paper-with-me

Papers Unsupervised Skeleton Based Action Recognition

“Unsupervised Skeleton Based Action Recognition” 태그가 달린 논문 11편 · 필터 해제

Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition

2024-01-25 · Chuankun Li, Shuai Li, Yanbo Gao, Ping Chen 외

Unsupervised skeleton based action recognition has achieved remarkable progress recently. Existing unsupervised learning methods suffer from severe overfitting problem, and thus small networks are used, significantly red…

Action RecognitionSkeleton Based Action RecognitionUnsupervised Skeleton Based Action Recognition

Attack-Augmentation Mixing-Contrastive Skeletal Representation Learning

2023-04-08 · Binqian Xu, Xiangbo Shu, Jiachao Zhang, Rui Yan 외

Contrastive learning, relying on effective positive and negative sample pairs, is beneficial to learn informative skeleton representations in unsupervised skeleton-based action recognition. To achieve these positive and …

Action RecognitionContrastive LearningData AugmentationRepresentation Learning+2

Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition

2023-03-20 · CVPR 2023 1 · Lilang Lin, Jiahang Zhang, Jiaying Liu

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+1

HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations

2023-03-10 · Luca Franco, Paolo Mandica, Bharti Munjal, Fabio Galasso

Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the training sample sequence, from easy to comple…

Action RecognitionDomain AdaptationSkeleton Based Action RecognitionUnsupervised Skeleton Based Action Recognition+1

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

2022-07-20 · Qinying Liu, Zilei Wang

In this work, we consider the problem of cross-domain 3D action recognition in the open-set setting, which has been rarely explored before. Specifically, there is a source domain and a target domain that contain the skel…

3D Action RecognitionAction RecognitionClusteringContrastive Learning+7

Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance

2022-04-21 · Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan, Alessio Del Bue

This paper presents a novel end-to-end method for the problem of skeleton-based unsupervised human action recognition. We propose a new architecture with a convolutional autoencoder that uses graph Laplacian regularizati…

Action RecognitionSkeleton Based Action RecognitionTemporal Action LocalizationUnsupervised Skeleton Based Action Recognition

Bootstrapped Representation Learning for Skeleton-Based Action Recognition

2022-02-04 · Olivier Moliner, Sangxia Huang, Kalle Åström

In this work, we study self-supervised representation learning for 3D skeleton-based action recognition. We extend Bootstrap Your Own Latent (BYOL) for representation learning on skeleton sequence data and propose a new …

Action RecognitionData AugmentationKnowledge DistillationLinear evaluation+3

Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition

2021-11-22 · Peng Wang, Jun Wen, Chenyang Si, Yuntao Qian 외

Skeleton-based action recognition is widely used in varied areas, e.g., surveillance and human-machine interaction. Existing models are mainly learned in a supervised manner, thus heavily depending on large-scale labeled…

Action RecognitionContrastive LearningKnowledge DistillationRepresentation Learning+3

Unsupervised Motion Representation Learning with Capsule Autoencoders

2021-10-01 · NeurIPS 2021 12 · Ziwei Xu, Xudong Shen, Yongkang Wong, Mohan S Kankanhalli

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

Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition

2020-11-14 · Shihao Xu, Haocong Rao, Xiping Hu, Bin Hu

In this paper, we focus on unsupervised representation learning for skeleton-based action recognition. Existing approaches usually learn action representations by sequential prediction but they suffer from the inability …

Action RecognitionClusteringPredictionRepresentation Learning+5

PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition

2019-11-27 · CVPR 2020 6 · Kun Su, Xiulong Liu, Eli Shlizerman

We propose a novel system for unsupervised skeleton-based action recognition. Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions. Our system is ba…

Action RecognitionDecoderSelf-Supervised Human Action RecognitionSelf-supervised Skeleton-based Action Recognition+2
1–11 / 11