CRLC using random channel subsets for positive pairs in contrastive pretraining outperforms baselines for channel-agnostic models on EEG and ECG downstream tasks.
Multi-view self- supervised learning for multivariate variable-channel time series
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A comprehensive evaluation of pretraining strategies for channel-agnostic contrastive self-supervision of biosignals
CRLC using random channel subsets for positive pairs in contrastive pretraining outperforms baselines for channel-agnostic models on EEG and ECG downstream tasks.