TL;DR
HPCLR is a hierarchical part-aware contrastive learning framework for skeleton-based action recognition that leverages the consistency among joint, motion, and bone modalities to select more reliable positive samples, thereby contributing to more stable and informative multi-stream skeleton representations.
This work presents a novel self-supervised architecture centered on graph prototype learning that sets a new state-of-the-art on the ARMM dataset with an accuracy of 95.70%, substantiating the efficacy and transferability of prototype-guided self-supervised learning for skeleton-based action representation.
This work proposes MEMC (Masked Modeling with Efficient and Minimal Contrastive Learning), a novel framework that adopts an efficient sequential cascade strategy based on layer-grafted pretraining and introduces two CL enhancements to improve the discriminative capability of the learned representations.
FineX is introduced, which factorizes fine-grained cues into RGB appearance, pose heatmap geometry, and skeletal-graph topology and raises mean class accuracy on Gym99, Gym288, and Diving48 without textual supervision or large-scale vision-language pre-training.
Multimodal human activity recognition (HAR) benefits from complementary skeleton, inertial, and visual observations. However, many learning-based models still treat relationships among modalities, joints, and sensor variables as symmetric associations. This limits their ability to represent asymmetric information flow...
A novel and effective representation is presented that captures action-related information in the pipeline of HAR without any extra annotation overhead beyond the existing skeleton extraction and achieves significantly higher HAR accuracy with similar compactness and efficiency as compared with the state-of-the-art ske...
Comprehensive ablation studies reveal that the architectural innovations and the stability protocol contribute complementarily, and that BPA-STGCN achieves the best accuracy–stability trade-off among all tested configurations.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
