{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:19:50Z","timestamp":1759969190340,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP)","award":["RS-2022-00155857"],"award-info":[{"award-number":["RS-2022-00155857"]}]},{"DOI":"10.13039\/501100006374","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["RS-2024-00468747"],"award-info":[{"award-number":["RS-2024-00468747"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,8]]},"DOI":"10.1145\/3701716.3717563","type":"proceedings-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T16:12:56Z","timestamp":1748016776000},"page":"2161-2169","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Diverse Knowledge Selection for Enhanced Zero-shot Visual Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3393-4797","authenticated-orcid":false,"given":"Seunghoon","family":"Han","sequence":"first","affiliation":[{"name":"Chungnam National University, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2909-150X","authenticated-orcid":false,"given":"Mingyu","family":"Choi","sequence":"additional","affiliation":[{"name":"Chungnam National University, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9573-2916","authenticated-orcid":false,"given":"Hyewon","family":"Lee","sequence":"additional","affiliation":[{"name":"Chungnam National University, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7755-0041","authenticated-orcid":false,"given":"SoYoung","family":"Park","sequence":"additional","affiliation":[{"name":"Chungnam National University, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0774-3619","authenticated-orcid":false,"given":"Jong-Ryul","family":"Lee","sequence":"additional","affiliation":[{"name":"Chungnam National University, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5924-3398","authenticated-orcid":false,"given":"Sungsu","family":"Lim","sequence":"additional","affiliation":[{"name":"Chungnam National University, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4522-5388","authenticated-orcid":false,"given":"Tae-Ho","family":"Kim","sequence":"additional","affiliation":[{"name":"Nota Inc., Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Vqa: Visual question answering. In ICCV. 2425--2433.","author":"Antol Stanislaw","year":"2015","unstructured":"Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, and Devi Parikh. 2015. Vqa: Visual question answering. In ICCV. 2425--2433."},{"key":"e_1_3_2_2_2_1","volume-title":"Vqa-med: Overview of the medical visual question answering task at imageclef","author":"Abacha Asma Ben","year":"2019","unstructured":"Asma Ben Abacha, Sadid A Hasan, Vivek V Datla, Dina Demner-Fushman, and Henning M\u00fcller. 2019. Vqa-med: Overview of the medical visual question answering task at imageclef 2019. In CLEF (Working Notes)."},{"unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. In NeurIPS.","key":"e_1_3_2_2_3_1"},{"unstructured":"Rui Cao and Jing Jiang. 2024. Knowledge Generation for Zero-shot Knowledge-based VQA. In EACL. 533--549.","key":"e_1_3_2_2_4_1"},{"doi-asserted-by":"crossref","unstructured":"Zhuo Chen Jiaoyan Chen Yuxia Geng Jeff Z Pan Zonggang Yuan and Huajun Chen. 2021. Zero-shot visual question answering using knowledge graph. In ISWC. 146--162.","key":"e_1_3_2_2_5_1","DOI":"10.1007\/978-3-030-88361-4_9"},{"key":"e_1_3_2_2_6_1","volume-title":"Mukea: Multimodal knowledge extraction and accumulation for knowledge-based visual question answering. In CVPR. 5089--5098.","author":"Ding Yang","year":"2022","unstructured":"Yang Ding, Jing Yu, Bang Liu, Yue Hu, Mingxin Cui, and Qi Wu. 2022. Mukea: Multimodal knowledge extraction and accumulation for knowledge-based visual question answering. In CVPR. 5089--5098."},{"doi-asserted-by":"crossref","unstructured":"Noa Garcia Mayu Otani Chenhui Chu and Yuta Nakashima. 2020. KnowIT VQA: Answering knowledge-based questions about videos. In AAAI. 10826--10834.","key":"e_1_3_2_2_7_1","DOI":"10.1609\/aaai.v34i07.6713"},{"doi-asserted-by":"crossref","unstructured":"Yash Goyal Tejas Khot Douglas Summers-Stay Dhruv Batra and Devi Parikh. 2017. Making the v in vqa matter: Elevating the role of image understanding in visual question answering. In CVPR. 6904--6913.","key":"e_1_3_2_2_8_1","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_2_9_1","volume-title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language. In NAACL-HLT. 956--968.","author":"Gui Liangke","year":"2022","unstructured":"Liangke Gui, Borui Wang, Qiuyuan Huang, Alexander Hauptmann, Yonatan Bisk, and Jianfeng Gao. 2022. KAT: A Knowledge Augmented Transformer for Vision-and-Language. In NAACL-HLT. 956--968."},{"key":"e_1_3_2_2_10_1","volume-title":"Boyang Li, Dacheng Tao, and Steven Hoi.","author":"Guo Jiaxian","year":"2023","unstructured":"Jiaxian Guo, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Boyang Li, Dacheng Tao, and Steven Hoi. 2023. From images to textual prompts: Zero-shot visual question answering with frozen large language models. In CVPR. 10867--10877."