MoRA is a new retrieval-augmented module for IMU-based human activity recognition that uses uncertainty-adaptive fusion of retrieved motion patterns to improve model performance.
Mantis: Lightweight calibrated foundation model for user-friendly time series classification
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
COMODO is a cross-modal self-supervised distillation framework that uses a frozen video encoder and dynamic instance queue to align video and IMU embeddings, improving IMU-based egocentric HAR to match supervised performance.
citing papers explorer
-
Modular Retrieval-Augmented Generalization for Human Action Recognition
MoRA is a new retrieval-augmented module for IMU-based human activity recognition that uses uncertainty-adaptive fusion of retrieved motion patterns to improve model performance.
-
COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition
COMODO is a cross-modal self-supervised distillation framework that uses a frozen video encoder and dynamic instance queue to align video and IMU embeddings, improving IMU-based egocentric HAR to match supervised performance.
- TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis