{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:39:37Z","timestamp":1770226777087,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["No.62172101"],"award-info":[{"award-number":["No.62172101"]}]},{"name":"Municipal Hospital Frontier Joint Research Project","award":["No. SHDC12024136"],"award-info":[{"award-number":["No. SHDC12024136"]}]},{"name":"the Postdoctoral Fellowship Program of CPSF","award":["No. GZC20230483"],"award-info":[{"award-number":["No. GZC20230483"]}]},{"name":"the Science and Technology Commission of Shanghai Municipality","award":["No.23511100602, No.21511100500"],"award-info":[{"award-number":["No.23511100602, No.21511100500"]}]},{"name":"the Science and Technology Major Project of Commission of Science and Technology of Shanghai","award":["No.21XD1402500"],"award-info":[{"award-number":["No.21XD1402500"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681053","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"3897-3906","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["CT\n            <sup>2<\/sup>\n            C-QA: Multimodal Question Answering over Chinese Text, Table and Chart"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0544-0062","authenticated-orcid":false,"given":"Bowen","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University &amp; Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4654-9896","authenticated-orcid":false,"given":"Tianhao","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University &amp; Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7993-7223","authenticated-orcid":false,"given":"Yuejie","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University &amp; Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-3998","authenticated-orcid":false,"given":"Ying","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University &amp; Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4747-0574","authenticated-orcid":false,"given":"Rui","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University &amp; Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8645-5414","authenticated-orcid":false,"given":"Xiaobo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Children's Hospital of Fudan University &amp; National Children's Medical Center, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2659522.2659531"},{"key":"e_1_3_2_1_2_1","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 35 (2022) 23716--23736."},{"key":"e_1_3_2_1_3_1","volume-title":"Modality-based factorization for multimodal fusion. arXiv preprint arXiv:1811.12624","author":"Barezi Elham J","year":"2018","unstructured":"Elham J Barezi, Peyman Momeni, and Pascale Fung. 2018. Modality-based factorization for multimodal fusion. arXiv preprint arXiv:1811.12624 (2018)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25207-0_14"},{"key":"e_1_3_2_1_5_1","volume-title":"WebQA: Multihop and Multimodal QA. CoRR abs\/2109.00590","author":"Chang Yingshan","year":"2021","unstructured":"Yingshan Chang, Mridu Narang, Hisami Suzuki, Guihong Cao, Jianfeng Gao, and Yonatan Bisk. 2021. WebQA: Multihop and Multimodal QA. CoRR abs\/2109.00590 (2021). arXiv:2109.00590 https:\/\/arxiv.org\/abs\/2109.00590"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635777"},{"key":"e_1_3_2_1_8_1","unstructured":"Yuning Du Chenxia Li Ruoyu Guo Xiaoting Yin Weiwei Liu Jun Zhou Yifan Bai Zilin Yu Yehua Yang Qingqing Dang and Haoshuang Wang. 2020. PP-OCR: A Practical Ultra Lightweight OCR System. arXiv:2009.09941 [cs.CV]"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"e_1_3_2_1_10_1","volume-title":"Are you talking to a machine? dataset and methods for multilingual image question. Advances in neural information processing systems 28","author":"Gao Haoyuan","year":"2015","unstructured":"Haoyuan Gao, Junhua Mao, Jie Zhou, Zhiheng Huang, Lei Wang, and Wei Xu. 2015. Are you talking to a machine? dataset and methods for multilingual image question. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38067-9_8"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6294"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10285-x"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Yunseok Jang Yale Song Youngjae Yu Youngjin Kim and Gunhee Kim. 2017. TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering. arXiv:1704.04497 [cs.CV]","DOI":"10.1109\/CVPR.2017.149"},{"key":"e_1_3_2_1_16_1","unstructured":"Sujay Kumar Jauhar Peter Turney and Eduard Hovy. 2016. TabMCQ: A Dataset of General Knowledge Tables and Multiple-choice Questions. arXiv:1602.03960 [cs.CL]"},{"key":"e_1_3_2_1_17_1","volume-title":"Figureqa: An annotated figure dataset for visual reasoning. arXiv preprint arXiv:1710.07300","author":"Kahou Samira Ebrahimi","year":"2017","unstructured":"Samira Ebrahimi Kahou, Vincent Michalski, Adam Atkinson, \u00c1kos K\u00e1d\u00e1r, Adam Trischler, and Yoshua Bengio. 