SAGE-Yoga is a unified coarse‑to‑fine framework that performs yoga pose classification and joint‑level correction from a single RGB image. It uses a bagging ensemble of complementary visual backbones to rank candidate pose classes, a margin‑based gating mechanism to selectively apply geometric verification, and a medoid reference pose to compare joint angles against class‑specific distributions. On the Yoga‑82 dataset, the ensemble achieves 89.0% Top‑1 accuracy, while the full system reaches 90.7% Top‑1 accuracy and 90.1% Macro‑F1, demonstrating improved fine‑grained classification and interpretable corrective feedback.
arXiv:2202. 14019v3 Announce Type: replace-cross Abstract: Maintaining proper form while exercising is important for preventing injuries and maximizing muscle mass gains.
arXiv:2606. 28104v1 Announce Type: cross Abstract: Vision-based assessment can provide convenient and cost-effective evaluation in Traditional Chinese Medicine (TCM) rehabilitation training, where action quality assessment (AQA) from computer vision offers a promising solution.
arXiv:2604.28130v4 Announce Type: replace Abstract: Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts join...
arXiv:2606. 31127v1 Announce Type: cross Abstract: To enable personalized, real-time coaching using Augmented Reality glasses or fixed camera setups in domains such as sports, cooking, or music, a system must understand not just what a person does, but how well they execute an activity.
arXiv:2605. 01720v3 Announce Type: replace-cross Abstract: Existing large-scale sign language resources typically provide supervision only at the level of raw video-text alignment and are often produced in laboratory settings.
arXiv:2609.24424v1 Announce Type: new Abstract: Monocular RGB-based hand pose estimation has emerged as a critical research frontier in computer vision. The local hand pose estimation methods predict...
arXiv:2609.07534v1 Announce Type: cross Abstract: Contact-rich assembly remains challenging because it requires submillimeter spatial accuracy and reliable interpretation of forces during sustained c...
arXiv:2609.35726v2 Announce Type: replace Abstract: Automated quality assessment of rehabilitation exercises relies heavily on accurate human pose estimation from video data. Although numerous RGB-ba...
arXiv:2606. 12988v1 Announce Type: cross Abstract: This paper introduces a new methodology for real-time prediction of ergonomic and non-ergonomic human poses using volumetric video data in three dimensions.
arXiv:2609.07534v2 Announce Type: replace-cross Abstract: Contact-rich assembly remains challenging because it requires submillimeter spatial accuracy and reliable interpretation of forces during sus...
arXiv:2601.13913v3 Announce Type: replace Abstract: We consider monocular 3D human pose estimation (HPE), where the goal is to predict 3D human skeletal joints from a single 2D image, typically via 2...
arXiv:2608.29928v1 Announce Type: new Abstract: State-of-the-art monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechan...