{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:15:00Z","timestamp":1777637700799,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"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":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531826","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:08Z","timestamp":1657206728000},"page":"2178-2183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Cross-Probe BERT for Fast Cross-Modal Search"],"prefix":"10.1145","author":[{"given":"Tan","family":"Yu","sequence":"first","affiliation":[{"name":"Baidu Research, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongliang","family":"Fei","sequence":"additional","affiliation":[{"name":"Baidu Research, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Research, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.411"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"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) . 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_2_5_1","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR)","author":"Dinan Emily","year":"2019","unstructured":"Emily Dinan , Stephen Roller , Kurt Shuster , Angela Fan , Michael Auli , and Jason Weston . 2019 . Wizard of Wikipedia: Knowledge-Powered Conversational Agents . In Proceedings of the 7th International Conference on Learning Representations (ICLR) . New Orleans, LA. Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2019. Wizard of Wikipedia: Knowledge-Powered Conversational Agents. In Proceedings of the 7th International Conference on Learning Representations (ICLR) . New Orleans, LA."},{"key":"e_1_3_2_2_6_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2018","unstructured":"Fartash Faghri , David J. Fleet , Jamie Ryan Kiros, and Sanja Fidler . 2018 . VSE Fartash Faghri, David J. Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. VSE"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the British Machine Vision Conference (BMVC)","unstructured":": Improving Visual-Semantic Embeddings with Hard Negatives . In Proceedings of the British Machine Vision Conference (BMVC) . Newcastle, UK. : Improving Visual-Semantic Embeddings with Hard Negatives. In Proceedings of the British Machine Vision Conference (BMVC). Newcastle, UK."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.285"},{"key":"e_1_3_2_2_9_1","volume-title":"Retrieve Fast","author":"Geigle Gregor","year":"1920","unstructured":"Gregor Geigle , Jonas Pfeiffer , Nils Reimers , Ivan Vuli\u0107 , and Iryna Gurevych . 2021. Retrieve Fast , Rerank Smart : Cooperative and Joint Approaches for Improved Cross-Modal Retrieval . arXiv preprint arXiv:2103.1 1920 (2021). Gregor Geigle, Jonas Pfeiffer, Nils Reimers, Ivan Vuli\u0107 , and Iryna Gurevych. 2021. Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval. arXiv preprint arXiv:2103.11920 (2021)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR). Addis Ababa, Ethiopia.","author":"Humeau Samuel","year":"2020","unstructured":"Samuel Humeau , Kurt Shuster , Marie-Anne Lachaux , and Jason Weston . 2020 . Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring . In Proceedings of the 8th International Conference on Learning Representations (ICLR). Addis Ababa, Ethiopia. Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux, and Jason Weston. 2020. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In Proceedings of the 8th International Conference on Learning Representations (ICLR). Addis Ababa, Ethiopia."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_2_17_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_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the 13th European Conference on Computer Vision (ECCV), Part V","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin , Michael Maire , Serge J. Belongie , James Hays , Pietro Perona , Deva Ramanan , Piotr Doll\u00e1 r, and C. Lawrence Zitnick . 2014. Microsoft COCO: Common Objects in Context . In Proceedings of the 13th European Conference on Computer Vision (ECCV), Part V . Zurich, Switzerland, 740--755. Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1 r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Proceedings of the 13th European Conference on Computer Vision (ECCV), Part V. Zurich, Switzerland, 740--755."},{"key":"e_1_3_2_2_20_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 . 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. 2021. 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_2_21_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_2_22_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_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401271"},{"key":"e_1_3_2_2_25_1","volume-title":"Berg","author":"Ordonez Vicente","year":"2011","unstructured":"Vicente Ordonez , Girish Kulkarni , and Tamara L . Berg . 2011 . Im2Text: Describing Images Using 1 Million Captioned Photographs. In Advances in Neural Information Processing Systems (NIPS). Granada, Spain , 1143--1151. Vicente Ordonez, Girish Kulkarni, and Tamara L. Berg. 2011. Im2Text: Describing Images Using 1 Million Captioned Photographs. In Advances in Neural Information Processing Systems (NIPS). Granada, Spain, 1143--1151."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_2_27_1","unstructured":"Shaoqing Ren Kaiming He Ross B. Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems (NIPS). Montreal Canada 91--99. Shaoqing Ren Kaiming He Ross B. Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems (NIPS). Montreal Canada 91--99."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1062"},{"key":"e_1_3_2_2_33_1","volume-title":"Advances in Neural Information Processing Systems (NIPS).","author":"Vaswani Ashish","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 (NIPS). Long Beach, CA , 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 (NIPS). Long Beach, CA, 5998--6008."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00225"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482233"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403297"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462924"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531826","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:26Z","timestamp":1750183826000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531826"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":38,"alternative-id":["10.1145\/3477495.3531826","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531826","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}