2017. Figureqa: An annotated figure dataset for visual reasoning. arXiv preprint arXiv:1710.07300 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_19_1","volume-title":"Spatio-temporal grounding for video question answering. arXiv preprint arXiv:1904.11574","author":"Lei Jie","year":"2019","unstructured":"Jie Lei, Licheng Yu, Tamara L Berg, and Mohit Bansal. 2019. Tvqa+: Spatio-temporal grounding for video question answering. arXiv preprint arXiv:1904.11574 (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR","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 International conference on machine learning. PMLR, 19730-- 19742."},{"key":"e_1_3_2_1_21_1","unstructured":"Lei Li Yuwei Yin Shicheng Li Liang Chen Peiyi Wang Shuhuai Ren Mukai Li Yazheng Yang Jingjing Xu Xu Sun Lingpeng Kong and Qi Liu. 2023. M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning. arXiv:2306.04387 [cs.CV]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_23_1","volume-title":"Qibin Zhao, Ruslan Salakhutdinov, and Louis-Philippe Morency.","author":"Liang Paul Pu","year":"2019","unstructured":"Paul Pu Liang, Zhun Liu, Yao-Hung Hubert Tsai, Qibin Zhao, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2019. Learning representations from imperfect time series data via tensor rank regularization. arXiv preprint arXiv:1907.01011 (2019)."},{"key":"e_1_3_2_1_24_1","unstructured":"Fangyu Liu Francesco Piccinno Syrine Krichene Chenxi Pang Kenton Lee Mandar Joshi Yasemin Altun Nigel Collier and Julian Martin Eisenschlos. 2022. MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:254854495"},{"key":"e_1_3_2_1_25_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems 36 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.626"},{"key":"e_1_3_2_1_27_1","volume-title":"Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424","author":"Maaz Muhammad","year":"2023","unstructured":"Muhammad Maaz, Hanoona Rasheed, Salman Khan, and Fahad Shahbaz Khan. 2023. Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"A multi-world approach to question answering about real-world scenes based on uncertain input. Advances in neural information processing systems 27","author":"Malinowski Mateusz","year":"2014","unstructured":"Mateusz Malinowski and Mario Fritz. 2014. A multi-world approach to question answering about real-world scenes based on uncertain input. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_29_1","volume-title":"Jia Qing Tan, Shafiq R. Joty, and Enamul Hoque.","author":"Masry Ahmed","year":"2022","unstructured":"Ahmed Masry, Xuan Long Do, Jia Qing Tan, Shafiq R. Joty, and Enamul Hoque. 2022. ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning. ArXiv abs\/2203.10244 (2022). https:\/\/api. semanticscholar.org\/CorpusID:247593713"},{"key":"e_1_3_2_1_30_1","volume-title":"Jia Qing Tan, Shafiq Joty, and Enamul Hoque.","author":"Masry Ahmed","year":"2022","unstructured":"Ahmed Masry, Do Xuan Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022. ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning. arXiv:2203.10244 [cs.CL]"},{"key":"e_1_3_2_1_31_1","volume-title":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Methani Nitesh","year":"2019","unstructured":"Nitesh Methani, Pritha Ganguly, Mitesh M. Khapra, and Pratyush Kumar. 2019. PlotQA: Reasoning over Scientific Plots. 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) (2019), 1516--1525. https:\/\/api.semanticscholar. org\/CorpusID:210164961"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897739"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Panupong Pasupat and Percy Liang. 2015. Compositional Semantic Parsing on Semi-Structured Tables. arXiv:1508.00305 [cs.CL]","DOI":"10.3115\/v1\/P15-1142"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.134"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.10.005"},{"key":"e_1_3_2_1_37_1","volume-title":"100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250","author":"Rajpurkar Pranav","year":"2016","unstructured":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)."},{"key":"e_1_3_2_1_38_1","first-page":"5","article-title":"Image question answering: A visual semantic embedding model and a new dataset","volume":"1","author":"Ren Mengye","year":"2015","unstructured":"Mengye Ren, Ryan Kiros, and Richard Zemel. 2015. Image question answering: A visual semantic embedding model and a new dataset. Proc. Advances in Neural Inf. Process. Syst 1, 2 (2015), 5.","journal-title":"Proc. Advances in Neural Inf. Process. Syst"},{"key":"e_1_3_2_1_39_1","volume-title":"Levine (Eds.)","volume":"36","author":"Sanders Kate","year":"2023","unstructured":"Kate Sanders, David Etter, Reno Kriz, and Benjamin Van Durme. 