{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T21:56:59Z","timestamp":1785362219227,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"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":[[2022,10,17]]},"DOI":"10.1145\/3511808.3557653","type":"proceedings-article","created":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T01:22:22Z","timestamp":1665883342000},"page":"4655-4660","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Multi-scale Multi-modal Dictionary BERT For Effective Text-image Retrieval in Multimedia Advertising"],"prefix":"10.1145","author":[{"given":"Tan","family":"Yu","sequence":"first","affiliation":[{"name":"Baidu Research, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Ads, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipeng","family":"Jin","sequence":"additional","affiliation":[{"name":"Baidu Ads, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Baidu Ads, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Fei","sequence":"additional","affiliation":[{"name":"Baidu Research, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Research, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)","author":"Cao Yue","unstructured":"Yue Cao , Mingsheng Long , Jianmin Wang , Qiang Yang , and Philip S. Yu . 2016. Deep Visual-Semantic Hashing for Cross-Modal Retrieval . In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) . San Francisco, CA, 1445--1454. Yue Cao, Mingsheng Long, Jianmin Wang, Qiang Yang, and Philip S. Yu. 2016. Deep Visual-Semantic Hashing for Cross-Modal Retrieval. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). San Francisco, CA, 1445--1454."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_3_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) . Minneapolis, MN, 4171--4186. 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). Minneapolis, MN, 4171--4186."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of British Machine Vision Conference (BMVC)","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 British Machine Vision Conference (BMVC) . Newcastle, UK, 12. Fartash Faghri, David J. Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In Proceedings of British Machine Vision Conference (BMVC). Newcastle, UK, 12."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.285"},{"key":"e_1_3_2_1_6_1","volume-title":"Advances in Neural Information Processing Systems (NIPS).","author":"Frome Andrea","unstructured":"Andrea Frome , Gregory S. Corrado , Jonathon Shlens , Samy Bengio , Jeffrey Dean , Marc'Aurelio Ranzato , and Tom\u00e1 s Mikolov . 2013. DeViSE: A Deep Visual-Semantic Embedding Model . In Advances in Neural Information Processing Systems (NIPS). Lake Tahoe, NV , 2121--2129. Andrea Frome, Gregory S. Corrado, Jonathon Shlens, Samy Bengio, Jeffrey Dean, Marc'Aurelio Ranzato, and Tom\u00e1 s Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. In Advances in Neural Information Processing Systems (NIPS). Lake Tahoe, NV, 2121--2129."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_1_8_1","unstructured":"Zhe Gan Yen-Chun Chen Linjie Li Chen Zhu Yu Cheng and Jingjing Liu. 2020. Large-Scale Adversarial Training for Vision-and-Language Representation Learning. In Advances in Neural Information Processing Systems (NeurIPS). virtual. Zhe Gan Yen-Chun Chen Linjie Li Chen Zhu Yu Cheng and Jingjing Liu. 2020. Large-Scale Adversarial Training for Vision-and-Language Representation Learning. In Advances in Neural Information Processing Systems (NeurIPS). virtual."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00473"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"e_1_3_2_1_12_1","volume-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849","author":"Huang Zhicheng","year":"2020","unstructured":"Zhicheng Huang , Zhaoyang Zeng , Bei Liu , Dongmei Fu , and Jianlong Fu. 2020. Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 ( 2020 ). Zhicheng Huang, Zhaoyang Zeng, Bei Liu, Dongmei Fu, and Jianlong Fu. 2020. Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 (2020)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_14_1","volume-title":"Fahad Shahbaz Khan, and Mubarak Shah.","author":"Khan Salman","year":"2021","unstructured":"Salman Khan , Muzammal Naseer , Munawar Hayat , Syed Waqas Zamir , Fahad Shahbaz Khan, and Mubarak Shah. 2021 . Transformers in Vision : A Survey . arXiv preprint arXiv:2101.01169 (2021). Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, and Mubarak Shah. 2021. Transformers in Vision: A Survey. arXiv preprint arXiv:2101.01169 (2021)."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the NeurIPS 2019 Workshop on Visually Grounded Interaction and Language (ViGIL)","author":"Kiela Douwe","year":"2019","unstructured":"Douwe Kiela , Suvrat Bhooshan , Hamed Firooz , and Davide Testuggine . 2019 . Supervised Multimodal Bitransformers for Classifying Images and Text . In Proceedings of the NeurIPS 2019 Workshop on Visually Grounded Interaction and Language (ViGIL) . Vancouver, Canada. Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, and Davide Testuggine. 2019. Supervised Multimodal Bitransformers for Classifying Images and Text. In Proceedings of the NeurIPS 2019 Workshop on Visually Grounded Interaction and Language (ViGIL). Vancouver, Canada."},{"key":"e_1_3_2_1_16_1","unstructured":"Douwe Kiela Hamed Firooz Aravind Mohan Vedanuj Goswami Amanpreet Singh Pratik Ringshia and Davide Testuggine. 2020. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. In Advances in Neural Information Processing Systems (NeurIPS). Virtual. Douwe Kiela Hamed Firooz Aravind Mohan Vedanuj Goswami Amanpreet Singh Pratik Ringshia and Davide Testuggine. 2020. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. In Advances in Neural Information Processing Systems (NeurIPS). Virtual."