Featureless

Bypassing feature extraction in action categorization

Conference paper (2016)

Authors

S. Pintea Universiteit van Amsterdam
Pascal Mettes Universiteit van Amsterdam
J.C. van Gemert Pattern Recognition and Bioinformatics - EEMCS , Universiteit van Amsterdam
AWM Smeulders Universiteit van Amsterdam
Research Group
Pattern Recognition and Bioinformatics (EEMCS) (TU Delft)
Copyright: © 2016 S. Pintea, Pascal Mettes, J.C. van Gemert, AWM Smeulders
DOI
help_outline
https://doi.org/10.1109/ICIP.2016.7532346
Action recognition Multiclass Waldboost Video representations Feature learning
More Info
expand_more

Published Date

2016

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Pattern Recognition and Bioinformatics

Abstract

This method introduces an efficient manner of learning action categories without the need of feature estimation. The approach starts from low-level values, in a similar style to the successful CNN methods. However, rather than extracting general image features, we learn to predict specific video representations from raw video data. The benefit of such an approach is that at the same computational expense it can predict 2D video representations as well as 3D ones, based on motion. The proposed model relies on discriminative Wald-boost, which we enhance to a multiclass formulation for the purpose of learning video representations. The suitability of the proposed approach as well as its time efficiency are tested on the UCF11 action recognition dataset.

Files

1803.06962.pdf
(.pdf | 0.622 Mb)