Nicola Messina, Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro, Stéphane Marchand-Maillet. Towards Efficient Cross-Modal Visual Textual Retrieval using Transformer-Encoder Deep Features. In 18th International Conference on Content-Based Multimedia Indexing, CBMI 2021, Lille, France, June 28-30, 2021. pages 1-6, IEEE, 2021. [doi]
Abstract is missing.