Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval.

@inproceedings{shen-2025-maskaware, author = {Li-Cheng Shen and Jih-Kang Hsieh and Wei-Hua Li and Chu-Song Chen}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {2028--2032}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733484}, doi = {https://doi.org/10.1145/3731715.3733484} }