To address these limitations, we propose a novel method, Multi-granularity Spatial-Temporal Transformers (MSTFormer), for spatial-temporal feature extraction and fusion that leverages the structured information
Large-scale Assessments in Education (2023) 11:22 https://doi.org/10.1186/s40536-023-00165-9 Large-scale Assessments in Education METHODOLOGY Effects of DIF in MST routing in ILSAs Open Access Montserrat Valdivia Medinaceli1*, Leslie Rutkowski1, Dubravka Svetina Valdivia1 ...