Multivariate time series classification with crucial timestamps guidance

Da Zhang, Junyu Gao, Xuelong Li

Abstract: Highlights•A Gaussian-prior Transformer encoder is raised to better capture latent dependencies.•A data-driven mask strategy is designed to determine crucial timestamps.•We leverage context-aware positional encoding to improve model’s temporal invariance.•Sufficient experiments are conducted to validate the effectiveness of our method.•The proposed method is competitive and achieves SOTA performance on the datasets.