2023. Multi- VENT: Multilingual Videos of Events and Aligned Natural Text. In Advances in Neural Information Processing Systems, A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 51065--51079. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/ a054ff49751dbc991ec30ae479397c3d-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_2_1_40_1","volume-title":"Pandagpt: One model to instruction-follow them all. arXiv preprint arXiv:2305.16355","author":"Su Yixuan","year":"2023","unstructured":"Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, and Deng Cai. 2023. Pandagpt: One model to instruction-follow them all. arXiv preprint arXiv:2305.16355 (2023)."},{"key":"e_1_3_2_1_41_1","unstructured":"Alon Talmor Ori Yoran Amnon Catav Dan Lahav Yizhong Wang Akari Asai Gabriel Ilharco Hannaneh Hajishirzi and Jonathan Berant. 2021. MultiModalQA: Complex Question Answering over Text Tables and Images. arXiv:2104.06039 [cs.CL]"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"e_1_3_2_1_43_1","volume-title":"Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560","author":"Wang Yizhong","year":"2022","unstructured":"Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560 (2022)."},{"key":"e_1_3_2_1_44_1","volume-title":"Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519","author":"Wu Shengqiong","year":"2023","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2023. Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380688.3380693"},{"key":"e_1_3_2_1_46_1","volume-title":"Baize: An opensource chat model with parameter-efficient tuning on self-chat data. arXiv preprint arXiv:2304.01196","author":"Xu Canwen","year":"2023","unstructured":"Canwen Xu, Daya Guo, Nan Duan, and Julian McAuley. 2023. Baize: An opensource chat model with parameter-efficient tuning on self-chat data. arXiv preprint arXiv:2304.01196 (2023)."},{"key":"e_1_3_2_1_47_1","unstructured":"Dejing Xu Zhou Zhao Jun Xiao Fei Wu Hanwang Zhang Xiangnan He and Yueting Zhuang. 2017. Video Question Answering via Gradually Refined Attention over Appearance and Motion. In ACM Multimedia."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.11.022"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.165"},{"key":"e_1_3_2_1_50_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi Chaoya Jiang Chenliang Li Yuanhong Xu Hehong Chen Junfeng Tian Qian Qi Ji Zhang and Fei Huang. 2023. mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality. arXiv:2304.14178 [cs.CL]"},{"key":"e_1_3_2_1_51_1","unstructured":"Qinghao Ye Haiyang Xu Jiabo Ye Ming Yan Anwen Hu Haowei Liu Qi Qian Ji Zhang Fei Huang and Jingren Zhou. 2023. mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration. arXiv:2311.04257 [cs.CL]"},{"key":"e_1_3_2_1_52_1","volume-title":"Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and textto- sql task. arXiv preprint arXiv:1809.08887","author":"Yu Tao","year":"2018","unstructured":"Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, et al. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and textto- sql task. arXiv preprint arXiv:1809.08887 (2018)."},{"key":"e_1_3_2_1_53_1","volume-title":"Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250","author":"Zadeh Amir","year":"2017","unstructured":"Amir Zadeh, Minghai Chen, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"e_1_3_2_1_55_1","volume-title":"Speechgpt: Empowering large language models with intrinsic cross-modal conversational abilities. arXiv preprint arXiv:2305.11000","author":"Zhang Dong","year":"2023","unstructured":"Dong Zhang, Shimin Li, Xin Zhang, Jun Zhan, Pengyu Wang, Yaqian Zhou, and Xipeng Qiu. 2023. Speechgpt: Empowering large language models with intrinsic cross-modal conversational abilities. arXiv preprint arXiv:2305.11000 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Video-llama: An instructiontuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. 2023. Video-llama: An instructiontuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","unstructured":"Bowen Zhao Changkai Ji Yuejie Zhang Wen He Yingwen Wang Qing Wang Rui Feng and Xiaobo Zhang. 2023. Large Language Models are Complex Table Parsers. arXiv:2312.11521 [cs.CL]","DOI":"10.18653\/v1\/2023.emnlp-main.914"},{"key":"e_1_3_2_1_58_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681053","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681053"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":58,"alternative-id":["10.1145\/3664647.3681053","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681053","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}