Self-supervised Skeleton-based Action Recognition
21 papers with code • 2 benchmarks • 2 datasets
NTU RGB+D
NTU RGB+D 120
Most implemented papers
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
Mikexu007/AS_CAL
•
•
In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised manner.
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
levigty/acl
•
•
Inspired by SkeletonBYOL, this paper further presents a Cross-Model and Cross-Stream (CMCS) framework.
PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
shlizee/Predict-Cluster
•
•
CVPR 2020
Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions.
Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement
NIEQiang001/unsupervised-human-pose
•
•
ECCV 2020
Learning a good 3D human pose representation is important for human pose related tasks, e. g. human 3D pose estimation and action recognition.
3D Human Action Representation Learning via Cross-View Consistency Pursuit
LinguoLi/CrosSCLR
•
•
CVPR 2021
In this work, we propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR), by leveraging multi-view complementary supervision signal.
Skeleton-Contrastive 3D Action Representation Learning
fmthoker/skeleton-contrast
•
•
In particular, we propose inter-skeleton contrastive learning, which learns from multiple different input skeleton representations in a cross-contrastive manner.
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
levigty/aimclr
•
•
In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR) is proposed.
Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition
First, SkeleMix utilizes the topological information of skeleton data to mix two skeleton sequences by randomly combing the cropped skeleton fragments (the trimmed view) with the remaining skeleton sequences (the truncated view).
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
maoyunyao/cmd
•
•
In this work, we formulate the cross-modal interaction as a bidirectional knowledge distillation problem.
Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations
JHang2020/HiCLR
•
•
In this paper, we investigate the potential of adopting strong augmentations and propose a general hierarchical consistent contrastive learning framework (HiCLR) for skeleton-based action recognition.
