A Hybrid Network for Large-Scale Action Recognition from RGB and Depth Modalities

Autor:	Huogen Wang, Zhanjie Song, Wanqing Li, Pichao Wang
Jazyk:	angličtina
Rok vydání:	2020
Předmět:	action recognition weighted rank pooling weighted dynamic image 3D convolutional LSTM network canonical correlation analysis Chemical technology TP1-1185
Zdroj:	Sensors, Vol 20, Iss 11, p 3305 (2020)
Druh dokumentu:	article
ISSN:	1424-8220
DOI:	10.3390/s20113305
Popis:	The paper presents a novel hybrid network for large-scale action recognition from multiple modalities. The network is built upon the proposed weighted dynamic images. It effectively leverages the strengths of the emerging Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) based approaches to specifically address the challenges that occur in large-scale action recognition and are not fully dealt with by the state-of-the-art methods. Specifically, the proposed hybrid network consists of a CNN based component and an RNN based component. Features extracted by the two components are fused through canonical correlation analysis and then fed to a linear Support Vector Machine (SVM) for classification. The proposed network achieved state-of-the-art results on the ChaLearn LAP IsoGD, NTU RGB+D and Multi-modal & Multi-view & Interactive ( M 2 I ) datasets and outperformed existing methods by a large margin (over 10 percentage points in some cases).
Databáze:	Directory of Open Access Journals
Externí odkaz:	https://doaj.org/article/6098b16a1f3e498cb2709e22eae7512f Zobrazit plný text záznamu View record in DOAJ Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.