Understanding human actions in visual data is tied to advances in complementary research
areas including object recognition, human dynamics, domain adaptation and semantic …

Video-based human action recognition is currently one of the most active research areas in
computer vision. Various research studies indicate that the performance of action …

This paper presents a new method for 3D action recognition with skeleton sequences (ie, 3D
trajectories of human skeleton joints). The proposed method first transforms each skeleton …

In this paper, we propose a deep progressive reinforcement learning (DPRL) method for
action recognition in skeleton-based videos, which aims to distil the most informative frames …

Abstract Long Short-Term Memory (LSTM) networks have shown superior performance in
3D human action recognition due to their power in modeling the dynamics and …

Human action recognition in 3D skeleton sequences has attracted a lot of research attention.
Recently, long short-term memory (LSTM) networks have shown promising performance in …

Many few-shot learning models focus on recognising images. In contrast, we tackle a
challenging task of few-shot action recognition from videos. We build on a C3D encoder for …

This paper presents a new representation of skeleton sequences for 3D action recognition.
Existing methods based on hand-crafted features or recurrent neural networks cannot …

Recently, skeleton-based human action recognition has attracted a lot of research attention
in the field of computer vision. Graph convolutional networks (GCNs), which model the …

Skeleton sequences are lightweight and compact and thus are ideal candidates for action
recognition on edge devices. Recent skeleton-based action recognition methods extract …