@article{transformerdrivenmultimodalfusionforexpl, title = {Transformer-Driven Multimodal Fusion for Explainable Suspiciousness Estimation in Visual Surveillance}, author = {Kuldeep Singh Yadav and Lalan Kumar}, year = {2025}, eprint = {2512.09311}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.09311}, }