Expanded Parts Model for Semantic Description of Humans in Still Images - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2017

Expanded Parts Model for Semantic Description of Humans in Still Images

Résumé

We introduce an Expanded Parts Model (EPM) for recognizing human attributes (e.g. young, short hair, wearing suits) and actions (e.g. running, jumping) in still images. An EPM is a collection of part templates which are learnt discriminatively to explain specific scale-space regions in the images (in human centric coordinates). This is in contrast to current models which consist of a relatively few (i.e. a mixture of) 'average' templates. EPM uses only a subset of the parts to score an image and scores the image sparsely in space, i.e. it ignores redundant and random background in an image. To learn our model, we propose an algorithm which automatically mines parts and learns corresponding discriminative templates together with their respective locations from a large number of candidate parts. We validate our method on three recent challenging datasets of human attributes and actions. We obtain convincing qualitative and state-of-the-art quantitative results on the three datasets.
Fichier principal
Vignette du fichier
epm_pami.pdf (2.02 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01199160 , version 1 (20-03-2017)

Identifiants

Citer

Gaurav Sharma, Frédéric Jurie, Cordelia Schmid. Expanded Parts Model for Semantic Description of Humans in Still Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (1), pp.87-101. ⟨10.1109/TPAMI.2016.2537325⟩. ⟨hal-01199160⟩
522 Consultations
187 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More