Expanded Parts Model for Human Attribute and Action Recognition in Still Images - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Expanded Parts Model for Human Attribute and Action Recognition in Still Images

Abstract

We propose a new model for recognizing human attributes (e.g. wearing a suit, sitting, short hair) and actions (e.g. running, riding a horse) in still images. The proposed model relies on a collection of part templates which are learnt discriminatively to explain specific scale-space locations in the images (in human centric coordinates). It avoids the limitations of highly structured models, which consist of a few (i.e. a mixture of) 'average' templates. To learn our model, we propose an algorithm which automatically mines out parts and learns corresponding discriminative templates with their respective locations from a large number of candidate parts. We validate the method on recent challenging datasets: (i) Willow 7 actions [7], (ii) 27 Human Attributes (HAT) [25], and (iii) Stanford 40 actions [37]. We obtain convincing qualitative and state-of-the-art quantitative results on the three datasets.
Fichier principal
Vignette du fichier
sharma_epm_cvpr2013.pdf (2.48 Mo) Télécharger le fichier
Vignette du fichier
epm_iilus_icon.jpg (204.23 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Format Figure, Image
Loading...

Dates and versions

hal-00816144 , version 1 (19-04-2013)
hal-00816144 , version 2 (20-04-2013)

Identifiers

Cite

Gaurav Sharma, Frédéric Jurie, Cordelia Schmid. Expanded Parts Model for Human Attribute and Action Recognition in Still Images. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2013, Portland, Oregon, United States. pp.652-659, ⟨10.1109/CVPR.2013.90⟩. ⟨hal-00816144v2⟩
1492 View
1131 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More