{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:17Z","timestamp":1750309517637,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"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":[[2024,10,18]]},"DOI":"10.1145\/3711129.3711334","type":"proceedings-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T12:46:06Z","timestamp":1740055566000},"page":"1206-1212","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FMIQA: A multimodal integrated QA Robot with considerable intelligence"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3205-3636","authenticated-orcid":false,"given":"Xuezhong","family":"Li","sequence":"first","affiliation":[{"name":"Nanjing Nari Digital Service Co. Ltd., Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7549-8758","authenticated-orcid":false,"given":"Jinhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing Nari Digital Service Co. Ltd., Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3495-3929","authenticated-orcid":false,"given":"Yuxuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing Nari Digital Service Co. Ltd., Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6106-290X","authenticated-orcid":false,"given":"Yidan","family":"Xu","sequence":"additional","affiliation":[{"name":"NARI Group, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0395-1613","authenticated-orcid":false,"given":"Wensong","family":"Liu","sequence":"additional","affiliation":[{"name":"NARI Group, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8599-2900","authenticated-orcid":false,"given":"Yuxiao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing Nari Digital Service Co. Ltd., Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"key":"e_1_3_3_1_1_2","doi-asserted-by":"crossref","unstructured":"Yakub Kayode Saheed \u00a0Oluwadamilare Harazeem Abdulganiyu \u00a0Taha Ait Tchakoucht:Modified genetic algorithm and fine-tuned\u00a0long\u00a0short-term\u00a0memory\u00a0network for intrusion detection in the internet of things networks with edge capabilities.\u00a0Appl. Soft Comput.\u2002155:\u00a0111434\u00a0(2024)","DOI":"10.1016\/j.asoc.2024.111434"},{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Francesco Ardizzon \u00a0Paolo Casari \u00a0Stefano Tomasin: A\u00a0RNN-based approach to physical layer authentication in underwater acoustic networks with mobile devices.\u00a0Comput. Networks\u2002243:\u00a0110311\u00a0(2024)","DOI":"10.1016\/j.comnet.2024.110311"},{"key":"e_1_3_3_1_3_2","unstructured":"Ashish Vaswani \u00a0Noam Shazeer \u00a0Niki Parmar \u00a0Jakob Uszkoreit \u00a0Llion Jones \u00a0Aidan N. Gomez \u00a0Lukasz Kaiser \u00a0Illia Polosukhin:Attention\u00a0is\u00a0All\u00a0you\u00a0Need.\u00a0NIPS\u20022017:\u00a05998-6008"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.115"},{"volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Choi Eunsol","key":"e_1_3_3_1_5_2","unstructured":"Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen tau Yih, Yejin Choi, Percy Liang, and Luke Zettle moyer. Quac: Question answering in context. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018:2174\u20132184."},{"volume-title":"ICCV 2015: 2425\u20132433","author":"Antol Stanislaw","key":"e_1_3_3_1_6_2","unstructured":"Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, and Devi Parikh. VQA: visual question answering. ICCV 2015: 2425\u20132433."},{"key":"e_1_3_3_1_7_2","first-page":"7879","volume":"2020","author":"Hannan Darryl","unstructured":"Darryl Hannan,\u00a0Akshay Jain,\u00a0Mohit Bansal. ManyModalQA: Modality Disambiguation and QA over Diverse Input. AAAI 2020:7879-7896.","journal-title":"Diverse Input. AAAI"},{"volume-title":"Yin and Yang: Balancing and Answering Binary Visual Questions. CVPR 2016:5014-5022","author":"Peng","key":"e_1_3_3_1_8_2","unstructured":"Peng zhang, Yash Goyal, Douglas Summers-Stay,\u00a0Dhruv Batra,\u00a0Devi Parikh, Yin and Yang: Balancing and Answering Binary Visual Questions. CVPR 2016:5014-5022."