Proceedings of the AAAI Conference on Artificial Intelligence · 2023 · 46 citations · 37 references
ComputingVision ScienceComputer VisionRobot LearningVisual RepresentationAction RecognitionMotion AnalysisRepresentation LearningSelf-supervised LearningSequence LearningVideo AnalysisContrastive LearningData AugmentationMotion AttentionSelf-supervised Action RecognitionSelf-supervised Representation LearningSkeleton-based Action RecognitionSpatial MaskingSpatio-temporal Representation
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 views of the skeleton sequence for contrastive learning. However, due to the rich action clues in the skeleton sequences, existing methods may only take a global perspective to learn to discriminate different skeletons without thoroughly leveraging the local relationship between different skeleton joints and video frames, which is essential for real-world applications. In this work, we propose a Partial Spatio-Temporal Learning (PSTL) framework to exploit the local relationship from a partial skeleton sequences built by a unique spatio-temporal masking strategy. Specifically, we construct a negative-sample-free triplet steam structure that is composed of an anchor stream without any masking, a spatial masking stream with Central Spatial Masking (CSM), and a temporal masking stream with Motion Attention Temporal Masking (MATM). The feature cross-correlation matrix is measured between the anchor stream and the other two masking streams, respectively. (1) Central Spatial Masking discards selected joints from the feature calculation process, where the joints with a higher degree of centrality have a higher possibility of being selected. (2) Motion Attention Temporal Masking leverages the motion of action and remove frames that move faster with a higher possibility. Our method achieves state-of-the-art performance on NTURGB+D 60, NTURGB+D 120 and PKU-MMD under various downstream tasks. Furthermore, to simulate the real-world scenarios, a practical evaluation is performed where some skeleton joints are lost in downstream tasks.In contrast to previous methods that suffer from large performance drops, our PSTL can still achieve remarkable results under this challenging setting, validating the robustness of our method.
37
Momentum Contrast for Unsupervised Visual Representation Learning
Kaiming He, Haoqi Fan, Yuxin Wu et al. · 2020 · 12K citations
A Simple Framework for Contrastive Learning of Visual Representations
Ting Chen, Simon Kornblith, Mohammad Norouzi et al. · arXiv (Cornell University) · 2020 · 7.3K citations · Full text
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Zhe Cao, Tomas Simon, Shih-En Wei et al. · 2017 · 7.3K citations
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Amir Shahroudy, Jun Liu, Tian-Tsong Ng et al. · 2016 · 2.9K citations