{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:16:27Z","timestamp":1765307787986,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","funder":[{"name":"New Generation Artificial Intelligence-National Science and Technology Major Project","award":["2023ZD0121100"],"award-info":[{"award-number":["2023ZD0121100"]}]},{"name":"the National Natural Science Foundation of China (NSFC)","award":["62441614, 62176078"],"award-info":[{"award-number":["62441614, 62176078"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758178","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"12501-12508","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Ensuring Responses Contain Appropriate Images: Timing Judgment for Multimodal Responses"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8138-7387","authenticated-orcid":false,"given":"Hao","family":"Yang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2378-3580","authenticated-orcid":false,"given":"Tian","family":"Zheng","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1166-1459","authenticated-orcid":false,"given":"Yanyan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2543-5604","authenticated-orcid":false,"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_3_1","volume-title":"Mmdialog: A large-scale multi-turn dialogue dataset towards multi-modal open-domain conversation. arXiv preprint arXiv:2211.05719","author":"Feng Jiazhan","year":"2022","unstructured":"Jiazhan Feng, Qingfeng Sun, Can Xu, Pu Zhao, Yaming Yang, Chongyang Tao, Dongyan Zhao, and Qingwei Lin. 2022. Mmdialog: A large-scale multi-turn dialogue dataset towards multi-modal open-domain conversation. arXiv preprint arXiv:2211.05719 (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Language model as an annotator: Exploring DialoGPT for dialogue summarization. arXiv preprint arXiv:2105.12544","author":"Feng Xiachong","year":"2021","unstructured":"Xiachong Feng, Xiaocheng Feng, Libo Qin, Bing Qin, and Ting Liu. 2021. Language model as an annotator: Exploring DialoGPT for dialogue summarization. arXiv preprint arXiv:2105.12544 (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations (ICLR).","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_6_1","first-page":"21487","article-title":"Generating images with multimodal language models","volume":"36","author":"Koh Jing Yu","year":"2023","unstructured":"Jing Yu Koh, Daniel Fried, and Russ R Salakhutdinov. 2023. Generating images with multimodal language models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 21487-21506.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","volume-title":"Dialogcc: Large-scale multi-modal dialogue dataset. arXiv preprint arXiv:2212.04119","author":"Lee Young-Jun","year":"2022","unstructured":"Young-Jun Lee, Byungsoo Ko, Han-Gyu Kim, and Ho-Jin Choi. 2022. Dialogcc: Large-scale multi-modal dialogue dataset. arXiv preprint arXiv:2212.04119 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_9_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_10_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning (ICML). 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 (ICML). 8748-8763."},{"key":"e_1_3_2_1_12_1","volume-title":"International conference on machine learning. Pmlr, 8821-8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International conference on machine learning. Pmlr, 8821-8831."},{"key":"e_1_3_2_1_13_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_14_1","volume-title":"Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560","author":"Wang Yizhong","year":"2022","unstructured":"Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560 (2022)."},{"key":"e_1_3_2_1_15_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_16_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et al. 2023. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Photochat: A human-human dialogue dataset with photo sharing behavior for joint image-text modeling. arXiv preprint arXiv:2108.01453","author":"Zang Xiaoxue","year":"2021","unstructured":"Xiaoxue Zang, Lijuan Liu, Maria Wang, Yang Song, Hao Zhang, and Jindong Chen. 2021. Photochat: A human-human dialogue dataset with photo sharing behavior for joint image-text modeling. arXiv preprint arXiv:2108.01453 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"MMChat: Multi-modal chat dataset on social media. arXiv preprint arXiv:2108.07154","author":"Zheng Yinhe","year":"2021","unstructured":"Yinhe Zheng, Guanyi Chen, Xin Liu, and Jian Sun. 2021. MMChat: Multi-modal chat dataset on social media. arXiv preprint arXiv:2108.07154 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:14:57Z","timestamp":1765307697000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758178"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":19,"alternative-id":["10.1145\/3746027.3758178","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758178","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}