Redirigiendo al acceso original de articulo en 20 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 12 (2022)  /  Artículo
ARTÍCULO
TITULO

Whole-Body Keypoint and Skeleton Augmented RGB Networks for Video Action Recognition

Zizhao Guo and Sancong Ying    

Resumen

Incorporating multi-modality data is an effective way to improve action recognition performance. Based on this idea, we investigate a new data modality in which Whole-Body Keypoint and Skeleton (WKS) labels are used to capture refined body information. Unlike directly aggregated multi-modality, we leverage distillation to adapt an RGB network to classify action with the feature-extraction ability of the WKS network, which is only fed with RGB clips. Inspired by the success of transformers for vision tasks, we design an architecture that takes advantage of both three-dimensional (3D) convolutional neural networks (CNNs) and the Swin transformer to extract spatiotemporal features, resulting in advanced performance. Furthermore, considering the unequal discrimination among clips of a video, we also present a new method for aggregating the clip-level classification results, further improving the performance. The experimental results demonstrate that our framework achieves advanced accuracy of 93.4% with only RGB input on the UCF-101 dataset.

 Artículos similares

       
 
Hossein Shahverdi, Mohammad Nabati, Parisa Fard Moshiri, Reza Asvadi and Seyed Ali Ghorashi    
Human Activity Recognition (HAR) has been a popular area of research in the Internet of Things (IoT) and Human?Computer Interaction (HCI) over the past decade. The objective of this field is to detect human activities through numeric or visual representa... ver más
Revista: Information

 
Ahram Song    
Deep learning techniques have recently shown remarkable efficacy in the semantic segmentation of natural and remote sensing (RS) images. However, these techniques heavily rely on the size of the training data, and obtaining large RS imagery datasets is d... ver más
Revista: Aerospace

 
Xinzhi Liu, Jun Yu, Toru Kurihara, Congzhong Wu, Zhao Niu and Shu Zhan    
It seems difficult to recognize an object from its background with similar color using conventional segmentation methods. An efficient way is to utilize hyperspectral images that contain more wave bands and richer information than only RGB components. Pa... ver más
Revista: Applied Sciences

 
Philipp Satlawa and Robert B. Fisher    
Timely information about the need to thin forests is vital in forest management to maintain a healthy forest while maximizing income. Currently, very-high-spatial-resolution remote sensing data can provide crucial assistance to experts when evaluating th... ver más
Revista: Algorithms

 
Firozeh Solimani, Angelo Cardellicchio, Massimiliano Nitti, Alfred Lako, Giovanni Dimauro and Vito Renò    
Plant phenotyping studies the complex characteristics of plants, with the aim of evaluating and assessing their condition and finding better exemplars. Recently, a new branch emerged in the phenotyping field, namely, high-throughput phenotyping (HTP). Sp... ver más
Revista: Information