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_11_1","DOI":"10.1145\/775152.775191"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_12_1","DOI":"10.1145\/324133.324140"},{"doi-asserted-by":"crossref","unstructured":"Yunshi Lan Xiang Li Xin Liu Yang Li Wei Qin and Weining Qian. 2023. Improving zero-shot visual question answering via large language models with reasoning question prompts. In ACM Multimedia. 4389--4400.","key":"e_1_3_2_2_13_1","DOI":"10.1145\/3581783.3612389"},{"key":"e_1_3_2_2_14_1","volume-title":"Hoi","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 ICML. 12888--12900."},{"key":"e_1_3_2_2_15_1","volume-title":"Ok-vqa: A visual question answering benchmark requiring external knowledge. In CVPR. 3195--3204.","author":"Marino Kenneth","year":"2019","unstructured":"Kenneth Marino, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. 2019. Ok-vqa: A visual question answering benchmark requiring external knowledge. In CVPR. 3195--3204."},{"unstructured":"Lawrence Page. 1999. The PageRank citation ranking: Bringing order to the web. Technical Report. Technical Report.","key":"e_1_3_2_2_16_1"},{"key":"e_1_3_2_2_17_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR, Vol. 21, 140 (2020), 1--67.","journal-title":"JMLR"},{"doi-asserted-by":"crossref","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In EMNLP-IJCNLP. 3980--3990.","key":"e_1_3_2_2_18_1","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_2_19_1","volume-title":"A-okvqa: A benchmark for visual question answering using world knowledge. In ECCV. 146--162.","author":"Schwenk Dustin","year":"2022","unstructured":"Dustin Schwenk, Apoorv Khandelwal, Christopher Clark, Kenneth Marino, and Roozbeh Mottaghi. 2022. A-okvqa: A benchmark for visual question answering using world knowledge. In ECCV. 146--162."},{"key":"e_1_3_2_2_20_1","volume-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization. In ICCV. 618--626.","author":"Selvaraju Ramprasaath R","year":"2017","unstructured":"Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In ICCV. 618--626."},{"key":"e_1_3_2_2_21_1","volume-title":"Kvqa: Knowledge-aware visual question answering. In AAAI. 8876--8884.","author":"Shah Sanket","year":"2019","unstructured":"Sanket Shah, Anand Mishra, Naganand Yadati, and Partha Pratim Talukdar. 2019. Kvqa: Knowledge-aware visual question answering. In AAAI. 8876--8884."},{"doi-asserted-by":"crossref","unstructured":"Kevin J Shih Saurabh Singh and Derek Hoiem. 2016. Where to look: Focus regions for visual question answering. In CVPR. 4613--4621.","key":"e_1_3_2_2_22_1","DOI":"10.1109\/CVPR.2016.499"},{"doi-asserted-by":"crossref","unstructured":"Anthony Meng Huat Tiong Junnan Li Boyang Li Silvio Savarese and Steven CH Hoi. 2022. Plug-and-play vqa: Zero-shot vqa by conjoining large pretrained models with zero training. In EMNLP (Findings). 951--967.","key":"e_1_3_2_2_23_1","DOI":"10.18653\/v1\/2022.findings-emnlp.67"},{"doi-asserted-by":"crossref","unstructured":"Peng Wang Qi Wu Chunhua Shen Anthony R. Dick and Anton van den Hengel. 2017. Explicit Knowledge-based Reasoning for Visual Question Answering. In IJCAI. 1290--1296.","key":"e_1_3_2_2_24_1","DOI":"10.24963\/ijcai.2017\/179"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_25_1","DOI":"10.1016\/j.cviu.2017.05.001"},{"doi-asserted-by":"crossref","unstructured":"Alexandros Xenos Themos Stafylakis Ioannis Patras and Georgios Tzimiropoulos. 2023. A Simple Baseline for Knowledge-Based Visual Question Answering. In EMNLP. 14871--14877.","key":"e_1_3_2_2_26_1","DOI":"10.18653\/v1\/2023.emnlp-main.919"},{"doi-asserted-by":"crossref","unstructured":"Zhengyuan Yang Zhe Gan Jianfeng Wang Xiaowei Hu Yumao Lu Zicheng Liu and Lijuan Wang. 2022. An empirical study of gpt-3 for few-shot knowledge-based vqa. In AAAI. 3081--3089.","key":"e_1_3_2_2_27_1","DOI":"10.1609\/aaai.v36i3.20215"},{"doi-asserted-by":"crossref","unstructured":"Zichao Yang Xiaodong He Jianfeng Gao Li Deng and Alex Smola. 2016. Stacked attention networks for image question answering. In CVPR. 21--29.","key":"e_1_3_2_2_28_1","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_2_29_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"doi-asserted-by":"crossref","unstructured":"Chen Zhu Yanpeng Zhao Shuaiyi Huang Kewei Tu and Yi Ma. 2017. Structured attentions for visual question answering. In ICCV. 1291--1300.","key":"e_1_3_2_2_30_1","DOI":"10.1109\/ICCV.2017.145"}],"event":{"sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"acronym":"WWW '25","name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia"},"container-title":["Companion Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3717563","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701716.3717563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T03:04:32Z","timestamp":1759892672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3717563"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":30,"alternative-id":["10.1145\/3701716.3717563","10.1145\/3701716"],"URL":"https:\/\/doi.org\/10.1145\/3701716.3717563","relation":{},"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}