Continuous Action Recognition Based on Sequence Alignment - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal of Computer Vision Année : 2015

Continuous Action Recognition Based on Sequence Alignment

Résumé

Continuous action recognition is more challenging than isolated recognition because classification and segmentation must be simultaneously carried out. We build on the well known dynamic time warping (DTW) framework and devise a novel visual alignment technique, namely dynamic frame warping (DFW), which performs isolated recognition based on per-frame representation of videos, and on aligning a test sequence with a model sequence. Moreover, we propose two extensions which enable to perform recognition concomitant with segmentation, namely one-pass DFW and two-pass DFW. These two methods have their roots in the domain of continuous recognition of speech and, to the best of our knowledge, their extension to continuous visual action recognition has been overlooked. We test and illustrate the proposed techniques with a recently released dataset (RAVEL) and with two public-domain datasets widely used in action recognition (Hollywood-1 and Hollywood-2). We also compare the performances of the proposed isolated and continuous recognition algorithms with several recently published methods.
Fichier principal
Vignette du fichier
Kulkarni-IJCV-05May2014.pdf (16.49 Mo) Télécharger le fichier
Vignette du fichier
example-hal.png (236.37 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

hal-01058732 , version 1 (27-08-2014)

Identifiants

Citer

Kaustubh Kulkarni, Georgios Evangelidis, Jan Cech, Radu Horaud. Continuous Action Recognition Based on Sequence Alignment. International Journal of Computer Vision, 2015, 112 (1), pp.90-114. ⟨10.1007/s11263-014-0758-9⟩. ⟨hal-01058732⟩
662 Consultations
826 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More