{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:20:18Z","timestamp":1765041618802,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,16]]},"DOI":"10.1145\/3677389.3702516","type":"proceedings-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T16:55:46Z","timestamp":1741884946000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Disaster Image Tagging Using Generative AI for Digital Archives"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0399-4448","authenticated-orcid":false,"given":"Kotaro","family":"Yasuda","sequence":"first","affiliation":[{"name":"Kumamoto University, Kumamoto city, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0861-849X","authenticated-orcid":false,"given":"Masayoshi","family":"Aritsugi","sequence":"additional","affiliation":[{"name":"Kumamoto University, Kumamoto city, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2467-003X","authenticated-orcid":false,"given":"Yukiko","family":"Takeuchi","sequence":"additional","affiliation":[{"name":"Kumamoto University, Kumamoto city, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9725-536X","authenticated-orcid":false,"given":"Akihiro","family":"Shibayama","sequence":"additional","affiliation":[{"name":"Tohoku University, Sendai city, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6819-4305","authenticated-orcid":false,"given":"Israel","family":"Mendon\u00e7a","sequence":"additional","affiliation":[{"name":"Kumamoto University, Kumamoto city, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.09.013"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Alessandro Favero Luca Zancato Matthew Trager Siddharth Choudhary Pramuditha Perera Alessandro Achille Ashwin Swaminathan and Stefano Soatto. 2024. Multi-Modal Hallucination Control by Visual Information Grounding. arXiv:2403.14003 [cs.CV] https:\/\/arxiv.org\/abs\/2403.14003","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1102"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijdrr.2022.103085"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"e_1_3_2_1_6_1","unstructured":"Sunan He Taian Guo Tao Dai Ruizhi Qiao Bo Ren and Shu-Tao Xia. 2023. Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer. arXiv:2207.01887 [cs.CV] https:\/\/arxiv.org\/abs\/2207.01887"},{"key":"e_1_3_2_1_7_1","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin and Ting Liu. 2023. A Survey on Hallucination in Large Language Models: Principles Taxonomy Challenges and Open Questions. arXiv:2311.05232 [cs.CL] https:\/\/arxiv.org\/abs\/2311.05232"},{"key":"e_1_3_2_1_8_1","unstructured":"Xinyu Huang Yi-Jie Huang Youcai Zhang Weiwei Tian Rui Feng Yuejie Zhang Yanchun Xie Yaqian Li and Lei Zhang. 2023. Open-Set Image Tagging with Multi-Grained Text Supervision. arXiv:2310.15200 [cs.CV] https:\/\/arxiv.org\/abs\/2310.15200"},{"key":"e_1_3_2_1_9_1","unstructured":"Xinyu Huang Youcai Zhang Jinyu Ma Weiwei Tian Rui Feng Yuejie Zhang Yaqian Li Yandong Guo and Lei Zhang. 2024. Tag2Text: Guiding Vision-Language Model via Image Tagging. arXiv:2303.05657 [cs.CV] https:\/\/arxiv.org\/abs\/2303.05657"},{"volume-title":"Algorithms for clustering data","author":"Jain Anil K","key":"e_1_3_2_1_10_1","unstructured":"Anil K Jain and Richard C Dubes. 1988. Algorithms for clustering data. Prentice-Hall, Inc."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"e_1_3_2_1_12_1","unstructured":"Bo Li Kaichen Zhang Hao Zhang Dong Guo Renrui Zhang Feng Li Yuanhan Zhang Ziwei Liu and Chunyuan Li. 2024. LLaVA-NeXT: Stronger LLMs Supercharge Multimodal Capabilities in the Wild. https:\/\/llava-vl.github.io\/blog\/2024-05-10-llava-next-stronger-llms\/"},{"key":"e_1_3_2_1_13_1","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. arXiv:2301.12597 [cs.CV] https:\/\/arxiv.org\/abs\/2301.12597"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"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 Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 12888--12900. https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 16th International conference on information systems for crisis response and management (ISCRAM 2019","author":"Li Xukun","year":"2019","unstructured":"Xukun Li, Doina Caragea, Cornelia Caragea, Muhammad Imran, and Ferda Ofli. 2019. Identifying disaster damage images using a domain adaptation approach. In Proceedings of the 16th International conference on information systems for crisis response and management (ISCRAM 2019). 633--545. https:\/\/iscram2019.webs.upv.es\/wp-content\/uploads\/2019\/09\/ISCRAM2019_Proceedings.pdf"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"e_1_3_2_1_17_1","unstructured":"Yi Li Hualiang Wang Yiqun Duan and Xiaomeng Li. 2023. CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks. arXiv:2304.05653 [cs.CV] https:\/\/arxiv.org\/abs\/2304.05653"},{"key":"e_1_3_2_1_18_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2024. Improved Baselines with Visual Instruction Tuning. arXiv:2310.03744 [cs.CV] https:\/\/arxiv.org\/abs\/2310.03744"},{"key":"e_1_3_2_1_19_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"e_1_3_2_1_20_1","volume-title":"Levine (Eds.)","volume":"36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 34892--34916. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2019.101009"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2019.00016"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672359.3672364"},{"key":"e_1_3_2_1_28_1","unstructured":"Ximeng Sun Ping Hu and Kate Saenko. 2022. DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations. arXiv:2206.09541 [cs.CV] https:\/\/arxiv.org\/abs\/2206.09541"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Ikuto Takashima Kotaro Yasuda Yukiko Takeuchi Masayoshi Aritsugi Akihiro Shibayama and Israel Mendon\u00e7a. 2024. Semi-automated Disaster Image Tagging While Protecting Privacy: A Case Study. In Database and Expert Systems Applications Christine Strauss Toshiyuki Amagasa Giuseppe Manco Gabriele Kotsis A. Min Tjoa and Ismail Khalil (Eds.). Springer Nature Switzerland Cham 142--148. 10.1007\/978-3-031-68312-1_11","DOI":"10.1007\/978-3-031-68312-1_11"},{"key":"e_1_3_2_1_30_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 [cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_1_31_1","volume-title":"Oh (Eds.)","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 24824--24837. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/9d5609613524ecf4f15af0f7b31abca4-Paper-Conference.pdf"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_34_1","volume-title":"Recognize Anything: A Strong Image Tagging Model. arXiv:2306.03514 [cs.CV] https:\/\/arxiv.org\/abs\/2306.03514","author":"Zhang Youcai","year":"2023","unstructured":"Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, Yandong Guo, and Lei Zhang. 2023. Recognize Anything: A Strong Image Tagging Model. arXiv:2306.03514 [cs.CV] https:\/\/arxiv.org\/abs\/2306.03514"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"}],"event":{"name":"JCDL '24: 24th ACM\/IEEE Joint Conference on Digital Libraries","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","IEEE TCDL"],"location":"Hong Kong China","acronym":"JCDL '24"},"container-title":["Proceedings of the 24th ACM\/IEEE Joint Conference on Digital Libraries"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677389.3702516","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677389.3702516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:19:07Z","timestamp":1750295947000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677389.3702516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":35,"alternative-id":["10.1145\/3677389.3702516","10.1145\/3677389"],"URL":"https:\/\/doi.org\/10.1145\/3677389.3702516","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]},"assertion":[{"value":"2025-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}