Multidimensional time series data are widely used across various fields, and their effective representation is critical for subsequent analysis and mining tasks. Traditional shapelet transform methods extract features by projecting the single-dimensional time series into the shapelet space and then fusing them without considering the complex coupling relationships between different dimensions. Moreover, the restriction on shapelet length hinders the acquisition of long-range dependencies on sequences. To address these issues, a multidimensional time series representation method, CDT-ShapeNet, coupling both dimensional dependencies and long-range dependencies is proposed in this study. In this method, the dimensional information representation module captures the dependencies between different dimensions through a dimensional attention mechanism, while the long-term information representation module learns long-term temporal dependencies using an attention mechanism and a long-short-term memory network. Experiments conducted on nine UEA datasets show that this method enhances the average accuracy by 6.8% in comparison with other methods, validating its effectiveness in multidimensional time series representation.