A survey of video datasets for human action and activity recognition
JM Chaquet, EJ Carmona… - Computer Vision and …, 2013 - Elsevier
Vision-based human action and activity recognition has an increasing importance among
the computer vision community with applications to visual surveillance, video retrieval and …
the computer vision community with applications to visual surveillance, video retrieval and …
3D Human Action Recognition: Through the eyes of researchers
Abstract Human Action Recognition (HAR) has remained one of the most challenging tasks
in computer vision. With the surge in data-driven methodologies, the depth modality has …
in computer vision. With the surge in data-driven methodologies, the depth modality has …
Actional-structural graph convolutional networks for skeleton-based action recognition
Action recognition with skeleton data has recently attracted much attention in computer
vision. Previous studies are mostly based on fixed skeleton graphs, only capturing local …
vision. Previous studies are mostly based on fixed skeleton graphs, only capturing local …
Learning temporal regularity in video sequences
Perceiving meaningful activities in a long video sequence is a challenging problem due to
ambiguous definition ofmeaningfulness' as well as clutters in the scene. We approach this …
ambiguous definition ofmeaningfulness' as well as clutters in the scene. We approach this …
Symbiotic graph neural networks for 3d skeleton-based human action recognition and motion prediction
3D skeleton-based action recognition and motion prediction are two essential problems of
human activity understanding. In many previous works: 1) they studied two tasks separately …
human activity understanding. In many previous works: 1) they studied two tasks separately …
3D skeleton-based human action classification: A survey
LL Presti, M La Cascia - Pattern Recognition, 2016 - Elsevier
In recent years, there has been a proliferation of works on human action classification from
depth sequences. These works generally present methods and/or feature representations …
depth sequences. These works generally present methods and/or feature representations …
Factorized graph matching
F Zhou, F De la Torre - IEEE transactions on pattern analysis …, 2015 - ieeexplore.ieee.org
Graph matching (GM) is a fundamental problem in computer science, and it plays a central
role to solve correspondence problems in computer vision. GM problems that incorporate …
role to solve correspondence problems in computer vision. GM problems that incorporate …
Hypergraph neural network for skeleton-based action recognition
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 …
in the field of computer vision. Graph convolutional networks (GCNs), which model the …
Joint-Relation Transformer for Multi-Person Motion Prediction
Multi-person motion prediction is a challenging problem due to the dependency of motion on
both individual past movements and interactions with other people. Transformer-based …
both individual past movements and interactions with other people. Transformer-based …
Multi-scale mixed dense graph convolution network for skeleton-based action recognition
H Xia, X Gao - Ieee Access, 2021 - ieeexplore.ieee.org
In skeleton-based action recognition, the approaches based on graph convolutional
networks (GCN) have achieved remarkable performance by modeling spatial-temporal …
networks (GCN) have achieved remarkable performance by modeling spatial-temporal …