Papers Self-supervised Skeleton-based Action Recognition
“Self-supervised Skeleton-based Action Recognition” 태그가 달린 논문 30편 · 필터 해제
Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition
In self-supervised skeleton-based action recognition, the mask reconstruction paradigm is gaining interest in enhancing model refinement and robustness through effective masking. However, previous works primarily relied …
3D Action RecognitionAction RecognitionSelf-supervised Skeleton-based Action RecognitionSkeleton Based Action RecognitionCross-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+5STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences
Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition. However, we show that, unlike contrastive learning approaches, they do no…
3D Action RecognitionAction RecognitionContrastive LearningDecoder+4Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments
To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions-a common yet often overlooked scenario in existing self-supervised skeleton-based action re…
Action RecognitionImputationSelf-Supervised LearningSelf-supervised Skeleton-based Action Recognition+2SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition
Contrastive learning has achieved great success in skeleton-based action recognition. However, most existing approaches encode the skeleton sequences as entangled spatiotemporal representations and confine the contrasts …
Action RecognitionContrastive LearningDisentanglementRetrieval+3Masked Motion Predictors are Strong 3D Action Representation Learners
In 3D human action recognition, limited supervised data makes it challenging to fully tap into the modeling potential of powerful networks such as transformers. As a result, researchers have been actively investigating e…
3D Action RecognitionAction RecognitionFew-Shot Skeleton-Based Action Recognitionmotion prediction+3SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current methods usually require sufficient labeled…
Action RecognitionDecoderRepresentation LearningSelf-supervised Skeleton-based Action Recognition+1Cross-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+6Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition
Self-supervised skeleton-based action recognition enjoys a rapid growth along with the development of contrastive learning. The existing methods rely on imposing invariance to augmentations of 3D skeleton within a single…
Action RecognitionContrastive LearningRepresentation LearningSelf-supervised Skeleton-based Action Recognition+1Part Aware Contrastive Learning for Self-Supervised Action Recognition
In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features…
Action RecognitionContrastive LearningData AugmentationRepresentation Learning+3Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition
Learning view-invariant representation is a key to improving feature discrimination power for skeleton-based action recognition. Existing approaches cannot effectively remove the impact of viewpoint due to the implicit v…
Action RecognitionContrastive LearningRepresentation LearningSelf-supervised Skeleton-based Action Recognition+1HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
Supervised learning of skeleton sequence encoders for action recognition has received significant attention in recent times. However, learning such encoders without labels continues to be a challenging problem. While pri…
Action RecognitionContrastive LearningLinear evaluationSelf-Supervised Learning+3Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition
The self-supervised pretraining paradigm has achieved great success in skeleton-based action recognition. However, these methods treat the motion and static parts equally, and lack an adaptive design for different parts,…
Action RecognitionContrastive LearningSelf-supervised Skeleton-based Action RecognitionSkeleton Based Action Recognition+1DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition
In this work, we propose a new Dual Min-Max Games (DMMG) based self-supervised skeleton action recognition method by augmenting unlabeled data in a contrastive learning framework. Our DMMG consists of a viewpoint variati…
Action RecognitionContrastive LearningData AugmentationSelf-supervised Skeleton-based Action Recognition+1Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
Self-supervised learning has demonstrated remarkable capability in representation learning for skeleton-based action recognition. Existing methods mainly focus on applying global data augmentation to generate different v…
Action RecognitionContrastive LearningData AugmentationRepresentation Learning+5Modeling 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+2Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning
This paper targets unsupervised skeleton-based action representation learning and proposes a new Hierarchical Contrast (HiCo) framework. Different from the existing contrastive-based solutions that typically represent an…
Action RecognitionFew-Shot Skeleton-Based Action RecognitionRepresentation LearningRetrieval+2Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations
Contrastive learning has been proven beneficial for self-supervised skeleton-based action recognition. Most contrastive learning methods utilize carefully designed augmentations to generate different movement patterns of…
Action RecognitionContrastive LearningFew-Shot Skeleton-Based Action RecognitionSelf-supervised Skeleton-based Action Recognition+1SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition
Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contras…
Action RecognitionDecoderSelf-supervised Skeleton-based Action RecognitionSkeleton Based Action RecognitionCMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
In 3D action recognition, there exists rich complementary information between skeleton modalities. Nevertheless, how to model and utilize this information remains a challenging problem for self-supervised 3D action repre…
3D Action RecognitionAction RecognitionFew-Shot Skeleton-Based Action RecognitionKnowledge Distillation+2