{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T17:44:10Z","timestamp":1786470250646,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":42,"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"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62072462"],"award-info":[{"award-number":["62072462"]}]},{"name":"National Key R&D Program of China","award":["2020AAA0108600"],"award-info":[{"award-number":["2020AAA0108600"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3532047","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:08Z","timestamp":1657206728000},"page":"1012-1021","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Progressive Learning for Image Retrieval with Hybrid-Modality Queries"],"prefix":"10.1145","author":[{"given":"Yida","family":"Zhao","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqing","family":"Song","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 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 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 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 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186."},{"key":"e_1_3_2_2_8_1","volume-title":"Proceedings of the 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 , Jakob Uszkoreit , and Neil Houlsby . 2021 . An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale . In Proceedings of the International Conference on Learning Representations. 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 International Conference on Learning Representations."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the British Machine Vision Conference. 12","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. 12 . 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. 12."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. 676--686","author":"Guo Xiaoxiao","year":"2018","unstructured":"Xiaoxiao Guo , Hui Wu , Yu Cheng , Steven Rennie , Gerald Tesauro , and Rog\u00e9 rio Schmidt Feris . 2018 . Dialog-based Interactive Image Retrieval . In Proceedings of the Advances in Neural Information Processing Systems. 676--686 . Xiaoxiao Guo, Hui Wu, Yu Cheng, Steven Rennie, Gerald Tesauro, and Rog\u00e9 rio Schmidt Feris. 2018. Dialog-based Interactive Image Retrieval. In Proceedings of the Advances in Neural Information Processing Systems. 676--686."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080681"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 1771--1779","author":"Kim Jongseok","year":"2021","unstructured":"Jongseok Kim , Youngjae Yu , Hoeseong Kim , and Gunhee Kim . 2021 . Dual Compositional Learning in Interactive Image Retrieval . In Proceedings of the AAAI Conference on Artificial Intelligence. 1771--1779 . Jongseok Kim, Youngjae Yu, Hoeseong Kim, and Gunhee Kim. 2021. Dual Compositional Learning in Interactive Image Retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence. 1771--1779."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_2_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 . 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_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. 13--23","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 . In Proceedings of the Advances in Neural Information Processing Systems. 13--23 . Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In Proceedings of the Advances in Neural Information Processing Systems. 13--23."},{"key":"e_1_3_2_2_25_1","volume-title":"Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord , Yazhe Li , and Oriol Vinyals . 2018. Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748 ( 2018 ). Aaron 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_26_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 3942--3951","author":"Perez Ethan","unstructured":"Ethan Perez , Florian Strub , Harm de Vries , Vincent Dumoulin , and Aaron C. Courville . 2018. FiLM: Visual Reasoning with a General Conditioning Layer . In Proceedings of the AAAI Conference on Artificial Intelligence. 3942--3951 . Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, and Aaron C. Courville. 2018. FiLM: Visual Reasoning with a General Conditioning Layer. In Proceedings of the AAAI Conference on Artificial Intelligence. 3942--3951."},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the 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 , Gretchen Krueger , and Ilya Sutskever . 2021 . Learning Transferable Visual Models From Natural Language Supervision . In Proceedings of the International Conference on Machine Learning. 8748--8763 . 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 International Conference on Machine Learning. 8748--8763."},{"key":"e_1_3_2_2_28_1","volume-title":"et almbox","author":"Radford Alec","year":"2019","unstructured":"Alec Radford , Jeffrey Wu , Rewon Child , David Luan , Dario Amodei , Ilya Sutskever , et almbox . 2019 . Language Models are Unsupervised Multitask Learners. OpenAI blog, Vol. 1 , 8 (2019), 9. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et almbox. 2019. Language Models are Unsupervised Multitask Learners. OpenAI blog, Vol. 1, 8 (2019), 9."},{"key":"e_1_3_2_2_29_1","volume-title":"Fashion-Gen: The Generative Fashion Dataset and Challenge. arXiv preprint arXiv:1806.08317","author":"Rostamzadeh Negar","year":"2018","unstructured":"Negar Rostamzadeh , Seyedarian Hosseini , Thomas Boquet , Wojciech Stokowiec , Ying Zhang , Christian Jauvin , and Chris Pal . 2018. Fashion-Gen: The Generative Fashion Dataset and Challenge. arXiv preprint arXiv:1806.08317 ( 2018 ). Negar Rostamzadeh, Seyedarian Hosseini, Thomas Boquet, Wojciech Stokowiec, Ying Zhang, Christian Jauvin, and Chris Pal. 2018. Fashion-Gen: The Generative Fashion Dataset and Challenge. arXiv preprint arXiv:1806.08317 (2018)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925954"},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. 4967--4976","author":"Santoro Adam","year":"2017","unstructured":"Adam Santoro , David Raposo , David G. T. Barrett , Mateusz Malinowski , Razvan Pascanu , Peter W. Battaglia , and Tim Lillicrap . 2017 . A simple neural network module for relational reasoning . In Proceedings of the Advances in Neural Information Processing Systems. 4967--4976 . Adam Santoro, David Raposo, David G. T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter W. Battaglia, and Tim Lillicrap. 2017. A simple neural network module for relational reasoning. In Proceedings of the Advances in Neural Information Processing Systems. 4967--4976."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_1"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475483"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462881"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413917"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"}],"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\/3477495.3532047","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3532047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:35Z","timestamp":1750183835000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3532047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":42,"alternative-id":["10.1145\/3477495.3532047","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3532047","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"}}]}}