Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

Abstract

Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer. In Human Action Recognition (HAR), attention mechanisms have been primarily adopted on top of standard convolutional or recurrent layers, improving the overall generalization capability. In this work, we introduce Action Transformer (AcT), a simple, fully self-attentional architecture that consistently outperforms more elaborated networks that mix convolutional, recurrent and attentive layers. In order to limit computational and energy requests, building on previous human action recognition research, the proposed approach exploits 2D pose representations over small temporal windows, providing a low latency solution for accurate and effective real-time performance. Moreover, we open-source MPOSE2021, a new large-scale dataset, as an attempt to build a formal training and evaluation benchmark for real-time, short-time HAR. The proposed methodology was extensively tested on MPOSE2021 and compared to several state-of-the-art architectures, proving the effectiveness of the AcT model and laying the foundations for future work on HAR.

Published by Pattern Recognition, Elsevier

References in corpus (6)

• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
• ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
• Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition
• Keyword Transformer: A Self-Attention Model for Keyword Spotting
• Robust Ultra-wideband Range Error Mitigation with Deep Learning at the Edge
• Driving Behavior Explanation with Multi-level Fusion

Cited by in corpus (6)

• Deep learning for 3D human pose estimation and mesh recovery: A survey
• SMART-Vision: Survey of Modern Action Recognition Techniques in Vision
• PowerSkel: A Device-Free Framework Using CSI Signal for Human Skeleton Estimation in Power Station
• Kinematics Modeling Network for Video-based Human Pose Estimation
• Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks
• On the Relevance of Temporal Features for Medical Ultrasound Video Recognition