Self-Supervised Human Action Recognition
1개 벤치마크 · 논문 9편 · 이 태스크의 논문 보기 →
Benchmarks
NTU RGB+D 120
Most implemented
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
Unsupervised Motion Representation Learning with Capsule Autoencoders
Papers
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
Considering the instance-level discriminative ability, contrastive learning methods, including MoCo and SimCLR, have been adapted from the original image representation learning task to solve the self-supervised skeleton…
Action RecognitionContrastive LearningEnsemble LearningPseudo Label+5Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
Considering the instance-level discriminative ability, contrastive learning methods, including MoCo and SimCLR, have been adapted from the original image representation learning task to solve the self-supervised skeleton…
Action RecognitionContrastive LearningEnsemble LearningPseudo Label+6Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition
Contrastive learning has been successfully leveraged to learn action representations for addressing the problem of semi-supervised skeleton-based action recognition. However, most contrastive learning-based methods only …
Action RecognitionContrastive LearningSelf-Supervised Human Action RecognitionSkeleton Based Action RecognitionModeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition
Visual tempo characterizes the dynamics and the temporal evolution, which helps describe actions. Recent approaches directly perform visual tempo prediction on skeleton sequences, which may suffer from insufficient f…
Action RecognitionContrastive LearningData AugmentationSelf-Supervised Human Action Recognition+2Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal aug…
Action RecognitionContrastive LearningFew-Shot Skeleton-Based Action RecognitionRepresentation Learning+4Unsupervised Motion Representation Learning with Capsule Autoencoders
We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the low…
Action RecognitionRepresentation LearningSelf-Supervised Human Action RecognitionSkeleton Based Action Recognition+1