@article{anovelattentionbasedaggregationfunction, title = {A Novel Attention-based Aggregation Function to Combine Vision and Language}, author = {Matteo Stefanini and Marcella Cornia and Lorenzo Baraldi and Rita Cucchiara}, year = {2020}, eprint = {2004.13073}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2004.13073v2}, }