{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:31:23Z","timestamp":1765506683960,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","funder":[{"name":"the National Natural Science Foundation of China","award":["62476165,62173252"],"award-info":[{"award-number":["62476165,62173252"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3760794","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:52:37Z","timestamp":1762563157000},"page":"5026-5030","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Intra-Modal Consistency for Cross-Modal Alignment and Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2486-6455","authenticated-orcid":false,"given":"Fengyang","family":"Mao","sequence":"first","affiliation":[{"name":"Sino-European School of Technology, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0536-1345","authenticated-orcid":false,"given":"Xiaodong","family":"Yue","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Institute, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3645-9046","authenticated-orcid":false,"given":"Yufei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4991-9796","authenticated-orcid":false,"given":"Jiaqing","family":"Ma","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Institute, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2590-4737","authenticated-orcid":false,"given":"Zheran","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sino-European School of Technology, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4369-8400","authenticated-orcid":false,"given":"Jie","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Adam: A method for stochastic optimization. ICLR","author":"Diederik P Kingma","year":"2015","unstructured":"P Kingma Diederik. 2015. Adam: A method for stochastic optimization. ICLR (2015)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3227416"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3393843"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27955"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/104"},{"key":"e_1_3_2_1_8_1","volume-title":"Hero: Hierarchical encoder for video language omni-representation pre-training. arXiv preprint arXiv:2005.00200","author":"Li Linjie","year":"2020","unstructured":"Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan, Licheng Yu, and Jingjing Liu. 2020. Hero: Hierarchical encoder for video language omni-representation pre-training. arXiv preprint arXiv:2005.00200 (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635757"},{"key":"e_1_3_2_1_10_1","first-page":"38655","article-title":"Text-adaptive multiple visual prototype matching for video-text retrieval","volume":"35","author":"Lin Chengzhi","year":"2022","unstructured":"Chengzhi Lin, Ancong Wu, Junwei Liang, Jun Zhang, Wenhang Ge, Wei-Shi Zheng, and Chunhua Shen. 2022. Text-adaptive multiple visual prototype matching for video-text retrieval. Advances in Neural Information Processing Systems, Vol. 35 (2022), 38655-38666.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"e_1_3_2_1_12_1","volume-title":"Use what you have: Video retrieval using representations from collaborative experts. BMVC","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. BMVC (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"SGDR: Stochastic Gradient Descent with Warm Restarts. In ICLR.","author":"Loshchilov Ilya","year":"2022","unstructured":"Ilya Loshchilov and Frank Hutter. 2022. SGDR: Stochastic Gradient Descent with Warm Restarts. In ICLR."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. 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. 8748-8763."},{"key":"e_1_3_2_1_16_1","volume-title":"Disentangled representation learning for text-video retrieval. arXiv:2203.07111","author":"Wang Qiang","year":"2022","unstructured":"Qiang Wang, Yanhao Zhang, Yun Zheng, Pan Pan, and Xian-Sheng Hua. 2022. Disentangled representation learning for text-video retrieval. arXiv:2203.07111 (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"e_1_3_2_1_18_1","volume-title":"Videoclip: Contrastive pre-training for zero-shot video-text understanding. EMNLP","author":"Xu Hu","year":"2021","unstructured":"Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, and Christoph Feichtenhofer. 2021. Videoclip: Contrastive pre-training for zero-shot video-text understanding. EMNLP (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_20_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=GNjzMAgawq","author":"Xue Hongwei","year":"2023","unstructured":"Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, and Jiebo Luo. 2023. CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=GNjzMAgawq"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592064"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"e_1_3_2_1_25_1","first-page":"3","article-title":"Deep learning for video-text retrieval: a review","volume":"12","author":"Zhu Cunjuan","year":"2023","unstructured":"Cunjuan Zhu, Qi Jia, Wei Chen, Yanming Guo, and Yu Liu. 2023. Deep learning for video-text retrieval: a review. INT J MULTIMED INF R, Vol. 12, 1 (2023), 3.","journal-title":"INT J MULTIMED INF R"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3760794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:26:32Z","timestamp":1765506392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3760794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":26,"alternative-id":["10.1145\/3746252.3760794","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3760794","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}