{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:20:52Z","timestamp":1777735252103,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Key Research and Development Project of New Generation Artificial Intelligence","award":["No.:2018AAA0102502"],"award-info":[{"award-number":["No.:2018AAA0102502"]}]},{"name":"the Shenzhen College Stability Support Plan","award":["No.: GXWD20220817144428005"],"award-info":[{"award-number":["No.: GXWD20220817144428005"]}]},{"name":"the Shandong Provincial Natural Science Foundation","award":["No.:ZR2022YQ59"],"award-info":[{"award-number":["No.:ZR2022YQ59"]}]},{"name":"the National Natural Science Foundation of China","award":["No.: 62006142, No.:U1936203, and No.:62236003"],"award-info":[{"award-number":["No.: 62006142, No.:U1936203, and No.:62236003"]}]},{"name":"the Special Fund for distinguished professors of Shandong Jianzhu University"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591633","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"195-204","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Adapting Generative Pretrained Language Model for Open-domain Multimodal Sentence Summarization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2982-3942","authenticated-orcid":false,"given":"Dengtian","family":"Lin","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9827-5835","authenticated-orcid":false,"given":"Liqiang","family":"Jing","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-4197","authenticated-orcid":false,"given":"Xuemeng","family":"Song","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5764","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0932-8910","authenticated-orcid":false,"given":"Teng","family":"Sun","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1175"},{"key":"e_1_3_2_2_2_1","volume-title":"TransZero: Attribute-Guided Transformer for Zero-Shot Learning. In The Innovative Applications of Artificial Intelligence Conference. AAAI Press, 330--338","author":"Chen Shiming","year":"2022","unstructured":"Shiming Chen, Ziming Hong, Yang Liu, Guo-Sen Xie, Baigui Sun, Hao Li, Qinmu Peng, Ke Lu, and Xinge You. 2022. TransZero: Attribute-Guided Transformer for Zero-Shot Learning. In The Innovative Applications of Artificial Intelligence Conference. AAAI Press, 330--338."},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 1597--1607","author":"Chen Ting","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the International Conference on Machine Learning. PMLR, 1597--1607."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ACL, 93--98","author":"Chopra Sumit","unstructured":"Sumit Chopra, Michael Auli, and Alexander M. Rush. 2016. Abstractive Sentence Summarization with Attentive Recurrent Neural Networks. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ACL, 93--98."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622655.1622667"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ACL, 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ACL, 4171--4186."},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--22","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--22."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1523"},{"key":"e_1_3_2_2_9_1","volume-title":"SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition. In The Innovative Applications of Artificial Intelligence Conference. AAAI Press, 551--560","author":"Fan Zhaoxin","year":"2022","unstructured":"Zhaoxin Fan, Zhenbo Song, Hongyan Liu, Zhiwu Lu, Jun He, and Xiaoyong Du. 2022. SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition. In The Innovative Applications of Artificial Intelligence Conference. AAAI Press, 551--560."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_2_2_11_1","volume-title":"Automatic Generation of Chinese Short Product Titles for Mobile Display. In The Innovative Applications of Artificial Intelligence Conference. AAAI Press, 9460--9465","author":"Gong Yu","year":"2019","unstructured":"Yu Gong, Xusheng Luo, Kenny Q. Zhu, Wenwu Ou, Zhao Li, and Lu Duan. 2019. Automatic Generation of Chinese Short Product Titles for Mobile Display. In The Innovative Applications of Artificial Intelligence Conference. AAAI Press, 9460--9465."},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics. ACL, 1631--1640","author":"Gu Jiatao","unstructured":"Jiatao Gu, Zhengdong Lu, Hang Li, and Victor O. K. Li. 2016. Incorporating Copying Mechanism in Sequence-to-Sequence Learning. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. ACL, 1631--1640."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_14_1","volume-title":"Vision Enhanced Generative Pre-trained Language Model for Multimodal Sentence Summarization. Machine Intelligence Research","author":"Jing Liqiang","year":"2023","unstructured":"Liqiang Jing, Yiren Li, Junhao Xu, Yongcan Yu, Pei Shen, and Xuemeng Song. 2023. Vision Enhanced Generative Pre-trained Language Model for Multimodal Sentence Summarization. Machine Intelligence Research (2023), 1--10."},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--15","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--15."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/577"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.496"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2031"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics. ACL, 74--81","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. ACL, 74--81."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.144"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531776"},{"key":"e_1_3_2_2_23_1","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems. CAI, 3111--3119","author":"Mikolov Tom\u00e1","year":"2013","unstructured":"Tom\u00e1 s Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In Proceedings of the Conference and Workshop on Neural Information Processing Systems. CAI, 3111--3119."},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. ACL, 1532--1543","author":"Pennington Jeffrey","unstructured":"Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global Vectors for Word Representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. ACL, 1532--1543."},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 8748--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 International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_26_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. Journal of Artificial Intelligence Research, Vol. 21 (2020), 140:1--140:67.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-015-0089-9"},{"key":"e_1_3_2_2_29_1","volume-title":"Manning","author":"Liu Peter J.","year":"2017","unstructured":"Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get To The Point: Summarization with Pointer-Generator Networks. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. ACL, 1073--1083."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475321"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532076"},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems. CAI, 5998--6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proceedings of the Annual Conference on Neural Information Processing Systems. CAI, 5998--6008."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531825"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475665"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.326"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531795"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1101"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462938"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591633","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:40Z","timestamp":1750182700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591633"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":39,"alternative-id":["10.1145\/3539618.3591633","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591633","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}