{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:12:45Z","timestamp":1784178765309,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006579","name":"Ministry of Industry and Information Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["ZTZB-23-990-024"],"award-info":[{"award-number":["ZTZB-23-990-024"]}],"id":[{"id":"10.13039\/501100006579","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172404"],"award-info":[{"award-number":["62172404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761265","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:55:33Z","timestamp":1762559733000},"page":"2566-2576","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Retrieval-Augmented Image Captioning via Synthesized Entity-Aware Knowledge Representations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9570-767X","authenticated-orcid":false,"given":"Lin","family":"Shen","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5228-7989","authenticated-orcid":false,"given":"Chenxu","family":"Cui","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1835-1700","authenticated-orcid":false,"given":"Jinchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4366-9121","authenticated-orcid":false,"given":"Haihui","family":"Fan","sequence":"additional","affiliation":[{"name":"Instute of information engineering, chinese academy of Science, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6482-8461","authenticated-orcid":false,"given":"Haotian","family":"Jin","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6709-0942","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"e_1_3_2_1_3_1","volume-title":"NeurIPS 2023 workshop on instruction tuning and instruction following.","author":"Asai Akari","year":"2023","unstructured":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Self-reflective retrieval augmented generation. In NeurIPS 2023 workshop on instruction tuning and instruction following."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization@ACL 2005","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. In Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization@ACL 2005, Ann Arbor, Michigan, USA, June 29, 2005. 65-72. https:\/\/aclanthology.org\/W05-0909\/"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1470"},{"key":"e_1_3_2_1_6_1","first-page":"1877","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, and Subbiah. 2020. Language Models are Few-Shot Learners, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877-1901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611987"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729921"},{"key":"e_1_3_2_1_9_1","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL]"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612326"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01422"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00291"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00291"},{"key":"e_1_3_2_1_15_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Guti\u00e9rrez Bernal Jim\u00e9nez","year":"2024","unstructured":"Bernal Jim\u00e9nez Guti\u00e9rrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. Hipporag: Neurobiologically inspired long-term memory for large language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32342"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681161"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32454"},{"key":"e_1_3_2_1_21_1","first-page":"9459","volume-title":"Lin (Eds.)","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 9459-9474."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"19742","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 Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 19730-19742."},{"key":"e_1_3_2_1_23_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA. 12888-12900."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01303"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.31"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.503"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_29_1","volume-title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. In The Twelfth International Conference on Learning Representations.","author":"Yuan-Fang Li LINHAO LUO","year":"2024","unstructured":"LINHAO LUO, Yuan-Fang Li, Reza Haf, and Shirui Pan. 2024. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096424"},{"key":"e_1_3_2_1_31_1","volume-title":"Yuille","author":"Mao Junhua","year":"2014","unstructured":"Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, and Alan L. Yuille. 2014. Explain Images with Multimodal Recurrent Neural Networks. CoRR, Vol. abs\/1410.1090 (2014). arXiv:1410.1090 http:\/\/arxiv.org\/abs\/1410.1090"},{"key":"e_1_3_2_1_32_1","volume-title":"Bermano","author":"Mokady Ron","year":"2021","unstructured":"Ron Mokady, Amir Hertz, and Amit H. Bermano. 2021. ClipCap: CLIP Prefix for Image Captioning. CoRR, Vol. abs\/2111.09734 (2021). arXiv:2111.09734"},{"key":"e_1_3_2_1_33_1","unstructured":"OpenAI. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL]"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_36_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_37_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019a. Language Models are Unsupervised Multitask Learners."},{"key":"e_1_3_2_1_38_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019b. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.266"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"e_1_3_2_1_41_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01747"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.558"},{"key":"e_1_3_2_1_46_1","volume-title":"Vision-language dataset distillation. arXiv preprint arXiv:2308.07545","author":"Wu Xindi","year":"2023","unstructured":"Xindi Wu, Byron Zhang, Zhiwei Deng, and Olga Russakovsky. 2023. Vision-language dataset distillation. arXiv preprint arXiv:2308.07545 (2023)."},{"key":"e_1_3_2_1_47_1","unstructured":"An Yang Baosong Yang and Binyuan Hui. 2024. Qwen2 Technical Report. arXiv:2407.10671 [cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_1_48_1","volume-title":"Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Mohammad Shoeybi, Ming-Yu Liu, Yuke Zhu, Bryan Catanzaro, Chaowei Xiao, and Anima Anandkumar.","author":"Yang Zhuolin","year":"2023","unstructured":"Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Anand Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Mohammad Shoeybi, Ming-Yu Liu, Yuke Zhu, Bryan Catanzaro, Chaowei Xiao, and Anima Anandkumar. 2023. Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning. In The 2023 Conference on Empirical Methods in Natural Language Processing. https:\/\/openreview.net\/forum?id=GOBxWdRpfz"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.13916"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34386"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.50"},{"key":"e_1_3_2_1_53_1","volume-title":"Synthesizing Informative Training Samples with GAN. NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research","author":"Zhao Bo","year":"2022","unstructured":"Bo Zhao and Hakan Bilen. 2022. Synthesizing Informative Training Samples with GAN. NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research (2022)."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:03:32Z","timestamp":1765497812000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":53,"alternative-id":["10.1145\/3746252.3761265","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761265","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}