Skip to Main content Skip to Navigation
Conference papers

A time series kernel for action recognition

Adrien Gaidon 1, 2 Zaid Harchaoui 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [7 references]  Display  Hide  Download
Contributor : Thoth Team Connect in order to contact the contributor
Submitted on : Friday, August 5, 2011 - 11:09:43 AM
Last modification on : Thursday, January 20, 2022 - 5:28:05 PM
Long-term archiving on: : Monday, December 5, 2016 - 12:25:52 AM




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⟩



Les métriques sont temporairement indisponibles