{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:53:38Z","timestamp":1778860418594,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of China","award":["62006034"],"award-info":[{"award-number":["62006034"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611810","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"5464-5473","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6933-922X","authenticated-orcid":false,"given":"Bo","family":"Zhang","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4656-7446","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7146-8036","authenticated-orcid":false,"given":"Hui","family":"Ma","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-978X","authenticated-orcid":false,"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0872-7688","authenticated-orcid":false,"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 30th ACM International Conference on Multimedia. 4142--4153","author":"Chen Feilong","unstructured":"Feilong Chen, Duzhen Zhang, Xiuyi Chen, Jing Shi, Shuang Xu, and Bo XU. 2022. Unsupervised and Pseudo-Supervised Vision-Language Alignment in Visual Dialog. In Proceedings of the 30th ACM International Conference on Multimedia. 4142--4153."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1925--1935","author":"Chen Yun","unstructured":"Yun Chen, Yang Liu, Yong Cheng, and Victor O.K. Li. 2017. A Teacher-Student Framework for Zero-Resource Neural Machine Translation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1925--1935."},{"key":"e_1_3_2_1_3_1","volume-title":"Visual Dialog. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","author":"Das Abhishek","year":"2017","unstructured":"Abhishek Das, Satwik Kottur, Khushi Gupta, Avi Singh, Deshraj Yadav, Jose M. F. Moura, Devi Parikh, and Dhruv Batra. 2017. Visual Dialog. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Dong Li","year":"2019","unstructured":"Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, and Hsiao-Wuen Hon. 2019. Unified Language Model Pretraining for Natural Language Understanding and Generation. In Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Learning Representations.","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 International Conference on Learning Representations."},{"key":"e_1_3_2_1_6_1","volume-title":"Maureen de Seyssel, Patricia Roz\u00e9, Morgane Rivi\u00e8re, Eugene Kharitonov, and Emmanuel Dupoux.","author":"Dunbar Ewan","year":"2021","unstructured":"Ewan Dunbar, Mathieu Bernard, Nicolas Hamilakis, Tu Anh Nguyen, Maureen de Seyssel, Patricia Roz\u00e9, Morgane Rivi\u00e8re, Eugene Kharitonov, and Emmanuel Dupoux. 2021. The Zero Resource Speech Challenge 2021: Spoken language modelling. In Interspeech 2021-Conference of the International Speech Communication Association."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Ewan Dunbar Julien Karadayi Mathieu Bernard Xuan-Nga Cao Robin Algayres Lucas Ondel Laurent Besacier Sakriani Sakti and Emmanuel Dupoux. 2020. The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units. (2020).","DOI":"10.21437\/Interspeech.2020-2743"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4103"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1026"},{"key":"e_1_3_2_1_10_1","volume-title":"The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educational and psychological measurement 33, 3","author":"Fleiss Joseph L","year":"1973","unstructured":"Joseph L Fleiss and Jacob Cohen. 1973. The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educational and psychological measurement 33, 3 (1973), 613--619."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173851"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"e_1_3_2_1_15_1","first-page":"8475","article-title":"Zero-Resource Knowledge-Grounded Dialogue Generation","volume":"33","author":"Li Linxiao","year":"2020","unstructured":"Linxiao Li, Can Xu, Wei Wu, YUFAN ZHAO, Xueliang Zhao, and Chongyang Tao. 2020. Zero-Resource Knowledge-Grounded Dialogue Generation. In Advances in Neural Information Processing Systems, Vol. 33. 8475--8485.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.435"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462970"},{"key":"e_1_3_2_1_18_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. 74--81."},{"key":"e_1_3_2_1_19_1","first-page":"740","article-title":"Microsoft COCO","volume":"2014","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Computer Vision - ECCV 2014. 740--755.","journal-title":"Common Objects in Context. In Computer Vision - ECCV"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1230"},{"key":"e_1_3_2_1_21_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462824"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 462--472","author":"Mostafazadeh Nasrin","year":"2017","unstructured":"Nasrin Mostafazadeh, Chris Brockett, Bill Dolan, Michel Galley, Jianfeng Gao, Georgios Spithourakis, and Lucy Vanderwende. 2017. Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 462--472."},{"key":"e_1_3_2_1_24_1","volume-title":"Retrieved","author":"AI.","year":"2022","unstructured":"OpenAI. 2022. ChatGPT: Optimizing Language Models for Dialogue. Retrieved November 30, 2022 from https:\/\/openai.com\/blog\/chatgpt\/"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","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 38th International Conference on Machine Learning, Vol. 139. 8748--8763."},{"key":"e_1_3_2_1_27_1","unstructured":"Ashwin Ram Rohit Prasad Chandra Khatri Anu Venkatesh Raefer Gabriel Qing Liu Jeff Nunn Behnam Hedayatnia Ming Cheng Ashish Nagar et al. 2018. Conversational ai: The science behind the alexa prize. (2018). arXiv:1801.03604"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475568"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.219"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).","author":"Sun Qingfeng","unstructured":"Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, and Daxin Jiang. [n. d.]. Multimodal Dialogue Response Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)."},{"key":"e_1_3_2_1_32_1","volume-title":"Weinberger (Eds.)","volume":"27","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems, Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K.Q. Weinberger (Eds.), Vol. 27."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17675"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3161151"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 270--278","author":"Zhang Yizhe","year":"2020","unstructured":"Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2020. DIALOGPT: Large-Scale Generative Pre-training for Conversational Response Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 270--278."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.164"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00368"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611810","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:10:12Z","timestamp":1755821412000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611810"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":39,"alternative-id":["10.1145\/3581783.3611810","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611810","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}