VLMs bridging-enhanced Scene Semantic Reasoning Framework for Image-Text Matching.

@inproceedings{gao-2025-vlms, author = {Yihua Gao and Junyu Chen and Mingyong Li}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{VLMs bridging-enhanced Scene Semantic Reasoning Framework for Image-Text Matching}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {330--339}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733465}, doi = {https://doi.org/10.1145/3731715.3733465} }