{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:51:02Z","timestamp":1779306662900,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62176043, No.62072077"],"award-info":[{"award-number":["No.62176043, No.62072077"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intelligent Terminal Key Laboratory of Sichuan Province","award":["Grant SCITLAB-30002"],"award-info":[{"award-number":["Grant SCITLAB-30002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657929","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2579-2583","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Predicting Micro-video Popularity via Multi-modal Retrieval Augmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8163-3146","authenticated-orcid":false,"given":"Ting","family":"Zhong","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China & Kash Institute of Electronics and Information Industry, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0876-0497","authenticated-orcid":false,"given":"Jian","family":"Lang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2527-1059","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0097-3617","authenticated-orcid":false,"given":"Zhangtao","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1474-3169","authenticated-orcid":false,"given":"Kunpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, College Park, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8038-8150","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China & Intelligent Terminal Key Laboratory of Sichuan Province, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964314"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.108085"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Zhangtao Cheng Wenxue Ye Leyuan Liu Wenxin Tai and Fan Zhou. 2023. Enhancing Information Diffusion Prediction with Self-Supervised Disentangled User and Cascade Representations. In ACM International Conference on Information and Knowledge Management (CIKM). 3808--3812.","DOI":"10.1145\/3583780.3615230"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.140"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"e_1_3_2_1_6_1","volume-title":"Contextual lstm (clstm) models for large scale nlp tasks. arXiv preprint arXiv:1602.06291","author":"Ghosh Shalini","year":"2016","unstructured":"Shalini Ghosh, Oriol Vinyals, Brian Strope, Scott Roy, Tom Dean, and Larry Heck. 2016. Contextual lstm (clstm) models for large scale nlp tasks. arXiv preprint arXiv:1602.06291 (2016)."},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 3887--3896","author":"Guo Ruiqi","year":"2020","unstructured":"Ruiqi Guo, Philip Sun, Erik Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar. 2020. Accelerating large-scale inference with anisotropic vector quantization. In International Conference on Machine Learning (ICML). PMLR, 3887--3896."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463001"},{"key":"e_1_3_2_1_10_1","unstructured":"Douglas R Hofstadter. 1995. Fluid concepts and creative analogies: Computer models of the fundamental mechanisms of thought. Basic books."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47436-2_59"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. 2."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2567996"},{"key":"e_1_3_2_1_14_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416273"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063576.2063915"},{"key":"e_1_3_2_1_17_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems (NeuIPS) 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505523"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning (ICML). PMLR, 12888--12900."},{"key":"e_1_3_2_1_20_1","volume-title":"Angle-optimized text embeddings. arXiv preprint arXiv:2309.12871","author":"Li Xianming","year":"2023","unstructured":"Xianming Li and Jing Li. 2023. Angle-optimized text embeddings. arXiv preprint arXiv:2309.12871 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 6959--6969","author":"Long Alexander","unstructured":"Alexander Long, Wei Yin, Thalaiyasingam Ajanthan, Vu Nguyen, Pulak Purkait, Ravi Garg, Alan Blair, Chunhua Shen, and Anton van den Hengel. 2022. Retrieval augmented classification for long-tail visual recognition. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 6959--6969."},{"key":"e_1_3_2_1_22_1","volume-title":"A Content-Driven Micro-Video Recommendation Dataset at Scale. arXiv preprint arXiv:2309.15379","author":"Ni Yongxin","year":"2023","unstructured":"Yongxin Ni, Yu Cheng, Xiangyan Liu, Junchen Fu, Youhua Li, Xiangnan He, Yongfeng Zhang, and Fajie Yuan. 2023. A Content-Driven Micro-Video Recommendation Dataset at Scale. arXiv preprint arXiv:2309.15379 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0151"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2265079"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2635589"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.312"},{"key":"e_1_3_2_1_27_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems (NeuIPS) 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (NeuIPS) 30 (2017)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9970"},{"key":"e_1_3_2_1_30_1","volume-title":"Visual transformers: Token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677","author":"Wu Bichen","year":"2020","unstructured":"Bichen Wu, Chenfeng Xu, Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Zhicheng Yan, Masayoshi Tomizuka, Joseph Gonzalez, Kurt Keutzer, and Peter Vajda. 2020. Visual transformers: Token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)."},{"key":"e_1_3_2_1_31_1","volume-title":"International Joint Conference on Artificial Intelligence (IJCAI). 1388--1394","author":"Wu Lianwei","year":"2021","unstructured":"Lianwei Wu, Yuan Rao, Xiong Yang, Wanzhen Wang, and Ambreen Nazir. 2021. Evidence-aware hierarchical interactive attention networks for explainable claim verification. In International Joint Conference on Artificial Intelligence (IJCAI). 1388--1394."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120537"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3126475"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571662.3571664"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3269244"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3433000"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155349"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657929","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:21:59Z","timestamp":1755840119000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657929"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":37,"alternative-id":["10.1145\/3626772.3657929","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657929","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}