{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:55:47Z","timestamp":1772301347448,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3731945","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T14:55:26Z","timestamp":1752504926000},"page":"4264-4268","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Embedding-based Retrieval in Multi-Modal Content Moderation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7101-5292","authenticated-orcid":false,"given":"Hanzhong","family":"Liang","sequence":"first","affiliation":[{"name":"TikTok, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0196-5111","authenticated-orcid":false,"given":"Jinghao","family":"Shi","sequence":"additional","affiliation":[{"name":"TikTok, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6457-0411","authenticated-orcid":false,"given":"Xiang","family":"Shen","sequence":"additional","affiliation":[{"name":"TikTok, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5532-5932","authenticated-orcid":false,"given":"Zixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"TikTok, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7328-409X","authenticated-orcid":false,"given":"Vera","family":"Wen","sequence":"additional","affiliation":[{"name":"TikTok, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1369-7639","authenticated-orcid":false,"given":"Ardalan","family":"Mehrani","sequence":"additional","affiliation":[{"name":"TikTok, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7445-4108","authenticated-orcid":false,"given":"Zhiqian","family":"Chen","sequence":"additional","affiliation":[{"name":"TikTok, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2798-8860","authenticated-orcid":false,"given":"Yifan","family":"Wu","sequence":"additional","affiliation":[{"name":"TikTok, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3768-7325","authenticated-orcid":false,"given":"Zhixin","family":"Zhang","sequence":"additional","affiliation":[{"name":"TikTok, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557442"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020","volume":"1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). PMLR, 1597-1607."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v17i1.22209"},{"key":"e_1_3_2_1_4_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-022-00951-3"},{"key":"e_1_3_2_1_7_1","volume-title":"Momentum Contrast for Unsupervised Visual Representation Learning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. Computer Vision Foundation \/ IEEE, 9726-9735."},{"key":"e_1_3_2_1_8_1","first-page":"2553","volume-title":"Embeddingbased Retrieval in Facebook Search. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Huang Jui-Ting","year":"2020","unstructured":"Jui-Ting Huang, Ashish Sharma, Shuying Sun, Li Xia, David Zhang, Philip Pronin, Janani Padmanabhan, Giuseppe Ottaviano, and Linjun Yang. 2020. Embeddingbased Retrieval in Facebook Search. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23-27, 2020. ACM, 2553-2561."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688039"},{"key":"e_1_3_2_1_10_1","unstructured":"Prannay Khosla Piotr Teterwak ChenWang Aaron Sarna Yonglong Tian Phillip Isola Aaron Maschinot Ce Liu and Dilip Krishnan. 2020. Supervised Contrastive Learning. (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022","volume":"12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 12888-12900."},{"key":"e_1_3_2_1_12_1","first-page":"3181","volume-title":"Embedding-based Product Retrieval in Taobao Search. In KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Li Sen","year":"2021","unstructured":"Sen Li, Fuyu Lv, Taiwei Jin, Guli Lin, Keping Yang, Xiaoyi Zeng, Xiao-Ming Wu, and Qianli Ma. 2021. Embedding-based Product Retrieval in Taobao Search. In KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, Singapore, August 14-18, 2021. ACM, 3181-3189."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680047"},{"key":"e_1_3_2_1_14_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_15_1","volume-title":"Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning. CoRR abs\/2310.03400","author":"Ma Huan","year":"2023","unstructured":"Huan Ma, Changqing Zhang, Huazhu Fu, Peilin Zhao, and Bingzhe Wu. 2023. Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning. CoRR abs\/2310.03400 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.54"},{"key":"e_1_3_2_1_17_1","unstructured":"notAI.tech. 2024. NudeNet: lightweight Nudity detection. https:\/\/github.com\/notAI-tech\/NudeNet"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"8763","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139). PMLR, 8748-8763."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591848"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680045"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Mengyang Wu Yuzhi Zhao Jialun Cao Mingjie Xu Zhongming Jiang Xuehui Wang Qinbin Li Guangneng Hu Shengchao Qin and Chi-Wing Fu. 2025. ICMAssistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation. (2025) 8413-8422.","DOI":"10.1609\/aaai.v39i8.32908"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.276"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00834"},{"key":"e_1_3_2_1_25_1","volume-title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning, ICML 2022","volume":"26009","author":"Zeng Yan","year":"2022","unstructured":"Yan Zeng, Xinsong Zhang, and Hang Li. 2022. Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 25994-26009."},{"key":"e_1_3_2_1_26_1","volume-title":"Why are Visually-Grounded Language Models Bad at Image Classification?","author":"Zhang Yuhui","year":"2024","unstructured":"Yuhui Zhang, Alyssa Unell, Xiaohan Wang, Dhruba Ghosh, Yuchang Su, Ludwig Schmidt, and Serena Yeung-Levy. 2024. Why are Visually-Grounded Language Models Bad at Image Classification? (2024)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3731945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:32:50Z","timestamp":1755887570000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3731945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":26,"alternative-id":["10.1145\/3726302.3731945","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3731945","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}