{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:19:44Z","timestamp":1791303584679,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP)","award":["No. 2021-0-01341, Artificial Intelligence Graduate School Program of Chung-Ang Univ."],"award-info":[{"award-number":["No. 2021-0-01341, Artificial Intelligence Graduate School Program of Chung-Ang Univ."]}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP)","award":["No. 2021-0-02067, Next Generation AI for Multi-purpose Video Search"],"award-info":[{"award-number":["No. 2021-0-02067, Next Generation AI for Multi-purpose Video Search"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591726","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"475-484","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["MEME: Multi-Encoder Multi-Expert Framework with Data Augmentation for Video Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8231-5763","authenticated-orcid":false,"given":"Seong-Min","family":"Kang","sequence":"first","affiliation":[{"name":"Chung-Ang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9110-7414","authenticated-orcid":false,"given":"Yoon-Sik","family":"Cho","sequence":"additional","affiliation":[{"name":"Chung-Ang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"8748","volume-title":"International Conference on Machine Learning","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. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, pages 8748--8763. PMLR, 2021."},{"key":"e_1_3_2_1_2_1","volume-title":"Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning. Neurocomput., 508(C):293--304, oct","author":"Luo Huaishao","year":"2022","unstructured":"Huaishao Luo, Lei Ji, Ming Zhong, Yang Chen, Wen Lei, Nan Duan, and Tianrui Li. Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning. Neurocomput., 508(C):293--304, oct 2022."},{"key":"e_1_3_2_1_3_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548010"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_3_2_1_11_1","volume-title":"Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097","author":"Fang Han","year":"2021","unstructured":"Han Fang, Pengfei Xiong, Luhui Xu, and Yu Chen. Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097, 2021."},{"key":"e_1_3_2_1_12_1","volume-title":"Mdmmt-2: Multidomain multimodal transformer for video retrieval, one more step towards generalization. arXiv preprint arXiv:2203.07086","author":"Kunitsyn Alexander","year":"2022","unstructured":"Alexander Kunitsyn, Maksim Kalashnikov, Maksim Dzabraev, and Andrei Ivaniuta. Mdmmt-2: Multidomain multimodal transformer for video retrieval, one more step towards generalization. arXiv preprint arXiv:2203.07086, 2022."},{"key":"e_1_3_2_1_13_1","volume-title":"Align, match and distill for video-text retrieval","author":"Gao Zijian","year":"2022","unstructured":"Zijian Gao, Jingyu Liu, Weiqi Sun, Sheng Chen, Dedan Chang, and Lili Zhao. Clip2tv: Align, match and distill for video-text retrieval, 2022."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"e_1_3_2_1_15_1","volume-title":"Disentangled representation learning for text-video retrieval. arXiv preprint arXiv:2203.07111","author":"Wang Qiang","year":"2022","unstructured":"Qiang Wang, Yanhao Zhang, Yun Zheng, Pan Pan, and Xian-Sheng Hua. Disentangled representation learning for text-video retrieval. arXiv preprint arXiv:2203.07111, 2022."},{"key":"e_1_3_2_1_16_1","volume-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng Xing","year":"2021","unstructured":"Xing Cheng, Hezheng Lin, Xiangyu Wu, Fan Yang, and Dong Shen. Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss, 2021."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_2_1_24_1","volume-title":"Clover: Towards a unified video-language alignment and fusion model. arXiv preprint arXiv:2207.07885","author":"Huang Jingjia","year":"2022","unstructured":"Jingjia Huang, Yinan Li, Jiashi Feng, Xiaoshuai Sun, and Rongrong Ji. Clover: Towards a unified video-language alignment and fusion model. arXiv preprint arXiv:2207.07885, 2022."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"e_1_3_2_1_26_1","volume-title":"Long-form video-language pre-training with multimodal temporal contrastive learning. arXiv preprint arXiv:2210.06031","author":"Sun Yuchong","year":"2022","unstructured":"Yuchong Sun, Hongwei Xue, Ruihua Song, Bei Liu, Huan Yang, and Jianlong Fu. Long-form video-language pre-training with multimodal temporal contrastive learning. arXiv preprint arXiv:2210.06031, 2022."},{"key":"e_1_3_2_1_27_1","volume-title":"Lijuan Wang, and Zicheng Liu. Violet: End-to-end video-language transformers with masked visual-token modeling. arXiv preprint arXiv:2111.12681","author":"Fu Tsu-Jui","year":"2021","unstructured":"Tsu-Jui Fu, Linjie Li, Zhe Gan, Kevin Lin, William Yang Wang, Lijuan Wang, and Zicheng Liu. Violet: End-to-end video-language transformers with masked visual-token modeling. arXiv preprint arXiv:2111.12681, 2021."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"e_1_3_2_1_30_1","volume-title":"Learning by abstraction: The neural state machine","author":"Hudson Drew A.","year":"2019","unstructured":"Drew A. Hudson and Christopher D. Manning. Learning by abstraction: The neural state machine, 2019."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Learning Representations","author":"Yao Lewei","year":"2022","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. FILIP: Fine-grained interactive language-image pre-training. In International Conference on Learning Representations, 2022."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00079"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"e_1_3_2_1_37_1","volume-title":"Multimodal self-supervised learning of general audio representations. arXiv preprint arXiv:2104.12807","author":"Wang Luyu","year":"2021","unstructured":"Luyu Wang, Pauline Luc, Adria Recasens, Jean-Baptiste Alayrac, and Aaron van den Oord. Multimodal self-supervised learning of general audio representations. arXiv preprint arXiv:2104.12807, 2021."},{"key":"e_1_3_2_1_38_1","first-page":"24206","article-title":"Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"Akbari Hassan","year":"2021","unstructured":"Hassan Akbari, Liangzhe Yuan, Rui Qian, Wei-Hong Chuang, Shih-Fu Chang, Yin Cui, and Boqing Gong. Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text. Advances in Neural Information Processing Systems, 34:24206--24221, 2021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","volume-title":"June","author":"Bogolin Simion-Vlad","year":"2022","unstructured":"Simion-Vlad Bogolin, Ioana Croitoru, Hailin Jin, Yang Liu, and Samuel Albanie. Cross modal retrieval with querybank normalisation, June 2022."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591726","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:00Z","timestamp":1750178820000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591726"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":42,"alternative-id":["10.1145\/3539618.3591726","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591726","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}