3D Action Recognition

32 papers with code • 2 benchmarks • 13 datasets

Image: Rahmani et al

Libraries

Use these libraries to find 3D Action Recognition models and implementations
2 papers
3,831

Latest papers with no code

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

no code yet • 15 Mar 2024

Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e. g., joint location), and may suffer from local information loss and low generalization ability.

Learning Scene Flow With Skeleton Guidance For 3D Action Recognition

no code yet • 23 Jun 2023

Among the existing modalities for 3D action recognition, 3D flow has been poorly examined, although conveying rich motion information cues for human actions.

Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization

no code yet • 18 Apr 2023

We investigate self-supervised representation learning and design a novel skeleton cloud colorization technique that is capable of learning spatial and temporal skeleton representations from unlabeled skeleton sequence data.

Spatial-Temporal Transformer for 3D Point Cloud Sequences

no code yet • 19 Oct 2021

We test the effectiveness our PST2 with two different tasks on point cloud sequences, i. e., 4D semantic segmentation and 3D action recognition.

Unsupervised View-Invariant Human Posture Representation

no code yet • 17 Sep 2021

Most recent view-invariant action recognition and performance assessment approaches rely on a large amount of annotated 3D skeleton data to extract view-invariant features.

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

no code yet • ICCV 2021

We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data.

Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model

no code yet • 24 May 2021

To tackle all these problems, we propose a real-time 3D action recognition framework by integrating the locally aggregated kinematic-guided skeletonlet (LAKS) with a supervised hashing-by-analysis (SHA) model.

Independent Sign Language Recognition with 3D Body, Hands, and Face Reconstruction

no code yet • 24 Nov 2020

Independent Sign Language Recognition is a complex visual recognition problem that combines several challenging tasks of Computer Vision due to the necessity to exploit and fuse information from hand gestures, body features and facial expressions.

VI-Net: View-Invariant Quality of Human Movement Assessment

no code yet • 11 Aug 2020

We propose a view-invariant method towards the assessment of the quality of human movements which does not rely on skeleton data.

Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

no code yet • ECCV 2020

Self-supervised learning (SSL) has been proved very effective at learning representations from unlabeled data in the image domain.