{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:09:51Z","timestamp":1776888591038,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":47,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"PolyU internal grants","award":["ZVQ0, ZVVX"],"award-info":[{"award-number":["ZVQ0, ZVVX"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076212"],"award-info":[{"award-number":["62076212"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grants Council of Hong Kong","award":["15207122, 15207920, 15207821"],"award-info":[{"award-number":["15207122, 15207920, 15207821"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681651","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"9591-9600","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["SCREEN: A Benchmark for Situated Conversational Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8846-8622","authenticated-orcid":false,"given":"Dongding","family":"Lin","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8992-8336","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6124-1890","authenticated-orcid":false,"given":"Chak Tou","family":"Leong","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7360-8864","authenticated-orcid":false,"given":"Wenjie","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.04023"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1189"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2207.07934"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939746"},{"key":"e_1_3_2_2_5_1","volume-title":"SIMMC: Situated Interactive Multi-Modal Conversational Data Collection And Evaluation Platform. CoRR","author":"Crook Paul A.","year":"2019","unstructured":"Paul A. Crook, Shivani Poddar, Ankita De, Semir Shafi, David Whitney, Alborz Geramifard, and Rajen Subba. 2019. SIMMC: Situated Interactive Multi-Modal Conversational Data Collection And Evaluation Platform. CoRR, Vol. abs\/1911.02690 (2019). showeprint[arXiv]1911.02690"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613755"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/S11280-023-01219--2"},{"key":"e_1_3_2_2_8_1","volume-title":"Measuring nominal scale agreement among many raters. Psychological bulletin","author":"Fleiss Joseph L","year":"1971","unstructured":"Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, Vol. 76, 5 (1971), 378."},{"key":"e_1_3_2_2_9_1","volume-title":"The structure of phenotypic personality traits. American psychologist","author":"Goldberg Lewis R","year":"1993","unstructured":"Lewis R Goldberg. 1993. The structure of phenotypic personality traits. American psychologist, Vol. 48, 1 (1993), 26."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2301.07597"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.654"},{"key":"e_1_3_2_2_12_1","volume-title":"AAAI 2021 DSTC9 Workshop.","author":"Huang Xin","year":"2021","unstructured":"Xin Huang, Chor Seng Tan, Yan Bin Ng, Wei Shi, Kheng Hui Yeo, Ridong Jiang, and Jung-jae Kim. 2021. Joint generation and bi-encoder for situated interactive multimodal conversations. In AAAI 2021 DSTC9 Workshop."},{"key":"e_1_3_2_2_13_1","volume-title":"GPT-4o: The Cutting-Edge Advancement in Multimodal LLM. Authorea Preprints","author":"Islam Raisa","year":"2024","unstructured":"Raisa Islam and Owana Marzia Moushi. 2024. GPT-4o: The Cutting-Edge Advancement in Multimodal LLM. Authorea Preprints (2024)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453154"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.2016299"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of The Eleventh Dialog System Technology Challenge. 235--241","author":"Kottur Satwik","year":"2023","unstructured":"Satwik Kottur and Seungwhan Moon. 2023. Overview of Situated and Interactive Multimodal Conversations (SIMMC) 2.1 Track at DSTC 11. In Proceedings of The Eleventh Dialog System Technology Challenge. 235--241."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.401"},{"key":"e_1_3_2_2_18_1","volume-title":"Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems. CoRR","author":"Kung Po-Nien","year":"2021","unstructured":"Po-Nien Kung, Chung-Cheng Chang, Tse-Hsuan Yang, Hsin-Kai Hsu, Yu-Jia Liou, and Yun-Nung Chen. 2021. Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems. CoRR, Vol. abs\/2110.05221 (2021)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2303.17760"},{"key":"e_1_3_2_2_20_1","volume-title":"Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal.","author":"Li Raymond","year":"2018","unstructured":"Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal. 2018. Towards Deep Conversational Recommendations. In Advances in Neural Information Processing Systems. 9748--9758."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462970"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I4.25567"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.356"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.98"},{"key":"e_1_3_2_2_25_1","volume-title":"Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark. In Findings of the Association for Computational Linguistics: ACL 2023","author":"Long Yuxing","year":"2023","unstructured":"Yuxing Long, Binyuan Hui, Caixia Yuan, Fei Huang, Yongbin Li, and Xiaojie Wang. 2023. Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9--14, 2023, Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (Eds.). Association for Computational Linguistics, 3515--3533."},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of The Eleventh Dialog System Technology Challenge. 15--24","author":"Long Yuxing","year":"2023","unstructured":"Yuxing Long, Huibin Zhang, Binyuan Hui, Zhenglu Yang, Caixia Yuan, Xiaojie Wang, Fei Huang, and Yongbin Li. 2023. Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning. In Proceedings of The Eleventh Dialog System Technology Challenge. 15--24."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3480025"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.96"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108724"},{"key":"e_1_3_2_2_30_1","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11331"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210002"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.72"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.345"},{"key":"e_1_3_2_2_37_1","unstructured":"Yuxiang Wu Zhengyao Jiang Akbir Khan Yao Fu Laura Ruis Edward Grefenstette and Tim Rockt\u00e4schel. 2023. ChatArena: Multi-Agent Language Game Environments for Large Language Models."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3155900"},{"key":"e_1_3_2_2_39_1","volume-title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V. CoRR","author":"Yang Jianwei","year":"2023","unstructured":"Jianwei Yang, Hao Zhang, Feng Li, Xueyan Zou, Chunyuan Li, and Jianfeng Gao. 2023. Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V. CoRR, Vol. abs\/2310.11441 (2023)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597022"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.21437\/INTERSPEECH.2019--1886"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475234"},{"key":"e_1_3_2_2_43_1","volume-title":"KECRS: Towards Knowledge-Enriched Conversational Recommendation System. CoRR","author":"Zhang Tong","year":"2021","unstructured":"Tong Zhang, Yong Liu, Peixiang Zhong, Chen Zhang, Hao Wang, and Chunyan Miao. 2021. KECRS: Towards Knowledge-Enriched Conversational Recommendation System. CoRR, Vol. abs\/2105.08261 (2021)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.04473"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403143"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.365"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.10592"}],"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\/3664647.3681651","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681651"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":47,"alternative-id":["10.1145\/3664647.3681651","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681651","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"}}]}}