Skeleton Based Action Recognition
175 papers with code • 34 benchmarks • 29 datasets
Skeleton-based Action Recognition is a computer vision task that involves recognizing human actions from a sequence of 3D skeletal joint data captured from sensors such as Microsoft Kinect, Intel RealSense, and wearable devices. The goal of skeleton-based action recognition is to develop algorithms that can understand and classify human actions from skeleton data, which can be used in various applications such as human-computer interaction, sports analysis, and surveillance.
( Image credit: View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition )
Benchmarks
These leaderboards are used to track progress in Skeleton Based Action Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Skeleton Based Action Recognition models and implementationsDatasets
UCF101
Kinetics
HMDB51
Kinetics 400
NTU RGB+D
JHMDB
Penn Action
NTU RGB+D 120
SBU
UT-Kinect
Most implemented papers
Generative Action Description Prompts for Skeleton-based Action Recognition
More specifically, we employ a pre-trained large-scale language model as the knowledge engine to automatically generate text descriptions for body parts movements of actions, and propose a multi-modal training scheme by utilizing the text encoder to generate feature vectors for different body parts and supervise the skeleton encoder for action representation learning.
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition
Graph convolution networks (GCN) have been widely used in skeleton-based action recognition.
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
The proposed method is generic and principled as it can be used for transforming any spatio-temporal graph through employing a certain set of well defined steps.
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes.
Relational Autoencoder for Feature Extraction
Feature extraction becomes increasingly important as data grows high dimensional.
View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
microsoft/View-Adaptive-Neural-Networks-for-Skeleton-based-Human-Action-Recognition
•
•
In order to alleviate the effects of view variations, this paper introduces a novel view adaptation scheme, which automatically determines the virtual observation viewpoints in a learning based data driven manner.
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data.
Multigrid Predictive Filter Flow for Unsupervised Learning on Videos
aimerykong/predictive-filter-flow
•
•
We introduce multigrid Predictive Filter Flow (mgPFF), a framework for unsupervised learning on videos.
View-Invariant Probabilistic Embedding for Human Pose
google-research/google-research
•
•
ECCV 2020
Depictions of similar human body configurations can vary with changing viewpoints.
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
lshiwjx/2s-AGCN
•
•
Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.
