Human action recognition using extreme learning machine based on visual vocabularies

Minhas, Rashid; Baradarani, Aryaz; Seifzadeh, Sepideh; Wu, Qi

doi:10.1016/j.neucom.2010.01.020

Cited by 139 publications

(69 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Numerous endeavors have been made to discover interest focuses with different standards [46][47][48][49][50][51][52]. For instance, Rapantzikos et al [49] proposed a saliency-based interest focuses identifier which consolidates power, shading, and motion.…”

Section: Action Recognition With Space-time Local Featuresmentioning

confidence: 99%

See 1 more Smart Citation

A Review on Machine Learning Algorithms on Human Action Recognition

Rai

2017

Asian J Pharm Clin Res

View full text Add to dashboard Cite

Human action recognition is a vital field of computer vision research. Its applications incorporate observation frameworks, patient monitoring frameworks, and an assortment of frameworks that include interactions between persons and electronic gadgets, for example, human-computer interfaces. The vast majority of these applications require an automated recognition of abnormal or anomalistic action states, made out of various straightforward (or nuclear) actions of persons. This study gives an overview of different best in class research papers on human movement recognition. Open datasets intended for the assessment of the recognition procedures are also discussed in this paper too, for comparing results of several methodologies on this datasets. We examine both the approaches produced for basic human actions and those for abnormal action states. These methodologies are taxonomically classified based on looking at the points of interest and constraints of every methodology. Space-time volume approaches and sequential methodologies that represent actions and perceive such action sets straightforwardly from images are discussed. Next, hierarchical recognition approaches for abnormal action states are introduced and looked at. Statistic-based methodologies, syntactic methodologies, and description-based methodologies for hierarchical recognition are examined in the paper.

show abstract

Section: Action Recognition With Space-time Local Featuresmentioning

confidence: 99%

“…Minhas et al [48] proposed new strategies to process the spatiotemporal features utilizing 3D dual-tree discrete wavelet transform. 3D DTDWT was utilized to get the spatiotemporal data (subband vector of wavelet coefficients) productively, and a relative SIFT was utilized for nearby static features.…”

Section: Action Recognition With Space-time Local Featuresmentioning

confidence: 99%

A Review on Machine Learning Algorithms on Human Action Recognition

Rai

2017

Asian J Pharm Clin Res

View full text Add to dashboard Cite

show abstract

“…By observing (8), it can be seen that this equation can be used only in the cases where the matrix B = ΦΦ T is invertible, i.e., when N > D. A regularized version of the ELM algorithm addressing this issue has been proposed in [12], where the network output weights are obtained, according to a regularization paramter c > 0, by:…”

Section: Extreme Learning Machinementioning

confidence: 99%

“…ELM not only tends to reach a small training error, but also a small norm of output weights, indicating good generalization performance [7]. ELM has been successfully applied to many classification problems, including human action recognition [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Multi-view Regularized Extreme Learning Machine for Human Action Recognition

Iosifidis

Tefas

Pitas

2014

Artificial Intelligence: Methods and Applications

View full text Add to dashboard Cite

Abstract. In this paper, we propose an extension of the ELM algorithm that is able to exploit multiple action representations. This is achieved by incorporating proper regularization terms in the ELM optimization problem. In order to determine both optimized network weights and action representation combination weights, we propose an iterative optimization process. The proposed algorithm has been evaluated by using the state-of-the-art action video representation on three publicly available action recognition databases, where its performance has been compared with that of two commonly used video representation combination approaches, i.e., the vector concatenation before learning and the combination of classification outcomes based on learning on each view independently.

show abstract

“…Por tais virtudes proliferaram as aplicações do SIFT na área de Visão Computacional, tais como localização e mapeamento por robôs (SLAM) (LEE e SONG, 2010), reconhecimento de gestos (MINHAS et al, 2010), reconhecimento facial (TAN et al, 2010), realidade aumentada (SHEN et al, 2010) e análise de imagens médicas (TOEWS et al, 2009).…”

Section: Descritores De Região Para Mapas Densos De Pontos Homólogosunclassified

Correspondência eficiente de descritores SIFT para construção de mapas densos de pontos homólogos em imagens de sensoriamento remoto

Silveira¹,

Feitosa²,

Brito

et al. 2011

Bol. Ciênc. Geod.

View full text Add to dashboard Cite

RESUMOMétodos automáticos de localização de pontos homólogos em imagens digitais baseados em área, combinados com técnicas de crescimento de região, são capazes de produzir uma malha densa e exata de pontos homólogos. Entretanto, o processo de crescimento de região pode ser interrompido em regiões da imagem, cuja paralaxe no eixo horizontal apresenta variação abrupta. Essa situação geralmente é causada por uma descontinuidade na superfície ou espaço-objeto imageado, tal como um prédio numa cena urbana ou um paredão de exploração de uma mina a céu aberto. Nesses casos, novos pares de pontos homólogos (sementes) devem ser Bol.

show abstract

Human action recognition using extreme learning machine based on visual vocabularies

Cited by 139 publications

References 24 publications

A Review on Machine Learning Algorithms on Human Action Recognition

A Review on Machine Learning Algorithms on Human Action Recognition

Multi-view Regularized Extreme Learning Machine for Human Action Recognition

Correspondência eficiente de descritores SIFT para construção de mapas densos de pontos homólogos em imagens de sensoriamento remoto

Contact Info

Product

Resources

About