3D Action Recognition
34 papers with code • 3 benchmarks • 14 datasets
Image: Rahmani et al
Benchmarks
These leaderboards are used to track progress in 3D Action Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Action Recognition models and implementationsDatasets
NTU RGB+D
BABEL
UAV-Human
Assembly101
Florence3D
Navigation Turing Test
FR-FS
3DYoga90
Fitness-AQA
MultiviewC
Subtasks
Latest papers
Deep Hierarchical Representation of Point Cloud Videos via Spatio-Temporal Decomposition
hehefan/PSTNet2
•
•
IEEE Transactions on Pattern Analysis and Machine Intelligence 2021
Specifically, a spatial operation is employed to capture the local structure of each spatial region in a tube and a temporal operation is used to model the dynamics of the spatial regions along the tube.
3DVNet: Multi-View Depth Prediction and Volumetric Refinement
Furthermore, unlike existing volumetric MVS techniques, our 3D CNN operates on a feature-augmented point cloud, allowing for effective aggregation of multi-view information and flexible iterative refinement of depth maps.
Real-time 3D human action recognition based on Hyperpoint sequence
xingli1012/sequentialpointnet
•
•
Instead of capturing spatio-temporal local structures, SequentialPointNet encodes the temporal evolution of static appearances to recognize human actions.
Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos
hehefan/P4Transformer
•
•
CVPR 2021
To capture the dynamics in point cloud videos, point tracking is usually employed.
BABEL: Bodies, Action and Behavior with English Labels
abhinanda-punnakkal/BABEL
•
•
CVPR 2021
To address this, we present BABEL, a large dataset with language labels describing the actions being performed in mocap sequences.
Revisiting Skeleton-based Action Recognition
open-mmlab/mmaction2
•
•
CVPR 2022
In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons.
Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition
Although various methods have been proposed for 3D action recognition, some of which are basic and some use deep learning, the need of basic methods based on generalized eigenvalue problem is sensed for action recognition.
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.
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly.
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
kennymckormick/pyskl
•
•
CVPR 2020
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics.
