{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:11:29Z","timestamp":1765357889540,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758264","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"13119-13125","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["OpenEvents V1: Large-Scale Benchmark Dataset for Multimodal Event Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7726-5301","authenticated-orcid":false,"given":"Hieu","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0720-4038","authenticated-orcid":false,"given":"Phuc-Tan","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0800-6884","authenticated-orcid":false,"given":"Thien-Phuc","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3520-4624","authenticated-orcid":false,"given":"Minh-Quang","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0236-7992","authenticated-orcid":false,"given":"Tam V.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Dayton, Dayton, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7363-2610","authenticated-orcid":false,"given":"Trung-Nghia","family":"Le","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM, Ho Chi Minh, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"e_1_3_2_1_2_1","volume-title":"Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, et al.","author":"Deitke Matt","year":"2024","unstructured":"Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, et al., 2024. Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models. CoRR (2024)."},{"key":"e_1_3_2_1_3_1","first-page":"27092","article-title":"Datacomp: In search of the next generation of multimodal datasets","volume":"36","author":"Gadre Samir Yitzhak","year":"2023","unstructured":"Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, et al., 2023. Datacomp: In search of the next generation of multimodal datasets. Advances in Neural Information Processing Systems, Vol. 36 (2023), 27092-27112.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. CLIPScore: A Reference-free Evaluation Metric for Image Captioning. In EMNLP (1)."},{"unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Keming Lu et al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186 (2024).","key":"e_1_3_2_1_5_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.3115\/1626355.1626389"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1007\/978-3-030-01225-0_13"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1109\/TMM.2019.2896494"},{"key":"e_1_3_2_1_9_1","volume-title":"Anton Lozhkov, Nouamane Tazi, et al.","author":"Marafioti Andr\u00e9s","year":"2025","unstructured":"Andr\u00e9s Marafioti, Orr Zohar, Miquel Farr\u00e9, Merve Noyan, Elie Bakouch, Pedro Cuenca, Cyril Zakka, Loubna Ben Allal, Anton Lozhkov, Nouamane Tazi, et al., 2025. Smolvlm: Redefining small and efficient multimodal models. arXiv preprint arXiv:2504.05299 (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"VisChronos: Revolutionizing Image Captioning Through Real-Life Events. In International Symposium on Information and Communication Technology. Springer, 127-140","author":"Nguyen Phuc-Tan","year":"2024","unstructured":"Phuc-Tan Nguyen, Hieu Nguyen, and Trung-Nghia Le. 2024. VisChronos: Revolutionizing Image Captioning Through Real-Life Events. In International Symposium on Information and Communication Technology. Springer, 127-140."},{"key":"e_1_3_2_1_11_1","volume-title":"Common-pool resources and institutions: Toward a revised theory. Handbook of agricultural economics","author":"Ostrom Elinor","year":"2002","unstructured":"Elinor Ostrom. 2002. Common-pool resources and institutions: Toward a revised theory. Handbook of agricultural economics, Vol. 2 (2002), 1315-1339."},{"key":"e_1_3_2_1_12_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_13_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."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.18653\/v1\/D19-1410"},{"unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information processing systems Vol. 35 (2022) 25278-25294.","key":"e_1_3_2_1_15_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1145\/3404835.3463257"},{"unstructured":"Gemma Team Aishwarya Kamath Johan Ferret Shreya Pathak Nino Vieillard Ramona Merhej Sarah Perrin Tatiana Matejovicova Alexandre Ram\u00e9 Morgane Rivi\u00e8re et al. 2025. Gemma 3 technical report. arXiv preprint arXiv:2503.19786 (2025).","key":"e_1_3_2_1_17_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1145\/2812802"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1145\/3746027.3762067"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1109\/CVPR.2015.7299087"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.3390\/plants13091176"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1145\/3581783.3611830"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:00:08Z","timestamp":1765342808000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758264"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":22,"alternative-id":["10.1145\/3746027.3758264","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758264","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"}}]}}