Papers with Code 아카이브

Skeleton Based Action Recognition

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/nntanaka/Fourier-Analysis-for-Skeleton-based-Action-Recognition

공식 코드

Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition

https://github.com/noboevbo/ehpi_action_recognition

공식 코드

Simple yet efficient real-time pose-based action recognition

https://github.com/oliverhxh/skeletongcl

공식 코드

Graph Contrastive Learning for Skeleton-based Action Recognition

https://github.com/opengvlab/hulk

공식 코드

Hulk: A Universal Knowledge Translator for Human-Centric Tasks

https://github.com/opengvlab/humanbench

공식 코드

Hulk: A Universal Knowledge Translator for Human-Centric Tasks

https://github.com/ostadabbas/video-based-infant-action-recognition

공식 코드

Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art

https://github.com/osvai/ske2grid

공식 코드

Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition

https://github.com/outsiders17711/e2eet-skeleton-based-hgr-using-data-level-fusion

공식 코드

Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN

https://github.com/paolomandica/hysp

공식 코드

HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations

https://github.com/pha123661/SA-DVAE

공식 코드

SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders

https://github.com/realcrane/SMART

공식 코드

Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack

https://github.com/ruizhuo-xu/skeleton2vec

공식 코드

Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence

https://github.com/sfadingz/tse_gcn

공식 코드

Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition

https://github.com/shahroudy/NTURGB-D

공식 코드

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

https://github.com/shanakarg/stjd-spatio-temporal-joint-density-driven-learning-for-skeleton-based-action-recognition

공식 코드

Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition

https://github.com/shanice-l/st-cubism

공식 코드

Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition

https://github.com/skelemoa/ntu-x

공식 코드

NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actions

https://github.com/skelemoa/psumnet

공식 코드

PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition

https://github.com/skelemoa/quovadis

공식 코드

Quo Vadis, Skeleton Action Recognition ?

https://github.com/sperimental3/charon

공식 코드

Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning

https://github.com/srijandas07/VPN

공식 코드

VPN: Learning Video-Pose Embedding for Activities of Daily Living

https://github.com/srijandas07/vpnplusplus

공식 코드

VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living

https://github.com/steveliao93/gcn_logsigrnn

공식 코드

Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition

https://github.com/stnoah1/infogcn2

공식 코드

InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition

https://github.com/stnoah1/sode

공식 코드

InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition

https://github.com/stoa-xh91/acfl

공식 코드

Skeleton-based Action Recognition via Adaptive Cross-Form Learning

https://github.com/tailin1009/dualhead-network

공식 코드

Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition

https://github.com/tecsar-uncc/adg-pose

공식 코드

ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation

https://github.com/tkipf/pygcn

공식 코드

Semi-Supervised Classification with Graph Convolutional Networks

https://github.com/vvhj/tsgcnext

공식 코드

TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential

https://github.com/wengwanjiang/usdrl

공식 코드

USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation

https://github.com/wenhanwu95/freqmixformer

공식 코드

Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer

https://github.com/wiktormucha/SHARP

공식 코드

SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition

https://github.com/wiktormucha/effhandegonet

공식 코드

In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition

https://github.com/xh20/HAGCN

공식 코드

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

https://github.com/xuyankun/stvig-for-reads-v

공식 코드

VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.