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR)","author":"Lee Sangho","year":"2021","unstructured":"Sangho Lee , Youngjae Yu , Gunhee Kim , Thomas M. Breuel , Jan Kautz , and Yale Song . 2021 . Parameter Efficient Multimodal Transformers for Video Representation Learning . In Proceedings of the 9th International Conference on Learning Representations (ICLR) . Virtual Event, Austria. Sangho Lee, Youngjae Yu, Gunhee Kim, Thomas M. Breuel, Jan Kautz, and Yale Song. 2021. Parameter Efficient Multimodal Transformers for Video Representation Learning. In Proceedings of the 9th International Conference on Learning Representations (ICLR). Virtual Event, Austria."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"e_1_3_2_1_22_1","volume-title":"A Closer Look at the Robustness of Vision-and-Language Pre-trained Models. arXiv preprint arXiv:2012.08673","author":"Li Linjie","year":"2020","unstructured":"Linjie Li , Zhe Gan , and Jingjing Liu . 2020c. A Closer Look at the Robustness of Vision-and-Language Pre-trained Models. arXiv preprint arXiv:2012.08673 ( 2020 ). Linjie Li, Zhe Gan, and Jingjing Liu. 2020c. A Closer Look at the Robustness of Vision-and-Language Pre-trained Models. arXiv preprint arXiv:2012.08673 (2020)."},{"key":"e_1_3_2_1_23_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 . 2019 . Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019). Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP). Virtual Event \/ Punta Cana, Dominican Republic, 9796--9809","author":"Liu Haoliang","year":"2021","unstructured":"Haoliang Liu , Tan Yu , and Ping Li . 2021 a. Inflate and Shrink: Enriching and Reducing Interactions for Fast Text-Image Retrieval . In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP). Virtual Event \/ Punta Cana, Dominican Republic, 9796--9809 . Haoliang Liu, Tan Yu, and Ping Li. 2021a. Inflate and Shrink: Enriching and Reducing Interactions for Fast Text-Image Retrieval. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP). Virtual Event \/ Punta Cana, Dominican Republic, 9796--9809."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.772"},{"key":"e_1_3_2_1_27_1","unstructured":"Jiaheng Liu Tan Yu Hanyu Peng Mingming Sun and Ping Li. 2022. Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval. In Findings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). Jiaheng Liu Tan Yu Hanyu Peng Mingming Sun and Ping Li. 2022. Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval. In Findings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)."},{"key":"e_1_3_2_1_28_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS).","author":"Lu Jiasen","unstructured":"Jiasen Lu , Dhruv Batra , Devi Parikh , and Stefan Lee . 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks . In Advances in Neural Information Processing Systems (NeurIPS). Vancouver, Canada , 13--23. Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In Advances in Neural Information Processing Systems (NeurIPS). Vancouver, Canada, 13--23."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Xiaopeng Lu Tiancheng Zhao and Kyusong Lee. 2021. VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL\/IJCNLP). Virtual Event 5020--5029. Xiaopeng Lu Tiancheng Zhao and Kyusong Lee. 2021. VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL\/IJCNLP). Virtual Event 5020--5029.","DOI":"10.18653\/v1\/2021.acl-long.389"},{"key":"e_1_3_2_1_31_1","volume-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353","author":"Luo Huaishao","year":"2020","unstructured":"Huaishao Luo , Lei Ji , Botian Shi , Haoyang Huang , Nan Duan , Tianrui Li , Jason Li , Taroon Bharti , and Ming Zhou . 2020 . Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020). Huaishao Luo, Lei Ji, Botian Shi, Haoyang Huang, Nan Duan, Tianrui Li, Jason Li, Taroon Bharti, and Ming Zhou. 2020. Univl: A unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"e_1_3_2_1_33_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 ). 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_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_1_35_1","volume-title":"Learning video representations using contrastive bidirectional transformer. arXiv preprint arXiv:1906.05743","author":"Sun Chen","year":"2019","unstructured":"Chen Sun , Fabien Baradel , Kevin Murphy , and Cordelia Schmid . 2019a. Learning video representations using contrastive bidirectional transformer. arXiv preprint arXiv:1906.05743 ( 2019 ). Chen Sun, Fabien Baradel, Kevin Murphy, and Cordelia Schmid. 2019a. Learning video representations using contrastive bidirectional transformer. arXiv preprint arXiv:1906.05743 (2019)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531826"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482233"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403297"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481937"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481937"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"}],"event":{"name":"CIKM '22: The 31st ACM International Conference on Information and Knowledge Management","location":"Atlanta GA USA","acronym":"CIKM '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 31st ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557653","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3511808.3557653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:48Z","timestamp":1750182528000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557653"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,17]]},"references-count":45,"alternative-id":["10.1145\/3511808.3557653","10.1145\/3511808"],"URL":"https:\/\/doi.org\/10.1145\/3511808.3557653","relation":{},"subject":[],"published":{"date-parts":[[2022,10,17]]},"assertion":[{"value":"2022-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}