A graph-attention model for accident severity prediction reports 85% Macro F1 on FARS and 84% on ARI-BUET, but the FARS label distribution is inconsistent with the dataset's own description.
Spatio -temporal graph convolutional networks: A comprehensive review,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
STARN-GAT: A Multi-Modal Spatio-Temporal Graph Attention Network for Accident Severity Prediction
A graph-attention model for accident severity prediction reports 85% Macro F1 on FARS and 84% on ARI-BUET, but the FARS label distribution is inconsistent with the dataset's own description.