{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:47:00Z","timestamp":1765500420259,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3760826","type":"proceedings-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:37:32Z","timestamp":1762799852000},"page":"4827-4831","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal RAG Enhanced Visual Description"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8848-7041","authenticated-orcid":false,"given":"Amit Kumar","family":"Jaiswal","sequence":"first","affiliation":[{"name":"Indian Institute of Technology (BHU), Varanasi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0390-3657","authenticated-orcid":false,"given":"Haiming","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Southampton, Southampton, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5622-5132","authenticated-orcid":false,"given":"Ingo","family":"Frommholz","sequence":"additional","affiliation":[{"name":"Modul University Vienna, Vienna, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al., 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23716-23736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","volume-title":"SPICE: Semantic propositional image caption evaluation. In Computer Vision-ECCV","author":"Anderson Peter","year":"2016","unstructured":"Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. 2016. SPICE: Semantic propositional image caption evaluation. In Computer Vision-ECCV 2016. Springer, 382-398."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1250"},{"key":"e_1_3_2_1_4_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, Andy Zeng, Igor Mordatch, and Pete Florence. 2023. PaLM-E: an embodied multimodal language model. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML'23). JMLR.org, Article 340, 20 pages."},{"key":"e_1_3_2_1_6_1","volume-title":"Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization? arXiv preprint arXiv:2402","author":"Fu Xue-Yong","year":"2024","unstructured":"Xue-Yong Fu, Md Tahmid Rahman Laskar, Elena Khasanova, Cheng Chen, and Shashi Bhushan TN. 2024. Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization? arXiv preprint arXiv:2402.00841 (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"Peng Gao Jiaming Han Renrui Zhang Ziyi Lin Shijie Geng Aojun Zhou Wei Zhang Pan Lu Conghui He Xiangyu Yue et al. 2023. Llama-adapter v2: Parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010 (2023)."},{"key":"e_1_3_2_1_8_1","first-page":"6704","article-title":"CyCLIP: Cyclic contrastive language-image pretraining","volume":"35","author":"Goel Shashank","year":"2022","unstructured":"Shashank Goel, Hritik Bansal, Sumit Bhatia, Ryan Rossi, Vishwa Vinay, and Aditya Grover. 2022. CyCLIP: Cyclic contrastive language-image pretraining. Advances in Neural Information Processing Systems, Vol. 35 (2022), 6704-6719.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_9_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=sE7-XhLxHA","author":"He Pengcheng","year":"2023","unstructured":"Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2023. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=sE7-XhLxHA"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_2_1_11_1","volume-title":"Language Is Not All You Need: Aligning Perception with Language Models. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=UpN2wfrLec","author":"Huang Shaohan","year":"2023","unstructured":"Shaohan Huang, Li Dong, Wenhui Wang, Yaru Hao, Saksham Singhal, Shuming Ma, Tengchao Lv, Lei Cui, Owais Khan Mohammed, Barun Patra, Qiang Liu, Kriti Aggarwal, Zewen Chi, Johan Bjorck, Vishrav Chaudhary, Subhojit Som, Xia Song, and Furu Wei. 2023. Language Is Not All You Need: Aligning Perception with Language Models. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=UpN2wfrLec"},{"key":"e_1_3_2_1_12_1","volume-title":"International conference on machine learning. PMLR, 4904-4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904-4916."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning","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 (Honolulu, Hawaii, USA) (ICML'23). JMLR.org, Article 814, 13 pages."},{"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. 2022a. 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","volume-title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zq1iJkNk3uN","author":"Li Yangguang","year":"2022","unstructured":"Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, and Junjie Yan. 2022b. Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zq1iJkNk3uN"},{"key":"e_1_3_2_1_18_1","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang Victor Weixin","year":"2022","unstructured":"Victor Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, and James Y Zou. 2022. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 17612-17625.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"ROUGE: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_21_1","volume-title":"A deep architecture for matching short texts. Advances in neural information processing systems","author":"Lu Zhengdong","year":"2013","unstructured":"Zhengdong Lu and Hang Li. 2013. A deep architecture for matching short texts. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_22_1","volume-title":"Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_23_1","volume-title":"Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734","author":"Mokady Ron","year":"2021","unstructured":"Ron Mokady, Amir Hertz, and Amit H Bermano. 2021. Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_25_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_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"e_1_3_2_1_27_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al., 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25278-25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557067"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_31_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612245"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/481"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.793"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_1_38_1","volume-title":"International Conference on Machine Learning. PMLR, 12697-12706","author":"Zhao Zihao","year":"2021","unstructured":"Zihao Zhao, Eric Wallace, Shi Feng, Dan Klein, and Sameer Singh. 2021. Calibrate before use: Improving few-shot performance of language models. In International Conference on Machine Learning. PMLR, 12697-12706."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"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\/3746252.3760826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:43:50Z","timestamp":1765500230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3760826"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":38,"alternative-id":["10.1145\/3746252.3760826","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3760826","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"}}]}}