Skip to Main content Skip to Navigation
Conference papers

Flexible Dictionaries for Action Classification

Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [33 references]  Display  Hide  Download

https://hal.inria.fr/inria-00326723
Contributor : Peter Sturm <>
Submitted on : Sunday, October 5, 2008 - 12:46:37 PM
Last modification on : Wednesday, August 7, 2019 - 12:14:40 PM
Long-term archiving on: : Monday, October 8, 2012 - 1:56:52 PM

File

mlvma08_submission_13.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00326723, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

172

Files downloads

328