Efficient Combination of Classifiers for 3D Action Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F21%3A00118857" target="_blank" >RIV/00216224:14330/21:00118857 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s00530-021-00767-9" target="_blank" >https://link.springer.com/article/10.1007/s00530-021-00767-9</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s00530-021-00767-9" target="_blank" >10.1007/s00530-021-00767-9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Combination of Classifiers for 3D Action Recognition

Popis výsledku v původním jazyce

The popular task of 3D human action recognition is almost exclusively solved by training deep-learning classifiers. To achieve high recognition accuracy, input 3D actions are often pre-processed by various normalization or augmentation techniques. However, it is not computationally feasible to train a classifier for each possible variant of training data in order to select the best-performing combination of pre-processing techniques for a given dataset. In this paper, we propose an evaluation procedure that determines the best combination in a very efficient way. In particular, we only train one independent classifier for each available pre-processing technique and estimate the accuracy of a specific combination by efficient fusion of the corresponding classification results based on a strict majority vote rule. In addition, for the best-ranked combination, we can retrospectively apply the normalized/augmented variants of input data to train only a single classifier. This enables to decide whether it is generally better to train a single model, or rather a set of independent classifiers whose results are fused within the classification phase. We evaluate the experiments on single-subject as well as person-interaction datasets of 3D skeleton sequences and all combinations of up to 16 normalization and augmentation techniques, some of them also proposed in this paper.

Název v anglickém jazyce

Efficient Combination of Classifiers for 3D Action Recognition

Popis výsledku anglicky

The popular task of 3D human action recognition is almost exclusively solved by training deep-learning classifiers. To achieve high recognition accuracy, input 3D actions are often pre-processed by various normalization or augmentation techniques. However, it is not computationally feasible to train a classifier for each possible variant of training data in order to select the best-performing combination of pre-processing techniques for a given dataset. In this paper, we propose an evaluation procedure that determines the best combination in a very efficient way. In particular, we only train one independent classifier for each available pre-processing technique and estimate the accuracy of a specific combination by efficient fusion of the corresponding classification results based on a strict majority vote rule. In addition, for the best-ranked combination, we can retrospectively apply the normalized/augmented variants of input data to train only a single classifier. This enables to decide whether it is generally better to train a single model, or rather a set of independent classifiers whose results are fused within the classification phase. We evaluate the experiments on single-subject as well as person-interaction datasets of 3D skeleton sequences and all combinations of up to 16 normalization and augmentation techniques, some of them also proposed in this paper.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

<a href="/cs/project/GA19-02033S" target="_blank" >GA19-02033S: Vyhledávání, analytika a anotace datových toků lidských pohybů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Multimedia Systems

ISSN

0942-4962

e-ISSN

1432-1882

Svazek periodika

27

Číslo periodika v rámci svazku

5

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

12

Strana od-do

941-952

Kód UT WoS článku

000628724200001

EID výsledku v databázi Scopus

2-s2.0-85102599920