MOSAIC proposes modality-specific warm-up, statistics-decoupled batch normalization, and curriculum-guided repulsive objectives to support incremental addition of sensor modalities in PD gait assessment while reducing forgetting.
Towards re- laxed multimodal inputs for gait-based parkinson’s disease assessment,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MOSAIC: Modality-Specific Adaptation for Incremental Continual Learning in Parkinson's Disease Gait Assessment
MOSAIC proposes modality-specific warm-up, statistics-decoupled batch normalization, and curriculum-guided repulsive objectives to support incremental addition of sensor modalities in PD gait assessment while reducing forgetting.