{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T06:56:50Z","timestamp":1781247410806,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3763761","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"14079-14085","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MVP: Winning Solution to SMP Challenge 2025 Video Track"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5076-2404","authenticated-orcid":false,"given":"Liliang","family":"Ye","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3412-9262","authenticated-orcid":false,"given":"Yunyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9019-3047","authenticated-orcid":false,"given":"Yafeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4122-3767","authenticated-orcid":false,"given":"Yi-Ping Phoebe","family":"Chen","sequence":"additional","affiliation":[{"name":"La Trobe University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7057-0402","authenticated-orcid":false,"given":"Junqing","family":"Yu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1189-1254","authenticated-orcid":false,"given":"Wei","family":"Yang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6651-2027","authenticated-orcid":false,"given":"Zikai","family":"Song","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Principal component analysis","author":"Abdi Herv\u00e9","year":"2010","unstructured":"Herv\u00e9 Abdi and Lynne J Williams. 2010. Principal component analysis. Wiley interdisciplinary reviews: computational statistics, Vol. 2, 4 (2010), 433-459."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.15691"},{"key":"e_1_3_2_1_3_1","volume-title":"Multimodal machine learning: A survey and taxonomy","author":"Baltru\u0161aitis Tadas","year":"2018","unstructured":"Tadas Baltru\u0161aitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multimodal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 2 (2018), 423-443."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Gedas Bertasius Heng Wang and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding ? arXiv:2102.05095 [cs] doi:10.48550\/arXiv.2102.05095","DOI":"10.48550\/arXiv.2102.05095"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672041"},{"key":"e_1_3_2_1_7_1","unstructured":"Cisco. 2020. Cisco Annual Internet Report - Cisco Annual Internet Report (2018-2023) White Paper. https:\/\/www.cisco.com\/c\/en\/us\/solutions\/collateral\/executive-perspectives\/annual-internet-report\/white-paper-c11-741490.html."},{"key":"e_1_3_2_1_8_1","volume-title":"CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363","author":"Dorogush Anna Veronika","year":"2018","unstructured":"Anna Veronika Dorogush, Vasily Ershov, and Andrey Gulin. 2018. CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688998"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02710"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416273"},{"key":"e_1_3_2_1_12_1","volume-title":"Coupled mamba: Enhanced multi-modal fusion with coupled state space model. arXiv preprint arXiv:2405.18014","author":"Li Wenbing","year":"2024","unstructured":"Wenbing Li, Hang Zhou, Junqing Yu, Zikai Song, and Wei Yang. 2024. Coupled mamba: Enhanced multi-modal fusion with coupled state space model. arXiv preprint arXiv:2405.18014 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Haixu Liu Wenning Wang Haoxiang Zheng Penghao Jiang Qirui Wang Ruiqing Yan and Qiuzhuang Sun. 2025. Multi-Modal Video Feature Extraction for Popularity Prediction. arXiv:2501.01422 [cs] doi:10.48550\/arXiv.2501.01422","DOI":"10.48550\/arXiv.2501.01422"},{"key":"e_1_3_2_1_14_1","volume-title":"Use what you have: Video retrieval using representations from collaborative experts. arXiv preprint arXiv:1907.13487","author":"Liu Yang","year":"2019","unstructured":"Yang Liu, Samuel Albanie, Arsha Nagrani, and Andrew Zisserman. 2019. Use what you have: Video retrieval using representations from collaborative experts. arXiv preprint arXiv:1907.13487 (2019)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28192"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Yiwei Ma Guohai Xu Xiaoshuai Sun Ming Yan Ji Zhang and Rongrong Ji. 2022. X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval. arXiv:2207.07285 [cs] doi:10.48550\/arXiv.2207.07285","DOI":"10.48550\/arXiv.2207.07285"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612839"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1807.05959"},{"key":"e_1_3_2_1_19_1","volume-title":"Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516","author":"Miech Antoine","year":"2018","unstructured":"Antoine Miech, Ivan Laptev, and Josef Sivic. 2018. Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516 (2018)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.05615"},{"key":"e_1_3_2_1_21_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."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32749"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25327"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681104"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463629"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_1_28_1","unstructured":"Zhan Tong Yibing Song Jue Wang and Limin Wang. 2022. VideoMAE: Masked Autoencoders Are Data-Efficient Learners for Self-Supervised Video Pre-Training. https:\/\/arxiv.org\/abs\/2203.12602v3."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688999"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3614419.3644023"},{"key":"e_1_3_2_1_31_1","first-page":"8483","article-title":"Language models with image descriptors are strong few-shot video-language learners","volume":"35","author":"Wang Zhenhailong","year":"2022","unstructured":"Zhenhailong Wang, Manling Li, Ruochen Xu, Luowei Zhou, Jie Lei, Xudong Lin, Shuohang Wang, Ziyi Yang, Chenguang Zhu, Derek Hoiem, et al., 2022. Language models with image descriptors are strong few-shot video-language learners. Advances in Neural Information Processing Systems, Vol. 35 (2022), 8483-8497.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356084"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613853"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688996"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9970"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416274"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33169"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Yaochen Zhu Jiayi Xie and Zhenzhong Chen. 2020. Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework. https:\/\/arxiv.org\/abs\/2003.12724v1. doi:10.1109\/TMM.2021.3120537","DOI":"10.1109\/TMM.2021.3120537"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3763761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:44:02Z","timestamp":1765309442000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3763761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":38,"alternative-id":["10.1145\/3746027.3763761","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3763761","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"}}]}}