Redirigiendo al acceso original de articulo en 23 segundos...
Inicio  /  Applied Sciences  /  Vol: 10 Par: 12 (2020)  /  Artículo
ARTÍCULO
TITULO

Agglomerative Clustering and Residual-VLAD Encoding for Human Action Recognition

Ammar Mohsin Butt    
Muhammad Haroon Yousaf    
Fiza Murtaza    
Saima Nazir    
Serestina Viriri and Sergio A. Velastin    

Resumen

Human action recognition has gathered significant attention in recent years due to its high demand in various application domains. In this work, we propose a novel codebook generation and hybrid encoding scheme for classification of action videos. The proposed scheme develops a discriminative codebook and a hybrid feature vector by encoding the features extracted from CNNs (convolutional neural networks). We explore different CNN architectures for extracting spatio-temporal features. We employ an agglomerative clustering approach for codebook generation, which intends to combine the advantages of global and class-specific codebooks. We propose a Residual Vector of Locally Aggregated Descriptors (R-VLAD) and fuse it with locality-based coding to form a hybrid feature vector. It provides a compact representation along with high order statistics. We evaluated our work on two publicly available standard benchmark datasets HMDB-51 and UCF-101. The proposed method achieves 72.6% and 96.2% on HMDB51 and UCF101, respectively. We conclude that the proposed scheme is able to boost recognition accuracy for human action recognition.

 Artículos similares

       
 
Chunchun Li, Manuel Günther, Akshay Raj Dhamija, Steve Cruz, Mohsen Jafarzadeh, Touqeer Ahmad and Terrance E. Boult    
Clustering is a critical part of many tasks and, in most applications, the number of clusters in the data are unknown and must be estimated. This paper presents an Extreme Value Theory-based approach to threshold selection for clustering, proving that th... ver más
Revista: Algorithms

 
Kirill Androsov     Pág. 63 - 69
The article shows that the development of an effective segmentation algorithm for metallographic images is an urgent task. The mean shift algorithm and its disadvantages are considered. To eliminate the shortcomings, a modification of the algorithm based... ver más

 
Bilal Bataineh    
Clustering analysis is a significant technique in various fields, including unsupervised machine learning, data mining, pattern recognition, and image analysis. Many clustering algorithms are currently used, but almost all of them encounter various chall... ver más
Revista: Information

 
Xiao Chu, Xianghua Tan and Weili Zeng    
Performing clustering analysis on a large amount of historical trajectory data can obtain information such as frequent flight patterns of aircraft and air traffic flow distribution, which can provide a reference for the revision of standard flight proced... ver más
Revista: Aerospace

 
Adrien Wartelle, Farah Mourad-Chehade, Farouk Yalaoui, Jan Chrusciel, David Laplanche and Stéphane Sanchez    
Assessing patterns of healthcare problems in a general emergency department population through multimorbidity clustering analysis.
Revista: Applied Sciences