},{"volume-title":"CVPR 2017:6325-6334","author":"Goyal Yash","key":"e_1_3_3_1_9_2","unstructured":"Yash Goyal, Tejas Khot, Aishwarya Agrawal, Douglas Summers-Stay, Dhruv Batra, Devi Parikh: Making the V in VQA Matter: Elevating the role of Image Understanding in Visual Question Answering. CVPR 2017:6325-6334."},{"volume-title":"CVPR 2017: 1988-1997","author":"Johnson Justin","key":"e_1_3_3_1_10_2","unstructured":"Justin Johnson, Bharath Hariharan, Laurens van der Matten, Li Fei-Fei, C.Lawrence Zitnick, Ross. B.Girshick: CLEVR: \u00a0A\u00a0Diagnostic\u00a0Dataset\u00a0for\u00a0Compositional\u00a0Language\u00a0and\u00a0Elementary\u00a0Visual\u00a0Reasoning. CVPR 2017: 1988-1997."},{"volume-title":"CVPR 2019:6700-6709","author":"Hudson REW A.","key":"e_1_3_3_1_11_2","unstructured":"dREW A. Hudson, Christopher D.Manning: GQA: A new Dataset for Real-World Visual Reasoning and Compositional Question Answering. CVPR 2019:6700-6709."},{"volume-title":"WACV 2020:1516-1525","author":"Methani Nitesh","key":"e_1_3_3_1_12_2","unstructured":"Nitesh Methani, Pritha Ganguly, Mitesh M. Khapra, Pratyush Kumar: PlotQA: Reasoning over Scientific Plots. WACV 2020:1516-1525."},{"volume-title":"CVPR 2019:6720-6731","author":"Zellers Rowan","key":"e_1_3_3_1_13_2","unstructured":"Rowan Zellers, Yonatan Bisk, Ali Farhadi, Yejin Choi: From Recognition to Cognition: Visual Commonsense Reasoning. CVPR 2019:6720-6731."},{"key":"e_1_3_3_1_14_2","first-page":"8317","volume-title":"Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh","author":"Singh Amanpreet","year":"2019","unstructured":"Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, Marcus Rohrbach: Towards VQA Models That Can Read. CVPR 2019: 8317-8326."},{"key":"e_1_3_3_1_15_2","volume-title":"Yue Cao, Bin Li, Lewei Lu, Furu Wei","author":"Su Weijie","year":"2020","unstructured":"Weijie Su, Xizhou zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai: VL-BERT: Pretraining of Generic Visual-Linguistic Representations. ICLR 2020."},{"key":"e_1_3_3_1_16_2","volume-title":"Devi Parikh","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, Stefan Lee: ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and -Language Tasks. NeurIPS 2019:13-23."},{"key":"e_1_3_3_1_17_2","volume-title":"ICLR","author":"Chen Wenhu","year":"2021","unstructured":"Wenhu Chen, Ming-Wei Chang, Eva Schlinger, William Yang Wang, Willian W.Cohen: Open Question Answering over Tables and Text. ICLR 2021."},{"key":"e_1_3_3_1_18_2","first-page":"1026","volume":"2020","author":"Chen Wenhu","unstructured":"Wenhu Chen, Hanwen Zha, Zhiyu Chen, Wenhan Xiong, Hong Wang, William Yang Wang: HybridQA: A Dataset of Multi-Hop Question Answering over Tabular andTextual Data. EMNLP (Findings) 2020: 1026-1036.","journal-title":"Textual Data. EMNLP (Findings)"},{"key":"e_1_3_3_1_19_2","volume-title":"ICLR","author":"Talmor Alon","year":"2021","unstructured":"Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel iiharco, Hannaneh Hajishirzi, Jonathan Berant: MultiModalQA: complex question over text, table and images. ICLR 2021."},{"key":"e_1_3_3_1_20_2","volume-title":"Ying shen","author":"Haohao","year":"2023","unstructured":"Haohao luo, Ying shen, Yang Deng: Unifying Text, Tables, and Images for Multimodal question Answering. EMNLP (Findings ) 2023: 9355-9367."}],"event":{"name":"EITCE 2024: 2024 8th International Conference on Electronic Information Technology and Computer Engineering","acronym":"EITCE 2024","location":"Haikou Guangdong China"},"container-title":["Proceedings of the 2024 8th International Conference on Electronic Information Technology and Computer Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711129.3711334","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711129.3711334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:03Z","timestamp":1750295883000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711129.3711334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,18]]},"references-count":20,"alternative-id":["10.1145\/3711129.3711334","10.1145\/3711129"],"URL":"https:\/\/doi.org\/10.1145\/3711129.3711334","relation":{},"subject":[],"published":{"date-parts":[[2024,10,18]]},"assertion":[{"value":"2025-02-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}