A time series kernel for action recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

A time series kernel for action recognition


We address the problem of action recognition by describing actions as time series of frames and introduce a new kernel to compare their dynamical aspects. Action recognition in realistic videos has been successfully addressed using kernel methods like SVMs. Most existing approaches average local features over video volumes and compare the resulting vectors using kernels on bags of features. In contrast, we model actions as time series of per-frame representations and propose a kernel specifically tailored for the purpose of action recognition. Our main contributions are the following: (i) we provide a new principled way to compare the dynamics and temporal structure of actions by computing the distance between their auto-correlations, (ii) we derive a practical formulation to compute this distance in any feature space deriving from a base kernel between frames and (iii) we report experimental results on recent action recognition datasets showing that it provides useful complementary information to the average distribution of frames, as used in state-of-the-art models based on bag-of-features.
Fichier principal
Vignette du fichier
kernel_time_series.pdf (3.12 Mo) Télécharger le fichier
Vignette du fichier
daco_workflow_small.jpg (105.01 Ko) Télécharger le fichier
kernel_time_series_onepager.pdf (2.95 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Format : Figure, Image
Format : Other

Dates and versions

inria-00613089 , version 1 (02-08-2011)
inria-00613089 , version 2 (05-08-2011)



Adrien Gaidon, Zaid Harchaoui, Cordelia Schmid. A time series kernel for action recognition. BMVC 2011 - British Machine Vision Conference, Aug 2011, Dundee, United Kingdom. pp.63.1-63.11, ⟨10.5244/C.25.63⟩. ⟨inria-00613089v2⟩
918 View
1421 Download



Gmail Facebook X LinkedIn More