3D Action Recognition
29 papers with code • 2 benchmarks • 13 datasets
Image: Rahmani et al
Benchmarks
These leaderboards are used to track progress in 3D Action Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Datasets
BABEL
UAV-Human
Assembly101
Florence3D
FR-FS
Navigation Turing Test
Fitness-AQA
3DYoga90
MultiviewC
FLAG3D
Subtasks
Most implemented papers
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
adityac94/Grad_CAM_plus_plus
•
•
Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.
Unsupervised Learning of Object Keypoints for Perception and Control
deepmind/deepmind-research
•
•
NeurIPS 2019
In this work we aim to learn object representations that are useful for control and reinforcement learning (RL).
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
kenziyuliu/ms-g3d
•
•
CVPR 2020
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics.
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
benedekrozemberczki/pytorch_geometric_temporal
•
•
CVPR 2019
In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.
Reconstructing undersampled photoacoustic microscopy images using deep learning
axd465/PAM_Deep_Learning_Undersampling_Publication
•
•
One primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed.
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.
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
In this work, we propose to use a new class of models known as Temporal Convolutional Neural Networks (TCN) for 3D human action recognition.
Investigation of Different Skeleton Features for CNN-based 3D Action Recognition
The proposed method achieved state-of-the-art performance on NTU RGB+D dataset for 3D human action analysis.
Recognizing Involuntary Actions from 3D Skeleton Data Using Body States
This method introduces the definition of body states and then every action is modeled as a sequence of these states.
Fisherposes for Human Action Recognition Using Kinect Sensor Data
The proposed regularized Mahalanobis distance metric is used in order to recognize both the involuntary and highly made-up actions at the same time.
