We propose a self-supervised pre-training framework for multivariate time-series classification that addresses the mismatch between fixed-window tokenization and the inherently variable temporal structure of real-world signals. Our framework combines Dynamic-Segment Masking (DSM) with a channel-independent Transformer encoder. DSM uses a recursive linear-fit validator to partition each sequence into content-adaptive, \(\epsilon \) -linear segments and then randomly masks a proportion of segments. Besides, a lightweight, channel-independent Transformer encoder is trained to reconstruct the missing intervals, thereby learning temporal dependencies between observed and missing intervals. Despite having only 2.4 million parameters, our model achieves an average accuracy of 0.74 across 14 UEA benchmark datasets—exceeding a randomly initialized baseline by 7% and outperforming four larger state-of-the-art models, while also converging more rapidly. A comprehensive comparison with ten existing methods shows that our model achieves higher average accuracy than four baselines and ranks better than six. Ablation studies and sensitivity analyses further demonstrate the effectiveness of DSM and the robustness of the framework across a wide range of hyperparameters.