Inicio  /  Applied Sciences  /  Vol: 10 Par: 4 (2020)  /  Artículo
ARTÍCULO
TITULO

Body-Part-Aware and Multitask-Aware Single-Image-Based Action Recognition

Bhishan Bhandari    
Geonu Lee and Jungchan Cho    

Resumen

Action recognition is an application that, ideally, requires real-time results. We focus on single-image-based action recognition instead of video-based because of improved speed and lower cost of computation. However, a single image contains limited information, which makes single-image-based action recognition a difficult problem. To get an accurate representation of action classes, we propose three feature-stream-based shallow sub-networks (image-based, attention-image-based, and part-image-based feature networks) on the deep pose estimation network in a multitasking manner. Moreover, we design the multitask-aware loss function, so that the proposed method can be adaptively trained with heterogeneous datasets where only human pose annotations or action labels are included (instead of both pose and action information), which makes it easier to apply the proposed approach to new data on behavioral analysis on intelligent systems. In our extensive experiments, we showed that these streams represent complementary information and, hence, the fused representation is robust in distinguishing diverse fine-grained action classes. Unlike other methods, the human pose information was trained using heterogeneous datasets in a multitasking manner; nevertheless, it achieved 91.91% mean average precision on the Stanford 40 Actions Dataset. Moreover, we demonstrated the proposed method can be flexibly applied to multi-labels action recognition problem on the V-COCO Dataset.

 Artículos similares

       
 
Hui-Jun Kim, Jung-Soon Kim and Sung-Hee Kim    
The existing question-and-answer screening test has a limitation in that test accuracy varies due to a high learning effect and based on the inspector?s competency, which can have consequences for rapid-onset cognitive-related diseases. To solve this pro... ver más
Revista: Applied Sciences

 
Miao Feng and Jean Meunier    
Recognizing human actions can help in numerous ways, such as health monitoring, intelligent surveillance, virtual reality and human?computer interaction. A quick and accurate detection algorithm is required for daily real-time detection. This paper first... ver más
Revista: Algorithms

 
Shukai Li, Xiaofang Wang, Dongri Shan and Peng Zhang    
Temporal modeling is a key problem in action recognition, and it remains difficult to accurately model temporal information of videos. In this paper, we present a local spatiotemporal extraction module (LSTE) and a channel time excitation module (CTE), w... ver más
Revista: Applied Sciences

 
Abdorreza Alavigharahbagh, Vahid Hajihashemi, José J. M. Machado and João Manuel R. S. Tavares    
In this article, a hierarchical method for action recognition based on temporal and spatial features is proposed. In current HAR methods, camera movement, sensor movement, sudden scene changes, and scene movement can increase motion feature errors and de... ver más
Revista: Information

 
Hayat Ullah and Arslan Munir    
The recognition of human activities using vision-based techniques has become a crucial research field in video analytics. Over the last decade, there have been numerous advancements in deep learning algorithms aimed at accurately detecting complex human ... ver más
Revista: Algorithms