Multilingual Evaluation of Image-Text Retrieval in Vision-Language Models: A Metric-Based Perspective.

@inproceedings{maiti-2025-multilingual, author = {Bodhisatta Maiti}, editor = {Sherzod Hakimov and David Semedo and Eric M\"{u}ller-Budack and Marc A. Kastner and Takahiro Komamizu}, title = {{Multilingual Evaluation of Image-Text Retrieval in Vision-Language Models: A Metric-Based Perspective}}, booktitle = {{Proceedings of the 4th International Workshop on Multimodal Human Understanding for the Web and Social Media, MUWS 2025, Dublin, Ireland, 31 October 2025}}, pages = {10--16}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3728481.3762166}, doi = {https://doi.org/10.1145/3728481.3762166} }