Entity-Aware Cross-Modal Pretraining for Knowledge-Based Visual Question Answering.

@inproceedings{adjali-2025-entityaware, author = {Omar Adjali and Olivier Ferret and Sahar Ghannay and Herv\'{e} Le Borgne}, editor = {Claudia Hauff and Craig Macdonald and Dietmar Jannach and Gabriella Kazai and Franco Maria Nardini and Fabio Pinelli and Fabrizio Silvestri and Nicola Tonellotto}, title = {{Entity-Aware Cross-Modal Pretraining for Knowledge-Based Visual Question Answering}}, booktitle = {{Advances in Information Retrieval - 47th European Conference on Information Retrieval, ECIR 2025, Lucca, Italy, April 6-10, 2025, Proceedings, Part III}}, series = {Lecture Notes in Computer Science}, volume = {15574}, pages = {391--400}, publisher = {Springer}, year = {2025}, url = {https://doi.org/10.1007/978-3-031-88714-7_38}, doi = {https://doi.org/10.1007/978-3-031-88714-7_38} }