Flexible Dictionaries for Action Classification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Flexible Dictionaries for Action Classification


We present a simple approach to action classification which constructs a vector quantization of primitive motions from time series data corresponding to relative limb position estimates. The temporal scale, mean, and shape of primitive motion trajectories are independently modeled, thus creating a exible dictionary of action primitives. We then explore two inference techniques that leverage our action dictionary representation, and evaluate their performance on both motion capture and video benchmark data. Our results indicate that even simplistic algorithms can outperform significantly more sophisticated ones in existing benchmark datasets.
Fichier principal
Vignette du fichier
mlvma08_submission_13.pdf (137.46 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00326723 , version 1 (05-10-2008)


  • HAL Id : inria-00326723 , version 1


Michalis Raptis, Kamil Wnuk, Stefano Soatto. Flexible Dictionaries for Action Classification. The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. ⟨inria-00326723⟩


95 View
129 Download


Gmail Facebook Twitter LinkedIn More