Toward Automatic Relevance Judgment using Vision-Language Models for Image-Text Retrieval Evaluation.

@inproceedings{yang-2024-toward, author = {Jheng-Hong Yang and Jimmy Lin}, editor = {Clemencia Siro and Mohammad Aliannejadi and Hossein A. Rahmani and Nick Craswell and Charles L. A. Clarke and Guglielmo Faggioli and Bhaskar Mitra and Paul Thomas and Emine Yilmaz}, title = {{Toward Automatic Relevance Judgment using Vision-Language Models for Image-Text Retrieval Evaluation}}, booktitle = {{Proceedings of The First Workshop on Large Language Models for Evaluation in Information Retrieval (LLM4Eval 2024) co-located with 10th International Conference on Online Publishing (SIGIR 2024), Washington D.C., USA, July 18, 2024}}, series = {CEUR Workshop Proceedings}, volume = {3752}, pages = {113--123}, publisher = {CEUR-WS.org}, year = {2024}, url = {https://ceur-ws.org/Vol-3752/paper7.pdf} }