{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T13:15:30Z","timestamp":1769692530267,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"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":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591844","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"3310-3314","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Enhancing Dynamic Image Advertising with Vision-Language Pre-training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0894-5824","authenticated-orcid":false,"given":"Zhoufutu","family":"Wen","sequence":"first","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0253-5488","authenticated-orcid":false,"given":"Xinyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0863-2539","authenticated-orcid":false,"given":"Zhipeng","family":"Jin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5077-4782","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9931-4217","authenticated-orcid":false,"given":"Wei","family":"Jia","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8069-2845","authenticated-orcid":false,"given":"Xiaodong","family":"Chen","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7346-5258","authenticated-orcid":false,"given":"Shuanglong","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7305-8940","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei.","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei. 2022. VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV).","author":"Chen Yen-Chun","year":"2019","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2019. UNITER: UNiversal Image-TExt Representation Learning. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).","author":"Cubuk Ekin Dogus","unstructured":"Ekin Dogus Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V. Le. 2020. Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (NAACL-HLT).","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 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (NAACL-HLT)."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR).","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, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proceedings of the 9th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330651"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"e_1_3_2_2_8_1","volume-title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark. In Advances in Neural Information Processing Systems (NeurIPS).","author":"Gu Jiaxi","year":"2022","unstructured":"Jiaxi Gu, Xiaojun Meng, Guansong Lu, Lu Hou, Minzhe Niu, Xiaodan Liang, Lewei Yao, Runhu Huang, W. Zhang, Xingda Jiang, Chunjing Xu, and Hang Xu. 2022. Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR).","author":"He Kaiming","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR)."},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML).","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In Proceedings of the 38th International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML).","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In Proceedings of the 38th International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981--7"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123366"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML).","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 Proceedings of the International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_2_15_1","volume-title":"Shafiq R. Joty, Caiming Xiong, and Steven C. H. Hoi.","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Deepak Gotmare, Shafiq R. Joty, Caiming Xiong, and Steven C. H. Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896494"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_2_18_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_2_19_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML).","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)."},{"key":"e_1_3_2_2_20_1","volume-title":"Multi-view Contrastive Learning for Image-Text Pre-training. arXiv preprint arXiv:2209.15270","author":"Shan Bin","year":"2022","unstructured":"Bin Shan, Weichong Yin, Yu Sun, Hao Tian, Hua Wu, and Haifeng Wang. 2022. ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training. arXiv preprint arXiv:2209.15270 (2022)."},{"key":"e_1_3_2_2_21_1","volume-title":"Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748","author":"van den Oord A\u00e4ron","year":"2018","unstructured":"A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of the 10th International Conference on Learning Representations (ICLR).","author":"Wang Zirui","year":"2022","unstructured":"Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. 2022. SimVLM: Simple Visual Language Model Pretraining with Weak Supervision. In Proceedings of the 10th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_23_1","volume-title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese. arXiv preprint arXiv:2211.01335","author":"Yang Antoine","year":"2022","unstructured":"Antoine 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_2_24_1","volume-title":"CoCa: Contrastive Captioners are Image-Text Foundation Models. arXiv preprint arXiv:2205.01917","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. CoCa: Contrastive Captioners are Image-Text Foundation Models. arXiv preprint arXiv:2205.01917 (2022)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020786"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482143"},{"key":"e_1_3_2_2_27_1","volume-title":"TIRA in Baidu Image Advertising. In IEEE 37th International Conference on Data Engineering (ICDE).","author":"Yu Tan","year":"2021","unstructured":"Tan Yu, Xuemeng Yang, Yan Jiang, Hongfang Zhang, Weijie Zhao, and Ping Li. 2021. TIRA in Baidu Image Advertising. In IEEE 37th International Conference on Data Engineering (ICDE)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462924"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539212"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548226"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591844","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:59Z","timestamp":1750178279000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591844"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":31,"alternative-id":["10.1145\/3539618.3591844","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591844","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}