Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
Paper • 2506.08641 • Published
Vasilii Feofanov
vasilii-feofanov
AI & ML interests
time series foundation models, unsupervised analysis of pre-trained models, self-training algorithms
Recent Activity
authored a paper 7 days ago
Time Series Representations for Classification Lie Hidden in Pretrained
Vision Transformers authored a paper 7 days ago
CauKer: classification time series foundation models can be pretrained
on synthetic data only authored a paper 7 days ago
Self-Training: A SurveyOrganizations
authored 4
papers 7 days ago
authored 3
papers about 1 year ago
Mantis: Lightweight Calibrated Foundation Model for User-Friendly Time Series Classification
Paper • 2502.15637 • Published • 3
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
Paper • 2406.10327 • Published
AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
Paper • 2502.10235 • Published • 9
authored 3
papers over 1 year ago
Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
Paper • 2310.14814 • Published • 1
MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Paper • 2405.18979 • Published • 1
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
Paper • 2402.10198 • Published • 1