{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:55:03Z","timestamp":1782402903295,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":56,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["x2rjD2240100"],"award-info":[{"award-number":["x2rjD2240100"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Computer Federation (CCF)-Zhipu AI Large Model Fund"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076100"],"award-info":[{"award-number":["62076100"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Fund for Basic and Applied Basic Research?Regional Joint Fund Project (Key Project)","award":["2023B1515120078"],"award-info":[{"award-number":["2023B1515120078"]}]},{"name":"Guangdong Provincial Natural Science Foundation for Outstanding Youth Team Project","award":["2024B1515040010"],"award-info":[{"award-number":["2024B1515040010"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2020B0101100002"],"award-info":[{"award-number":["2020B0101100002"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680717","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"8701-8710","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3925-6225","authenticated-orcid":false,"given":"li","family":"yuan","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-789X","authenticated-orcid":false,"given":"Yi","family":"Cai","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8879-6596","authenticated-orcid":false,"given":"Junsheng","family":"Huang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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\/3581783.3612536"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of ECAI 2020. 2006","author":"Eberts Markus","year":"2020","unstructured":"Markus Eberts and Adrian Ulges. 2020. Span-Based Joint Entity and Relation Extraction with Transformer Pre-Training. In Proceedings of ECAI 2020. 2006--2013."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.319"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297378"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence. 6407--6414","author":"Gao Tianyu","year":"2019","unstructured":"Tianyu Gao, Xu Han, Zhiyuan Liu, and Maosong Sun. 2019. Hybrid attentionbased prototypical networks for noisy few-shot relation classification. In Proceedings of the AAAI conference on artificial intelligence. 6407--6414."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.204"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","volume-title":"Few-shot named entity recognition: A comprehensive study. arXiv preprint arXiv:2012.14978","author":"Huang Jiaxin","year":"2020","unstructured":"Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao, and Jiawei Han. 2020. Few-shot named entity recognition: A comprehensive study. arXiv preprint arXiv:2012.14978 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.488"},{"key":"e_1_3_2_1_12_1","volume-title":"Prompt ChatGPT In MNER: Improved multimodal named entity recognition method based on auxiliary refining knowledge from ChatGPT. arXiv preprint arXiv:2305.12212","author":"Li Jinyuan","year":"2023","unstructured":"Jinyuan Li, Han Li, Zhuo Pan, and Gang Pan. 2023. Prompt ChatGPT In MNER: Improved multimodal named entity recognition method based on auxiliary refining knowledge from ChatGPT. arXiv preprint arXiv:2305.12212 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.62"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the ICLR","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proceedings of the ICLR 2019."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the COLING 2022. 2055","author":"Lu Junyu","year":"2022","unstructured":"Junyu Lu, Dixiang Zhang, Jiaxing Zhang, and Pingjian Zhang. 2022. Flat Multimodal Interaction Transformer for Named Entity Recognition. In Proceedings of the COLING 2022. 2055--2064."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1105"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1078"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the ICML","author":"Qu Meng","year":"2020","unstructured":"Meng Qu, Tianyu Gao, Louis-Pascal Xhonneux, and Jian Tang. 2020. Few-shot relation extraction via bayesian meta-learning on relation graphs. In Proceedings of the ICML 2020. 7867--7876."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498409"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.142"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"e_1_3_2_1_24_1","volume-title":"Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Beck Labash, and Ashwin Gopinath. 2023. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of ICML","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. In Proceedings of ICML 2014."},{"key":"e_1_3_2_1_26_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems 30","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_2_1_28_1","first-page":"1952","article-title":"Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution","volume":"2021","author":"Verlinden Severine","year":"2021","unstructured":"Severine Verlinden, Klim Zaporojets, Johannes Deleu, Thomas Demeester, and Chris Develder. 2021. Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution. In Findings of the ACL-IJCNLP 2021. 1952--1957.","journal-title":"Findings of the ACL-IJCNLP"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531734"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591686"},{"key":"e_1_3_2_1_31_1","volume-title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework. CoRR abs\/2202.03052","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework. CoRR abs\/2202.03052 (2022)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.232"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467235"},{"key":"e_1_3_2_1_34_1","first-page":"1572","article-title":"TPLinker","volume":"2020","author":"Wang Yucheng","year":"2020","unstructured":"Yucheng Wang, Bowen Yu, Yueyang Zhang, Tingwen Liu, Hongsong Zhu, and Limin Sun. 2020. TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking. In Proceedings of the COLING 2020. 1572--1582.","journal-title":"In Proceedings of the COLING"},{"key":"e_1_3_2_1_35_1","volume-title":"A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382","author":"White Jules","year":"2023","unstructured":"Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C Schmidt. 2023. A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1533"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3263784"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413650"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.124"},{"key":"e_1_3_2_1_40_1","volume-title":"Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt. In Findings of the ACL","author":"Yang Xiaocui","year":"2023","unstructured":"Xiaocui Yang, Shi Feng, Daling Wang, Qi Sun, Wenfang Wu, Yifei Zhang, Pengfei Hong, and Soujanya Poria. 2023. Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt. In Findings of the ACL 2023. Toronto, Canada, 11575--11589."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.516"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the AAAI","author":"Yang Zhengyuan","year":"2022","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 knowledgebased vqa. In Proceedings of the AAAI 2022. 3081--3089."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Yang Yu and Dong Zhang. 2022. Few-Shot Multi-Modal Sentiment Analysis with Prompt-Based Vision-Aware Language Modeling. (2022) 1--6.","DOI":"10.1109\/ICME52920.2022.9859654"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548306"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the LRECCOLING","author":"Yuan Li","year":"2024","unstructured":"Li Yuan, Yi Cai, Haopeng Ren, and Jiexin Wang. 2024. A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation. In Proceedings of the LRECCOLING 2024. 759--772."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26309"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.206"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103264"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"e_1_3_2_1_53_1","volume-title":"A Picture IsWorth a Graph: Blueprint Debate on Graph for Multimodal Reasoning. arXiv preprint arXiv:2403.14972","author":"Zheng Changmeng","year":"2024","unstructured":"Changmeng Zheng, Dayong Liang, Wengyu Zhang, Xiao-Yong Wei, Tat-Seng Chua, and Qing Li. 2024. A Picture IsWorth a Graph: Blueprint Debate on Graph for Multimodal Reasoning. arXiv preprint arXiv:2403.14972 (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428274"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3013398"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.040"}],"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\/3664647.3680717","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:24Z","timestamp":1750291584000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680717"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":56,"alternative-id":["10.1145\/3664647.3680717","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680717","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"}}]}}