{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:03:43Z","timestamp":1772906623970,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611877","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"4219-4227","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["CCMB: A Large-scale Chinese Cross-modal Benchmark"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6607-8209","authenticated-orcid":false,"given":"Chunyu","family":"Xie","sequence":"first","affiliation":[{"name":"360 AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2868-6653","authenticated-orcid":false,"given":"Heng","family":"Cai","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7848-2809","authenticated-orcid":false,"given":"Jincheng","family":"Li","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2262-1990","authenticated-orcid":false,"given":"Fanjing","family":"Kong","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9770-180X","authenticated-orcid":false,"given":"Xiaoyu","family":"Wu","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2471-2060","authenticated-orcid":false,"given":"Jianfei","family":"Song","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9455-8571","authenticated-orcid":false,"given":"Henrique","family":"Morimitsu","sequence":"additional","affiliation":[{"name":"360 AI Research & Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3437-5607","authenticated-orcid":false,"given":"Lin","family":"Yao","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6208-6873","authenticated-orcid":false,"given":"Dexin","family":"Wang","sequence":"additional","affiliation":[{"name":"360 Search Department, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7700-5746","authenticated-orcid":false,"given":"Xiangzheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"360 Search Department, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5461-1681","authenticated-orcid":false,"given":"Dawei","family":"Leng","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6167-4760","authenticated-orcid":false,"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2416-6913","authenticated-orcid":false,"given":"Yafeng","family":"Deng","sequence":"additional","affiliation":[{"name":"360 AI Research & Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_1_2_1","volume-title":"Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. 1931--1942","author":"Cho Jaemin","year":"2021","unstructured":"Jaemin Cho, Jie Lei, Hao Tan, and Mohit Bansal. 2021. Unifying vision-and-language tasks via text generation. In International Conference on Machine Learning. 1931--1942."},{"key":"e_1_3_2_1_5_1","volume-title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing. In Conference on Empirical Methods in Natural Language Processing. 657--668","author":"Cui Yiming","year":"2020","unstructured":"Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, and Guoping Hu. 2020. Revisiting Pre-Trained Models for Chinese Natural Language Processing. In Conference on Empirical Methods in Natural Language Processing. 657--668."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","volume-title":"RedCaps: Web-curated image-text data created by the people, for the people. Advances in Neural Information Processing Systems Track on Datasets and Benchmarks","author":"Desai Karan","year":"2021","unstructured":"Karan Desai, Gaurav Kaul, Zubin Aysola, and Justin Johnson. 2021. RedCaps: Web-curated image-text data created by the people, for the people. Advances in Neural Information Processing Systems Track on Datasets and Benchmarks (2021)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the Human Language Technology Conference of the NAACL. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Human Language Technology Conference of the NAACL. 4171--4186."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the British Machine Vision Conference.","author":"Faghri Fartash","year":"2018","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. Vse: Improving visual-semantic embeddings with hard negatives. In Proceedings of the British Machine Vision Conference."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30761-2"},{"key":"e_1_3_2_1_12_1","volume-title":"Wukong: 100 Million Large-scale Chinese Cross-modal Pre-training Dataset and A Foundation Framework. arXiv preprint arXiv:2202.06767","author":"Gu Jiaxi","year":"2022","unstructured":"Jiaxi Gu, Xiaojun Meng, Guansong Lu, Lu Hou, Minzhe Niu, Hang Xu, Xiaodan Liang, Wei Zhang, Xin Jiang, and Chunjing Xu. 2022. Wukong: 100 Million Large-scale Chinese Cross-modal Pre-training Dataset and A Foundation Framework. arXiv preprint arXiv:2202.06767 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International Conference on Machine Learning. 4904--4916."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123366"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Machine Learning.","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."},{"key":"e_1_3_2_1_19_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processing Systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021b. Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_1_21_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019b. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896494"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 3251--3261","author":"Lin Junyang","year":"2021","unstructured":"Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, et al. 2021. M6: A chinese multimodal pretrainer. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 3251--3261."},{"key":"e_1_3_2_1_25_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)."},{"key":"e_1_3_2_1_26_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in Neural Information Processing Systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in Neural Information Processing Systems (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"e_1_3_2_1_28_1","volume-title":"Im2text: Describing images using 1 million captioned photographs. Advances in Neural Information Processing Systems","author":"Ordonez Vicente","year":"2011","unstructured":"Vicente Ordonez, Girish Kulkarni, and Tamara Berg. 2011. Im2text: Describing images using 1 million captioned photographs. Advances in Neural Information Processing Systems (2011)."},{"key":"e_1_3_2_1_29_1","volume-title":"Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966","author":"Qi Di","year":"2020","unstructured":"Di Qi, Lin Su, Jia Song, Edward Cui, Taroon Bharti, and Arun Sacheti. 2020. Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966 (2020)."},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. 8748--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, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748--8763."},{"key":"e_1_3_2_1_31_1","volume-title":"Advances in Neural Information Processing Systems Workshop","author":"Schuhmann Christoph","year":"2021","unstructured":"Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. Advances in Neural Information Processing Systems Workshop (2021)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"e_1_3_2_1_36_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","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 (2017)."},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Machine Learning. 23318--23340","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In International Conference on Machine Learning. 23318--23340."},{"key":"e_1_3_2_1_38_1","volume-title":"Aligning pretraining for detection via object-level contrastive learning. Advances in Neural Information Processing Systems","author":"Wei Fangyun","year":"2021","unstructured":"Fangyun Wei, Yue Gao, Zhirong Wu, Han Hu, and Stephen Lin. 2021. Aligning pretraining for detection via object-level contrastive learning. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_1_39_1","volume-title":"IEEE International Conference on Multimedia and Expo.","author":"Wu Jiahong","year":"2019","unstructured":"Jiahong Wu, He Zheng, Bo Zhao, Yixin Li, Baoming Yan, Rui Liang, Wenjia Wang, Shipei Zhou, Guosen Lin, Yanwei Fu, et al. 2019. Ai challenger: A large-scale dataset for going deeper in image understanding. In IEEE International Conference on Multimedia and Expo."},{"key":"e_1_3_2_1_40_1","volume-title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese. arXiv preprint arXiv:2211.01335","author":"Yang An","year":"2022","unstructured":"An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, and Chang Zhou. 2022. Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese. arXiv preprint arXiv:2211.01335 (2022)."},{"key":"e_1_3_2_1_41_1","volume-title":"FILIP: Fine-grained Interactive Language-Image Pre-Training. In International Conference on Learning Representations.","author":"Yao Lewei","year":"2022","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2022. FILIP: Fine-grained Interactive Language-Image Pre-Training. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611877","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:58:51Z","timestamp":1755820731000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":42,"alternative-id":["10.1145\/3581783.3611877","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611877","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}