{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:40Z","timestamp":1750309480455,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3688993","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"11426-11428","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DEMON24: ACM MM24 Demonstrative Instruction Following Challenge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6590-365X","authenticated-orcid":false,"given":"Zhiqi","family":"Ge","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2258-1291","authenticated-orcid":false,"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0190-5261","authenticated-orcid":false,"given":"Qifan","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6075-6749","authenticated-orcid":false,"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9017-2508","authenticated-orcid":false,"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Oncel Tuzel, Ping Huang, Jiulong Shan, Jianjun Shi, and Meng Cao.","author":"Bai Haoping","year":"2023","unstructured":"Haoping Bai, Shancong Mou, Tatiana Likhomanenko, Ramazan Gokberk Cinbis, Oncel Tuzel, Ping Huang, Jiulong Shan, Jianjun Shi, and Meng Cao. 2023. VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON. arXiv preprint arXiv:2306.07890 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings, Part XXI 16","author":"Bansal Ankan","year":"2020","unstructured":"Ankan Bansal, Yuting Zhang, and Rama Chellappa. 2020. Visual question answering on image sets. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXI 16. Springer, 51--67."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00437"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"e_1_3_2_1_7_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arxiv: 2305.06500 [cs.CV]"},{"key":"e_1_3_2_1_8_1","volume-title":"Neural naturalist: generating fine-grained image comparisons. arXiv preprint arXiv:1909.04101","author":"Forbes Maxwell","year":"2019","unstructured":"Maxwell Forbes, Christine Kaeser-Chen, Piyush Sharma, and Serge Belongie. 2019. Neural naturalist: generating fine-grained image comparisons. arXiv preprint arXiv:1909.04101 (2019)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688994"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_37"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00275"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.686"},{"key":"e_1_3_2_1_16_1","volume-title":"Learning to describe differences between pairs of similar images. arXiv preprint arXiv:1808.10584","author":"Jhamtani Harsh","year":"2018","unstructured":"Harsh Jhamtani and Taylor Berg-Kirkpatrick. 2018. Learning to describe differences between pairs of similar images. arXiv preprint arXiv:1808.10584 (2018)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"19742","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 Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202). PMLR, 19730--19742."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.290"},{"key":"e_1_3_2_1_21_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning."},{"key":"e_1_3_2_1_22_1","volume-title":"Storydall-e: Adapting pretrained text-to-image transformers for story continuation. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27","author":"Maharana Adyasha","year":"2022","unstructured":"Adyasha Maharana, Darryl Hannan, and Mohit Bansal. 2022. Storydall-e: Adapting pretrained text-to-image transformers for story continuation. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXXVII. Springer, 70--87."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00206"},{"key":"e_1_3_2_1_26_1","volume-title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/arxiv.org\/abs\/1912","author":"Shridhar Mohit","year":"2020","unstructured":"Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, and Dieter Fox. 2020. ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/arxiv.org\/abs\/1912.01734"},{"key":"e_1_3_2_1_27_1","volume-title":"A corpus for reasoning about natural language grounded in photographs. arXiv preprint arXiv:1811.00491","author":"Suhr Alane","year":"2018","unstructured":"Alane Suhr, Stephanie Zhou, Ally Zhang, Iris Zhang, Huajun Bai, and Yoav Artzi. 2018. A corpus for reasoning about natural language grounded in photographs. arXiv preprint arXiv:1811.00491 (2018)."},{"key":"e_1_3_2_1_28_1","volume-title":"Multimodalqa: Complex question answering over text, tables and images. arXiv preprint arXiv:2104.06039","author":"Talmor Alon","year":"2021","unstructured":"Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, and Jonathan Berant. 2021. Multimodalqa: Complex question answering over text, tables and images. arXiv preprint arXiv:2104.06039 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"Expressing visual relationships via language. arXiv preprint arXiv:1906.07689","author":"Tan Hao","year":"2019","unstructured":"Hao Tan, Franck Dernoncourt, Zhe Lin, Trung Bui, and Mohit Bansal. 2019. Expressing visual relationships via language. arXiv preprint arXiv:1906.07689 (2019)."},{"key":"e_1_3_2_1_30_1","volume-title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images. arXiv preprint arXiv:2301.04883","author":"Tanaka Ryota","year":"2023","unstructured":"Ryota Tanaka, Kyosuke Nishida, Kosuke Nishida, Taku Hasegawa, Itsumi Saito, and Kuniko Saito. 2023. SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images. arXiv preprint arXiv:2301.04883 (2023)."},{"key":"e_1_3_2_1_31_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688995"},{"key":"e_1_3_2_1_33_1","volume-title":"Recipeqa: A challenge dataset for multimodal comprehension of cooking recipes. arXiv preprint arXiv:1809.00812","author":"Yagcioglu Semih","year":"2018","unstructured":"Semih Yagcioglu, Aykut Erdem, Erkut Erdem, and Nazli Ikizler-Cinbis. 2018. Recipeqa: A challenge dataset for multimodal comprehension of cooking recipes. arXiv preprint arXiv:1809.00812 (2018)."},{"key":"e_1_3_2_1_34_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi Chenliang Li Yuanhong Xu Hehong Chen Junfeng Tian Qian Qi Ji Zhang and Fei Huang. 2023. mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality. arxiv: 2304.14178 [cs.CL]"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688993","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3688993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688993"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":34,"alternative-id":["10.1145\/3664647.3688993","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3688993","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"}}]}}