Retrieval-Augmented Image Captioning and Generation with Entity Concepts Enhancement for Baidu Multimodal Advertising.

@inproceedings{shen-2025-retrievalaugmented, author = {Lei Shen and Kang Zhao and Zhipeng Jin and Wen Tao and Yi Yang and Cong Han and Shuanglong Li and Zhongmin Cai and Lin Liu}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{Retrieval-Augmented Image Captioning and Generation with Entity Concepts Enhancement for Baidu Multimodal Advertising}}, booktitle = {{Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025}}, pages = {4324--4328}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3731957}, doi = {https://doi.org/10.1145/3726302.3731957} }