{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T04:59:52Z","timestamp":1784177992345,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3731957","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T14:55:26Z","timestamp":1752504926000},"page":"4324-4328","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Retrieval-Augmented Image Captioning and Generation with Entity Concepts Enhancement for Baidu Multimodal Advertising"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8510-7572","authenticated-orcid":false,"given":"Lei","family":"Shen","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3053-3965","authenticated-orcid":false,"given":"Kang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Baidu Search Ads, Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0863-2539","authenticated-orcid":false,"given":"Zhipeng","family":"Jin","sequence":"additional","affiliation":[{"name":"Baidu Search Ads, Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5481-4512","authenticated-orcid":false,"given":"Wen","family":"Tao","sequence":"additional","affiliation":[{"name":"Baidu Search Ads, Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5077-4782","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Baidu Search Ads, Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6516-1139","authenticated-orcid":false,"given":"Cong","family":"Han","sequence":"additional","affiliation":[{"name":"Baidu Search Ads, Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7346-5258","authenticated-orcid":false,"given":"Shuanglong","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Search Ads, Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4903-3992","authenticated-orcid":false,"given":"Zhongmin","family":"Cai","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7305-8940","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Search Ads, Baidu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966, Vol. 1, 2 (2023), 3."},{"key":"e_1_3_2_1_2_1","volume-title":"Controllable generation with text-to-image diffusion models: A survey. arXiv preprint arXiv:2403.04279","author":"Cao Pu","year":"2024","unstructured":"Pu Cao, Feng Zhou, Qing Song, and Lu Yang. 2024. Controllable generation with text-to-image diffusion models: A survey. arXiv preprint arXiv:2403.04279 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"European Conference on Computer Vision. Springer, 370-387","author":"Chen Lin","year":"2024","unstructured":"Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, and Dahua Lin. 2024a. Sharegpt4v: Improving large multi-modal models with better captions. In European Conference on Computer Vision. Springer, 370-387."},{"key":"e_1_3_2_1_4_1","volume-title":"Re-imagen: Retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491","author":"Chen Wenhu","year":"2022","unstructured":"Wenhu Chen, Hexiang Hu, Chitwan Saharia, and William W Cohen. 2022. Re-imagen: Retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al. 2024b. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198."},{"key":"e_1_3_2_1_6_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, Vol. 2 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Advertising and keyword selection strategies on Baidu: an empirical analysis. Industrial Management & Data Systems","author":"He Chengping","year":"2025","unstructured":"Chengping He, Jie Ren, and Hao Huang. 2025. Advertising and keyword selection strategies on Baidu: an empirical analysis. Industrial Management & Data Systems (2025)."},{"key":"e_1_3_2_1_8_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaaiss.v3i1.31256"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Wenyi Hong Weihan Wang Ming Ding Wenmeng Yu Qingsong Lv Yan Wang Yean Cheng Shiyu Huang Junhui Ji Zhao Xue et al. 2024. Cogvlm2: Visual language models for image and video understanding. arXiv preprint arXiv:2408.16500 (2024).","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_13_1","volume-title":"ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning. arXiv preprint arXiv:2412.19289","author":"Kim Taewhan","year":"2024","unstructured":"Taewhan Kim, Soeun Lee, Si-Woo Kim, and Dong-Jin Kim. 2024. ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning. arXiv preprint arXiv:2412.19289 (2024)."},{"key":"e_1_3_2_1_14_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01303"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569219.3569352"},{"key":"e_1_3_2_1_19_1","volume-title":"Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags. arXiv preprint arXiv:2406.10839","author":"Qi Daiqing","year":"2024","unstructured":"Daiqing Qi, Handong Zhao, Zijun Wei, and Sheng Li. 2024. Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags. arXiv preprint arXiv:2406.10839 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77083-9"},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. Pmlr, 8821-8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International conference on machine learning. Pmlr, 8821-8831."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10488-2"},{"key":"e_1_3_2_1_25_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"CLIP-Driven Low-Cost Image Captioning. In 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 1-8.","author":"Wang Yiyu","year":"2024","unstructured":"Yiyu Wang, Jungang Xu, and Yingfei Sun. 2024b. CLIP-Driven Low-Cost Image Captioning. In 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 1-8."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679969"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403297"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481937"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661350"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3731957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:31:47Z","timestamp":1755887507000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3731957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":32,"alternative-id":["10.1145\/3726302.3731957","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3731957","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}