{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:59:51Z","timestamp":1765339191752,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","funder":[{"name":"Natural Science Foundation of China","award":["62276242"],"award-info":[{"award-number":["62276242"]}]},{"name":"National Aviation Science Foundation","award":["2022Z071078001"],"award-info":[{"award-number":["2022Z071078001"]}]},{"name":"Hefei Municipal Natural Science Foundation","award":["HZR2431"],"award-info":[{"award-number":["HZR2431"]}]},{"name":"Dreams Foundation of Jianghuai Advance Technology Center","award":["2023-ZM01Z001"],"award-info":[{"award-number":["2023-ZM01Z001"]}]},{"name":"CAAI-MindSpore Open Fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3762060","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"13830-13836","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CMA-VC: Large Vision-Language Model for Cross-Modal Alignment in Intention-Oriented Video Captioning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4655-6517","authenticated-orcid":false,"given":"Xilong","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1980-7859","authenticated-orcid":false,"given":"Yunxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5688-4130","authenticated-orcid":false,"given":"Qiang","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_5_1","volume-title":"Generative adversarial networks: An overview","author":"Creswell Antonia","year":"2018","unstructured":"Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, and Anil A Bharath. 2018. Generative adversarial networks: An overview. IEEE signal processing magazine 35, 1 (2018), 53--65."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"volume-title":"Deep learning","author":"Goodfellow Ian","key":"e_1_3_2_1_8_1","unstructured":"Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep learning. Vol. 1. MIT press Cambridge."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-00998-5"},{"key":"e_1_3_2_1_10_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3762057"},{"key":"e_1_3_2_1_14_1","volume-title":"Deep learning. nature 521, 7553","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_15_1","volume-title":"Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122","author":"Lin Bin","year":"2023","unstructured":"Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, and Li Yuan. 2023. Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)."},{"key":"e_1_3_2_1_16_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_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103453"},{"key":"e_1_3_2_1_18_1","first-page":"689","article-title":"Multimodal deep learning","volume":"11","author":"Ngiam Jiquan","year":"2011","unstructured":"Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, Andrew Y Ng, et al. 2011. Multimodal deep learning.. In ICML, Vol. 11. 689--696.","journal-title":"ICML"},{"key":"e_1_3_2_1_19_1","volume-title":"The alignment template approach to statistical machine translation. Computational linguistics 30, 4","author":"Och Franz Josef","year":"2004","unstructured":"Franz Josef Och and Hermann Ney. 2004. The alignment template approach to statistical machine translation. Computational linguistics 30, 4 (2004), 417--449."},{"key":"e_1_3_2_1_20_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_21_1","volume-title":"Multi-task video captioning with video and entailment generation. arXiv preprint arXiv:1704.07489","author":"Pasunuru Ramakanth","year":"2017","unstructured":"Ramakanth Pasunuru and Mohit Bansal. 2017. Multi-task video captioning with video and entailment generation. arXiv preprint arXiv:1704.07489 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_25_1","volume-title":"Translating videos to natural language using deep recurrent neural networks. arXiv preprint arXiv:1412.4729","author":"Venugopalan Subhashini","year":"2014","unstructured":"Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, and Kate Saenko. 2014. Translating videos to natural language using deep recurrent neural networks. arXiv preprint arXiv:1412.4729 (2014)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"e_1_3_2_1_27_1","volume-title":"Internvideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191","author":"Li Kunchang","year":"2022","unstructured":"YiWang, Kunchang Li, Yizhuo Li, Yinan He, Bingkun Huang, Zhiyu Zhao, Hongjie Zhang, Jilan Xu, Yi Liu, Zun Wang, et al. 2022. Internvideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)."},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning. PMLR, 2048--2057."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413610"},{"key":"e_1_3_2_1_30_1","volume-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421","author":"Yang Zhengyuan","year":"2023","unstructured":"Zhengyuan Yang, Linjie Li, Kevin Lin, JianfengWang, Chung-Ching Lin, Zicheng Liu, and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421 (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\/3746027.3762060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:56:29Z","timestamp":1765338989000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3762060"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":30,"alternative-id":["10.1145\/3746027.3762060","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3762060","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"}}]}}