Using gradient saliency and pretrained video/time-series models, frame-level stroke exercise quality can be learned from video-level labels, with the best configuration reaching 72% AUC versus 69% for a ground-truth-trained baseline.
Qualitative analysis of stroke patients’ motivation for rehabilitation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Frame-Level Real-Time Assessment of Stroke Rehabilitation Exercises from Video-Level Labeled Data: Task-Specific vs. Foundation Models
Using gradient saliency and pretrained video/time-series models, frame-level stroke exercise quality can be learned from video-level labels, with the best configuration reaching 72% AUC versus 69% for a ground-truth-trained baseline.