Skeleton Based Action Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 34
- 보존된 평가 기록
- 415
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.
<span style="color:grey; opacity: 0.6">( Image credit: View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
PGCN-TCA: Pseudo Graph Convolutional Network With Temporal and Channel-Wise Attention for Skeleton-Based Action Recognition
Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition
Self-Attention Network for Skeleton-based Human Action Recognition
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition
Totally Deep Support Vector Machines
View-Invariant Probabilistic Embedding for Human Pose
Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
An Attention-Enhanced Recurrent Graph Convolutional Network for Skeleton-Based Action Recognition
Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
Chirality Nets for Human Pose Regression
Deep Independently Recurrent Neural Network (IndRNN)
Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction
Learning Coupled Spatial-temporal Attention for Skeleton-based Action Recognition
Making the Invisible Visible: Action Recognition Through Walls and Occlusions
Adversarial Attack on Skeleton-based Human Action Recognition
Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks
Learning Latent Global Network for Skeleton-based Action Prediction
Graph Based Skeleton Modeling for Human Activity Analysis
Learning stochastic differential equations using RNN with log signature features
SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition
Make Skeleton-based Action Recognition Model Smaller, Faster and Better
Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
Learning Shape-Motion Representations from Geometric Algebra Spatio-Temporal Model for Skeleton-Based Action Recognition
A Comparative Review of Recent Kinect-based Action Recognition Algorithms
Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons
Towards a Skeleton-Based Action Recognition For Realistic Scenarios
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition
Simple yet efficient real-time pose-based action recognition
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.