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/ZichenMiao/L3Net

공식 코드

Graph Convolution with Low-rank Learnable Local Filters

https://github.com/ZiweiXU/CapsuleMotion

공식 코드

Unsupervised Motion Representation Learning with Capsule Autoencoders

https://github.com/adeboissiere/FUSION-human-action-recognition

공식 코드

Infrared and 3D skeleton feature fusion for RGB-D action recognition

https://github.com/againerju/tcg_recognition

공식 코드

Traffic Control Gesture Recognition for Autonomous Vehicles

https://github.com/aikuniverse/tcte-net

공식 코드

Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition

https://github.com/airglow/gimme_signals_action_recognition

공식 코드

Gimme Signals: Discriminative signal encoding for multimodal activity recognition

https://github.com/andreYoo/PeGCNs

공식 코드

Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition

https://github.com/anshulbshah/PoseAction

공식 코드

Pose And Joint-Aware Action Recognition

https://github.com/anshulbshah/halp

공식 코드

HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions

https://github.com/asheshjain399/RNNexp

공식 코드

Structural-RNN: Deep Learning on Spatio-Temporal Graphs

https://github.com/azzh1/purls

공식 코드

Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition

https://github.com/bmartacho/UniPose

공식 코드

UniPose: Unified Human Pose Estimation in Single Images and Videos

https://github.com/buptsjzhang/std-cl

공식 코드

Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action Recognition

https://github.com/buptsjzhang/ta-mlp

공식 코드

SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition

https://github.com/canbaoburen/CoDT

공식 코드

Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition

https://github.com/carloscaetano/skeleton-images

공식 코드

SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition

https://github.com/cyfml/opstl

공식 코드

Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments

https://github.com/czhaneva/mst-gcn

공식 코드

Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

https://github.com/czhaneva/skelemixclr

공식 코드

Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition

https://github.com/damnull/lagcn

공식 코드

Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition

https://github.com/deepinmotion/autogcn

공식 코드

AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture Search

https://github.com/deepintostreams/gcn-devlstm

공식 코드

GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition

https://github.com/desehuileng0o0/ikem

공식 코드

Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision

https://github.com/dluvizon/deephar

공식 코드

Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition

https://github.com/fabienbaradel/glimpse_clouds

공식 코드

Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points

https://github.com/fandulu/DD-Net

공식 코드

Make Skeleton-based Action Recognition Model Smaller, Faster and Better

https://github.com/firework8/brl

공식 코드

Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition

https://github.com/fmthoker/skeleton-contrast

공식 코드

Skeleton-Contrastive 3D Action Representation Learning

https://github.com/githubofhyl97/skeattnclr

공식 코드

Part Aware Contrastive Learning for Self-Supervised Action Recognition

https://github.com/google-research/google-research

공식 코드

View-Invariant Probabilistic Embedding for Human Pose

https://github.com/haohuang2003/sfhead

공식 코드

Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition

https://github.com/heleiqiu/sttformer

공식 코드

Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition

https://github.com/hikvision-research/skelact

공식 코드

Skeleton-based Action Recognition with Convolutional Neural Networks

https://github.com/holzbock/st_mlp

공식 코드

A Spatio-Temporal Multilayer Perceptron for Gesture Recognition

https://github.com/hongyan1123/skeletonmae

공식 코드

SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training

https://github.com/huiguanlab/hico

공식 코드

Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning

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