series kernel based structured sparsity |
| Event: | European Conference on Computer Vision (ECCV) |
| Location: | Zürich, Switzerland |
| Dates: | 2014-09-06 - 2014-09-12 |
| ISBN-13: | 9783319105925 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/978-3-319-10593-2_10 |
| Publisher version: | http://dx.doi.org/10.1007/978-3-319-10593-2_10 |
| Language: | English |
| Additional information: | The final publication is available at Spingerlink: http://dx.doi.org/10.1007/978-3-319-10593-2_10. |
| Keywords: | facial expression classification, gesture recognition, structured sparsity, time-series kernel |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences |
| URI: | https://discovery.ucl.ac.uk/id/eprint/1435544 |
Archive Staff Only
 |
View Item |
