{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:10:28Z","timestamp":1781086228239,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":52,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672144,61872072"],"award-info":[{"award-number":["61672144,61872072"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","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\/3664647.3681012","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"2079-2088","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["AutoGraph: Enabling Visual Context via Graph Alignment in Open Domain Multi-Modal Dialogue Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8303-6943","authenticated-orcid":false,"given":"Deji","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9056-1308","authenticated-orcid":false,"given":"Donghong","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0247-9866","authenticated-orcid":false,"given":"Ye","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9512-7036","authenticated-orcid":false,"given":"Bo","family":"Ning","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3218-7320","authenticated-orcid":false,"given":"Mengxiang","family":"Li","sequence":"additional","affiliation":[{"name":"China Telecom Corp Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5929-2567","authenticated-orcid":false,"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7465-1082","authenticated-orcid":false,"given":"Shuangyong","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd, Beijing, 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":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_3_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Dettmers Tim","year":"2024","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2024. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_4_1","volume-title":"MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation. In The 61st Annual Meeting Of The Association For Computational Linguistics.","author":"Feng Jiazhan","year":"2023","unstructured":"Jiazhan Feng, Qingfeng Sun, Can Xu, Pu Zhao, Yaming Yang, Chongyang Tao, Dongyan Zhao, and Qingwei Lin. 2023. MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation. In The 61st Annual Meeting Of The Association For Computational Linguistics."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"e_1_3_2_1_6_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_7_1","volume-title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages. arXiv preprint arXiv:2308.12038","author":"Hu Jinyi","year":"2023","unstructured":"Jinyi Hu, Yuan Yao, Chongyi Wang, Shan Wang, Yinxu Pan, Qianyu Chen, Tianyu Yu, Hanghao Wu, Yue Zhao, Haoye Zhang, Xu Han, Yankai Lin, Jiao Xue, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2023. Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages. arXiv preprint arXiv:2308.12038 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3383123","article-title":"Challenges in building intelligent open-domain dialog systems","volume":"38","author":"Huang Minlie","year":"2020","unstructured":"Minlie Huang, Xiaoyan Zhu, and Jianfeng Gao. 2020. Challenges in building intelligent open-domain dialog systems. ACM Transactions on Information Systems (TOIS), Vol. 38, 3 (2020), 1--32.","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.61"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16273"},{"key":"e_1_3_2_1_12_1","volume-title":"Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations.","author":"Thomas","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","volume-title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-modal Dialogue Datasets. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following.","author":"Lee Young-Jun","year":"2023","unstructured":"Young-Jun Lee, Byungsoo Ko, Han-Gyu Kim, Jonghwan Hyeon, and Ho-Jin Choi. 2023. DialogCC: An Automated Pipeline for Creating High-Quality Multi-modal Dialogue Datasets. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following."},{"key":"e_1_3_2_1_14_1","first-page":"9287","article-title":"Elevater: A benchmark and toolkit for evaluating language-augmented visual models","volume":"35","author":"Li Chunyuan","year":"2022","unstructured":"Chunyuan Li, Haotian Liu, Liunian Li, Pengchuan Zhang, Jyoti Aneja, Jianwei Yang, Ping Jin, Houdong Hu, Zicheng Liu, Yong Jae Lee, et al. 2022. Elevater: A benchmark and toolkit for evaluating language-augmented visual models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 9287--9301.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.435"},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612425"},{"key":"e_1_3_2_1_20_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","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, Vol. 36 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"e_1_3_2_1_22_1","volume-title":"Openvidial: A large-scale, open-domain dialogue dataset with visual contexts. arXiv preprint arXiv:2012.15015","author":"Meng Yuxian","year":"2020","unstructured":"Yuxian Meng, Shuhe Wang, Qinghong Han, Xiaofei Sun, Fei Wu, Rui Yan, and Jiwei Li. 2020. Openvidial: A large-scale, open-domain dialogue dataset with visual contexts. arXiv preprint arXiv:2012.15015 (2020)."},{"key":"e_1_3_2_1_23_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_24_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/600"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_2_1_28_1","volume-title":"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, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_29_1","first-page":"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 machine learning research, Vol. 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_30_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. arXiv preprint arXiv:1801.03604 (2018)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11331"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475568"},{"key":"e_1_3_2_1_34_1","volume-title":"Image chat: Engaging grounded conversations. arXiv preprint arXiv:1811.00945","author":"Shuster Kurt","year":"2018","unstructured":"Kurt Shuster, Samuel Humeau, Antoine Bordes, and Jason Weston. 2018. Image chat: Engaging grounded conversations. arXiv preprint arXiv:1811.00945 (2018)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.398"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.204"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.327"},{"key":"e_1_3_2_1_38_1","unstructured":"Yu Sun Shuohuan Wang Shikun Feng Siyu Ding Chao Pang Junyuan Shang Jiaxiang Liu Xuyi Chen Yanbin Zhao Yuxiang Lu et al. 2021. Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. arXiv preprint arXiv:2107.02137 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657775"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. CoRR Vol. abs\/2307.09288 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2307.09288 showeprint[arXiv]2307.09288","DOI":"10.48550\/ARXIV.2307.09288"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.479"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.868"},{"key":"e_1_3_2_1_43_1","volume-title":"A larger-scale, open-domain dialogue generation dataset with visual contexts. arXiv preprint arXiv:2109.12761","author":"Wang Shuhe","year":"2021","unstructured":"Shuhe Wang, Yuxian Meng, Xiaoya Li, Xiaofei Sun, Rongbin Ouyang, and Jiwei Li. 2021. Openvidial 2.0: A larger-scale, open-domain dialogue generation dataset with visual contexts. arXiv preprint arXiv:2109.12761 (2021)."},{"key":"e_1_3_2_1_44_1","volume-title":"Zujin Guo, Kaiyang Zhou, Wayne Zhang, and Ziwei Liu.","author":"Yang Jingkang","year":"2022","unstructured":"Jingkang Yang, Yi Zhe Ang, Zujin Guo, Kaiyang Zhou, Wayne Zhang, and Ziwei Liu. 2022. Panoptic Scene Graph Generation. In ECCV."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17675"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611810"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475234"},{"key":"e_1_3_2_1_48_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations.","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_49_1","volume-title":"MuSE: A Multi-scale Emotional Flow Graph Model for Empathetic Dialogue Generation. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 491--507","author":"Zhao Deji","year":"2023","unstructured":"Deji Zhao, Donghong Han, Ye Yuan, Chao Wang, and Shuangyong Song. 2023. MuSE: A Multi-scale Emotional Flow Graph Model for Empathetic Dialogue Generation. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 491--507."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.843"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference. 5778--5786","author":"Zheng Yinhe","year":"2022","unstructured":"Yinhe Zheng, Guanyi Chen, Xin Liu, and Jian Sun. 2022. MMChat: Multi-Modal Chat Dataset on Social Media. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. 5778--5786."}],"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\/3664647.3681012","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:36Z","timestamp":1750295856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681012"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3664647.3681012","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681012","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"}}]}}