Human action recognition from various data modalities: A review
Human Action Recognition (HAR) aims to understand human behavior and assign a label to
each action. It has a wide range of applications, and therefore has been attracting increasing …
each action. It has a wide range of applications, and therefore has been attracting increasing …
Convolutional neural networks or vision transformers: Who will win the race for action recognitions in visual data?
Understanding actions in videos remains a significant challenge in computer vision, which
has been the subject of several pieces of research in the last decades. Convolutional neural …
has been the subject of several pieces of research in the last decades. Convolutional neural …
Revisiting skeleton-based action recognition
Human skeleton, as a compact representation of human action, has received increasing
attention in recent years. Many skeleton-based action recognition methods adopt GCNs to …
attention in recent years. Many skeleton-based action recognition methods adopt GCNs to …
Infogcn: Representation learning for human skeleton-based action recognition
Human skeleton-based action recognition offers a valuable means to understand the
intricacies of human behavior because it can handle the complex relationships between …
intricacies of human behavior because it can handle the complex relationships between …
Learning discriminative representations for skeleton based action recognition
Human action recognition aims at classifying the category of human action from a segment
of a video. Recently, people have dived into designing GCN-based models to extract …
of a video. Recently, people have dived into designing GCN-based models to extract …
Star-transformer: a spatio-temporal cross attention transformer for human action recognition
In action recognition, although the combination of spatio-temporal videos and skeleton
features can improve the recognition performance, a separate model and balancing feature …
features can improve the recognition performance, a separate model and balancing feature …
Multi-granularity anchor-contrastive representation learning for semi-supervised skeleton-based action recognition
In the semi-supervised skeleton-based action recognition task, obtaining more
discriminative information from both labeled and unlabeled data is a challenging problem …
discriminative information from both labeled and unlabeled data is a challenging problem …
Motionbert: A unified perspective on learning human motion representations
We present a unified perspective on tackling various human-centric video tasks by learning
human motion representations from large-scale and heterogeneous data resources …
human motion representations from large-scale and heterogeneous data resources …
Skeletonmae: graph-based masked autoencoder for skeleton sequence pre-training
Skeleton sequence representation learning has shown great advantages for action
recognition due to its promising ability to model human joints and topology. However, the …
recognition due to its promising ability to model human joints and topology. However, the …
A union of deep learning and swarm-based optimization for 3D human action recognition
Abstract Human Action Recognition (HAR) is a popular area of research in computer vision
due to its wide range of applications such as surveillance, health care, and gaming, etc …
due to its wide range of applications such as surveillance, health care, and gaming, etc …