{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:33:20Z","timestamp":1776886400057,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,8]]},"DOI":"10.1145\/3640457.3688098","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T15:39:28Z","timestamp":1728401968000},"page":"391-400","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["A Multi-modal Modeling Framework for Cold-start Short-video Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0619-1464","authenticated-orcid":false,"given":"Gaode","family":"Chen","sequence":"first","affiliation":[{"name":"Kuaishou Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6525-9754","authenticated-orcid":false,"given":"Ruina","family":"Sun","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5293-6885","authenticated-orcid":false,"given":"Yuezihan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2681-0119","authenticated-orcid":false,"given":"Jiangxia","family":"Cao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8971-503X","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1043-3593","authenticated-orcid":false,"given":"Jingjian","family":"Lin","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9801-9292","authenticated-orcid":false,"given":"Han","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3636-3618","authenticated-orcid":false,"given":"Kun","family":"Gai","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6954-5605","authenticated-orcid":false,"given":"Xinghua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557120"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25531"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/197"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080797"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403113"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2945180"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. 249\u2013256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. 249\u2013256."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Shawn Hershey Sourish Chaudhuri Daniel\u00a0PW Ellis Jort\u00a0F Gemmeke Aren Jansen R\u00a0Channing Moore Manoj Plakal Devin Platt Rif\u00a0A Saurous Bryan Seybold 2017. CNN architectures for large-scale audio classification. In 2017 ieee international conference on acoustics speech and signal processing (icassp). 131\u2013135.","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_1_13_1","volume-title":"A fast learning algorithm for deep belief nets. Neural computation 18, 7","author":"Hinton E","year":"2006","unstructured":"Geoffrey\u00a0E Hinton, Simon Osindero, and Yee-Whye Teh. 2006. A fast learning algorithm for deep belief nets. Neural computation 18, 7 (2006), 1527\u20131554."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of NAACL-HLT. 4171\u20134186","author":"Ming-Wei\u00a0Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171\u20134186."},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_18_1","volume-title":"The global k-means clustering algorithm. Pattern recognition 36, 2","author":"Likas Aristidis","year":"2003","unstructured":"Aristidis Likas, Nikos Vlassis, and Jakob\u00a0J Verbeek. 2003. The global k-means clustering algorithm. Pattern recognition 36, 2 (2003), 451\u2013461."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350953"},{"key":"e_1_3_2_1_20_1","volume-title":"Multi-modal Graph Attention Network for Video Recommendation. In 2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET). 94\u201399","author":"Liu Huizhi","year":"2022","unstructured":"Huizhi Liu, Chen Li, and Lihua Tian. 2022. Multi-modal Graph Attention Network for Video Recommendation. In 2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET). 94\u201399."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080658"},{"key":"e_1_3_2_1_22_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892382"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. 452\u2013461","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. 452\u2013461."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645751"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481941"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411947"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102277"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5120\/19308-0760"},{"key":"e_1_3_2_1_31_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008)."},{"key":"e_1_3_2_1_32_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\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583206"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548455"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"e_1_3_2_1_38_1","volume-title":"Deep learning based recommender system: A survey and new perspectives. ACM computing surveys (CSUR) 52, 1","author":"Zhang Shuai","year":"2019","unstructured":"Shuai Zhang, Lina Yao, Aixin Sun, and Yi Tay. 2019. Deep learning based recommender system: A survey and new perspectives. ACM computing surveys (CSUR) 52, 1 (2019), 1\u201338."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583286"}],"event":{"name":"RecSys '24: 18th ACM Conference on Recommender Systems","location":"Bari Italy","acronym":"RecSys '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["18th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688098","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640457.3688098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:29Z","timestamp":1750294709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688098"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":39,"alternative-id":["10.1145\/3640457.3688098","10.1145\/3640457"],"URL":"https:\/\/doi.org\/10.1145\/3640457.3688098","relation":{},"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}