{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:32:18Z","timestamp":1784737938663,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761655","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T01:03:27Z","timestamp":1762563807000},"page":"6486-6491","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["A Content-Driven Micro-Video Recommendation Dataset at Scale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7606-1475","authenticated-orcid":false,"given":"Yongxin","family":"Ni","sequence":"first","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7610-1695","authenticated-orcid":false,"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7804-6945","authenticated-orcid":false,"given":"Xiangyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-2042","authenticated-orcid":false,"given":"Junchen","family":"Fu","sequence":"additional","affiliation":[{"name":"Westlake University, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1290-3604","authenticated-orcid":false,"given":"Youhua","family":"Li","sequence":"additional","affiliation":[{"name":"Westlake University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-7992","authenticated-orcid":false,"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2633-8555","authenticated-orcid":false,"given":"Yongfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8452-9929","authenticated-orcid":false,"given":"Fajie","family":"Yuan","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_2_1","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML, Vol. 2. 4.","journal-title":"ICML"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330652"},{"key":"e_1_3_2_1_5_1","volume-title":"An Image Dataset for Benchmarking Recommender Systems with Raw Pixels. arXiv preprint arXiv:2309.06789","author":"Cheng Yu","year":"2023","unstructured":"Yu Cheng, Yunzhu Pan, Jiaqi Zhang, Yongxin Ni, Aixin Sun, and Fajie Yuan. 2023. An Image Dataset for Benchmarking Recommender Systems with Raw Pixels. arXiv preprint arXiv:2309.06789 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533143"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100618"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478329"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557065"},{"key":"e_1_3_2_1_16_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2631881"},{"key":"e_1_3_2_1_18_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis)","author":"Maxwell Harper F","year":"2015","unstructured":"F Maxwell Harper and Joseph A Konstan. 2015. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), Vol. 5, 4 (2015), 1-19."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959152"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080777"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_1_25_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413653"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_29_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.121"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467189"},{"key":"e_1_3_2_1_32_1","volume-title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation. arXiv preprint arXiv:2305.13731","author":"Li Jiacheng","year":"2023","unstructured":"Jiacheng Li, Ming Wang, Jin Li, Jinmiao Fu, Xin Shen, Jingbo Shang, and Julian McAuley. 2023. Text Is All You Need: Learning Language Representations for Sequential Recommendation. arXiv preprint arXiv:2305.13731 (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313513"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482417"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2008.33"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531744"},{"key":"e_1_3_2_1_38_1","volume-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv preprint arXiv:2203.12602","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. 2022. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv preprint arXiv:2203.12602 (2022)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_41_1","volume-title":"Deep content-based music recommendation. Advances in neural information processing systems","author":"den Oord Aaron Van","year":"2013","unstructured":"Aaron Van den Oord, Sander Dieleman, and Benjamin Schrauwen. 2013. Deep content-based music recommendation. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557464"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462890"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.331"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2913394"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539120"},{"key":"e_1_3_2_1_50_1","volume-title":"Personalized Showcases: Generating Multi-Modal Explanations for Recommendations. arXiv preprint arXiv:2207.00422","author":"Yan An","year":"2022","unstructured":"An Yan, Zhankui He, Jiacheng Li, Tianyang Zhang, and Julian McAuley. 2022. Personalized Showcases: Generating Multi-Modal Explanations for Recommendations. arXiv preprint arXiv:2207.00422 (2022)."},{"key":"e_1_3_2_1_51_1","volume-title":"Minsam Kim, and Juneyoung Park.","author":"Yang Yoonseok","year":"2022","unstructured":"Yoonseok Yang, Kyu Seok Kim, Minsam Kim, and Juneyoung Park. 2022. GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering. arXiv preprint arXiv:2204.04179 (2022)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346996"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26387-3_31"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_55_1","volume-title":"Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems. arXiv preprint arXiv:2210.10629","author":"Yuan Guanghu","year":"2022","unstructured":"Guanghu Yuan, Fajie Yuan, Yudong Li, Beibei Kong, Shujie Li, Lei Chen, Min Yang, Chenyun Yu, Bo Hu, Zang Li, et al., 2022. Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems. arXiv preprint arXiv:2210.10629 (2022)."},{"key":"e_1_3_2_1_56_1","volume-title":"Where to go next for recommender systems? id-vs. modality-based recommender models revisited. SIGIR","author":"Yuan Zheng","year":"2023","unstructured":"Zheng Yuan, Fajie Yuan, Yu Song, Youhua Li, Junchen Fu, Fei Yang, Yunzhu Pan, and Yongxin Ni. 2023. Where to go next for recommender systems? id-vs. modality-based recommender models revisited. SIGIR (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00314"},{"key":"e_1_3_2_1_58_1","volume-title":"Ninerec: A benchmark dataset suite for evaluating transferable recommendation","author":"Zhang Jiaqi","year":"2024","unstructured":"Jiaqi Zhang, Yu Cheng, Yongxin Ni, Yunzhu Pan, Zheng Yuan, Junchen Fu, Youhua Li, Jie Wang, and Fajie Yuan. 2024. Ninerec: A benchmark dataset suite for evaluating transferable recommendation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548428"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411954"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219826"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"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\/3746252.3761655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:46:04Z","timestamp":1765507564000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":62,"alternative-id":["10.1145\/3746252.3761655","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761655","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"}}]}}