{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:25:05Z","timestamp":1774124705714,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T00:00:00Z","timestamp":1656288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the State Key Laboratory of Software Development Environment of China","award":["No. SKLSDE-2022ZX-14"],"award-info":[{"award-number":["No. SKLSDE-2022ZX-14"]}]},{"name":"the National Natural Science Foundation of China","award":["No.61977002"],"award-info":[{"award-number":["No.61977002"]}]},{"name":"the German Federal Ministry of Education and Research (BMBF)","award":["No. 01IS18036A"],"award-info":[{"award-number":["No. 01IS18036A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,27]]},"DOI":"10.1145\/3512527.3531378","type":"proceedings-article","created":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T22:23:32Z","timestamp":1656023012000},"page":"99-108","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":27,"title":["Multi-Modal Contrastive Pre-training for Recommendation"],"prefix":"10.1145","author":[{"given":"Zhuang","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpu","family":"Ma","sequence":"additional","affiliation":[{"name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen Lehrstuhl f\u00fcr Datenbanksysteme und Data Mining, M\u00fcnchen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Schubert","sequence":"additional","affiliation":[{"name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen Lehrstuhl f\u00fcr Datenbanksysteme und Data Mining, M\u00fcnchen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanxin","family":"Ouyang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Advanced Computer Application Technology, Ministry of Education, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Multi-modal machine learning: A survey and taxonomy","author":"Baltruaitis Tadas","year":"2018","unstructured":"Tadas Baltruaitis , Chaitanya Ahuja , and Louis-Philippe Morency . 2018. Multi-modal machine learning: A survey and taxonomy . IEEE transactions on pattern analysis and machine intelligence 41, 2 ( 2018 ), 423--443. Tadas Baltruaitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multi-modal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence 41, 2 (2018), 423--443."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939812"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3291060"},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249--256","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. JMLR Workshop and Conference Proceedings, 249--256 . 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. JMLR Workshop and Conference Proceedings, 249--256."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Tinglin Huang Yuxiao Dong Ming Ding Zhen Yang Wenzheng Feng Xinyu Wang and Jie Tang. 2021. MixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems. (2021).  Tinglin Huang Yuxiao Dong Ming Ding Zhen Yang Wenzheng Feng Xinyu Wang and Jie Tang. 2021. MixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems. (2021).","DOI":"10.1145\/3447548.3467408"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"e_1_3_2_2_11_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). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475709"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3075052"},{"key":"e_1_3_2_2_14_1","volume-title":"Graph neural pre-training for enhancing recommendations using side information. arXiv preprint arXiv:2107.03936","author":"Meng Zaiqiao","year":"2021","unstructured":"Zaiqiao Meng , Siwei Liu , Craig Macdonald , and Iadh Ounis . 2021. Graph neural pre-training for enhancing recommendations using side information. arXiv preprint arXiv:2107.03936 ( 2021 ). Zaiqiao Meng, Siwei Liu, Craig Macdonald, and Iadh Ounis. 2021. Graph neural pre-training for enhancing recommendations using side information. arXiv preprint arXiv:2107.03936 (2021)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02300-2"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"e_1_3_2_2_17_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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. arXiv preprint arXiv:2103.00020 (2021). 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. arXiv preprint arXiv:2103.00020 (2021)."},{"key":"e_1_3_2_2_18_1","volume-title":"et al","author":"Radford Alec","year":"2019","unstructured":"Alec Radford , Jeffrey Wu , Rewon Child , David Luan , Dario Amodei , Ilya Sutskever , et al . 2019 . Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al . 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959172"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2697059"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.elerap.2019.100879"},{"key":"e_1_3_2_2_22_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_23_1","volume-title":"Order-embeddings of images and language. arXiv preprint arXiv:1511.06361","author":"Vendrov Ivan","year":"2015","unstructured":"Ivan Vendrov , Ryan Kiros , Sanja Fidler , and Raquel Urtasun . 2015. Order-embeddings of images and language. arXiv preprint arXiv:1511.06361 ( 2015 ). Ivan Vendrov, Ryan Kiros, Sanja Fidler, and Raquel Urtasun. 2015. Order-embeddings of images and language. arXiv preprint arXiv:1511.06361 (2015)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271786"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240535"},{"key":"e_1_3_2_2_26_1","volume-title":"International conference on machine learning. PMLR, 1083--1092","author":"Wang Weiran","year":"2015","unstructured":"Weiran Wang , Raman Arora , Karen Livescu , and Jeff Bilmes . 2015 . On deep multi-view representation learning . In International conference on machine learning. PMLR, 1083--1092 . Weiran Wang, Raman Arora, Karen Livescu, and Jeff Bilmes. 2015. On deep multi-view representation learning. In International conference on machine learning. PMLR, 1083--1092."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"e_1_3_2_2_31_1","volume-title":"Graph-bert: Only attention is needed for learning graph representations. arXiv preprint arXiv:2001.05140","author":"Zhang Jiawei","year":"2020","unstructured":"Jiawei Zhang , Haopeng Zhang , Congying Xia , and Li Sun . 2020 . Graph-bert: Only attention is needed for learning graph representations. arXiv preprint arXiv:2001.05140 (2020). Jiawei Zhang, Haopeng Zhang, Congying Xia, and Li Sun. 2020. Graph-bert: Only attention is needed for learning graph representations. arXiv preprint arXiv:2001.05140 (2020)."},{"key":"e_1_3_2_2_32_1","volume-title":"Latent Structures Mining with Contrastive Modality Fusion for Multimedia Recommendation. arXiv preprint arXiv:2111.00678","author":"Zhang Jinghao","year":"2021","unstructured":"Jinghao Zhang , Yanqiao Zhu , Qiang Liu , Mengqi Zhang , Shu Wu , and Liang Wang . 2021. Latent Structures Mining with Contrastive Modality Fusion for Multimedia Recommendation. arXiv preprint arXiv:2111.00678 ( 2021 ). Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Mengqi Zhang, Shu Wu, and Liang Wang. 2021. Latent Structures Mining with Contrastive Modality Fusion for Multimedia Recommendation. arXiv preprint arXiv:2111.00678 (2021)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313598"}],"event":{"name":"ICMR '22: International Conference on Multimedia Retrieval","location":"Newark NJ USA","acronym":"ICMR '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2022 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3512527.3531378","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3512527.3531378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:12Z","timestamp":1750188612000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3512527.3531378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,27]]},"references-count":33,"alternative-id":["10.1145\/3512527.3531378","10.1145\/3512527"],"URL":"https:\/\/doi.org\/10.1145\/3512527.3531378","relation":{},"subject":[],"published":{"date-parts":[[2022,6,27]]},"assertion":[{"value":"2022-06-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}