Skeleton Based Action Recognition
34개 벤치마크 · 논문 419편 · 이 태스크의 논문 보기 →
Benchmarks
NTU RGB+D
NTU RGB+D 120
Kinetics-Skeleton dataset
N-UCLA
J-HMDB
SBU / SBU-Refine
SYSU 3D
UAV-Human
CAD-120
Florence 3D
UT-Kinect
JHMDB (2D poses only)
PKU-MMD
Gaming 3D (G3D)
H2O (2 Hands and Objects)
MSR Action3D
JHMDB Pose Tracking
NTU60-X
UPenn Action
UWA3D
Drive&Act
HMDB51
J-HMBD Early Action
MSRC-12
TCG-dataset
UCF101
HDM05
Kinetics-400
MSR ActionPairs
Skeletics-152
Skeleton-Mimetics
Most implemented
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Graph Attention Networks
Semi-Supervised Classification with Graph Convolutional Networks
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Papers
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment
Zero-shot skeleton-based action recognition aims to classify unseen skeleton-based human actions without prior exposure to such categories during training. This task is extremely challenging due to the difficulty in gene…
Action RecognitionOne-Shot 3D Action RecognitionSkeleton Based Action RecognitionTransfer Learning+2Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition
Effective human action recognition is widely used for cobots in Industry 4.0 to assist in assembly tasks. However, conventional skeleton-based methods often lose keypoint semantics, limiting their effectiveness in comple…
Action RecognitionSkeleton Based Action RecognitionTemporal Action LocalizationWord Embeddings3D Skeleton-Based Action Recognition: A Review
With the inherent advantages of skeleton representation, 3D skeleton-based action recognition has become a prominent topic in the field of computer vision. However, previous reviews have predominantly adopted a model-ori…
Action RecognitionData AugmentationMambaSkeleton Based Action RecognitionSpatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
Traditional approaches in unsupervised or self supervised learning for skeleton-based action classification have concentrated predominantly on the dynamic aspects of skeletal sequences. Yet, the intricate interaction bet…
Action ClassificationAction RecognitionContrastive LearningSelf-Supervised Learning+1SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation
While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. These challenges are particularly pronounced…
Action RecognitionOne-Shot 3D Action RecognitionSkeleton Based Action RecognitionAction Recognition in Real-World Ambient Assisted Living Environment
The growing ageing population and their preference to maintain independence by living in their own homes require proactive strategies to ensure safety and support. Ambient Assisted Living (AAL) technologies have emerged …
Action RecognitionComputational EfficiencyData AugmentationHand Gesture Recognition+1