{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T23:39:32Z","timestamp":1784072372054,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation (NSF) of China","award":["62006140, 62006142"],"award-info":[{"award-number":["62006140, 62006142"]}]},{"name":"he Key R&D Program of Shandong (Major scientific and technological innovation projects)","award":["2020CXGC010111"],"award-info":[{"award-number":["2020CXGC010111"]}]},{"name":"Young creative team in universities of Shandong Province","award":["2020KJN012"],"award-info":[{"award-number":["2020KJN012"]}]},{"name":"the NSF of Shandong Province","award":["ZR2020QF106"],"award-info":[{"award-number":["ZR2020QF106"]}]},{"name":"new AI project towards the integration of education and industry in QLUT"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462829","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T03:08:41Z","timestamp":1626059321000},"page":"1104-1113","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":174,"title":["Dynamic Modality Interaction Modeling for Image-Text Retrieval"],"prefix":"10.1145","author":[{"given":"Leigang","family":"Qu","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlong","family":"Wu","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zan","family":"Gao","sequence":"additional","affiliation":[{"name":"Shandong Artificial Intelligence Institute, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"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":"10.1145\/3209978.3210036"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ACL, 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. ACL, 4171--4186."},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the British Machine Vision Conference. BMVA Press, 1--13","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. BMVA Press, 1--13."},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the Neural Information Processing Systems Conference. MIT Press, 2121--2129","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. In Proceedings of the Neural Information Processing Systems Conference. MIT Press, 2121--2129."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331186"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331213"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--13","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical Reparameterization with Gumbel-Softmax. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--13."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the Neural Information Processing Systems Conference. MIT Press, 2181--2191","author":"Lin Ji","year":"2017","unstructured":"Ji Lin, Yongming Rao, Jiwen Lu, and Jie Zhou. 2017. Runtime Neural Pruning. In Proceedings of the Neural Information Processing Systems Conference. MIT Press, 2181--2191."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--12","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 1--12."},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the Neural Information Processing Systems Conference. MIT Press, 849--856","author":"Ng Andrew Y","year":"2002","unstructured":"Andrew Y Ng, Michael I Jordan, Yair Weiss, et al. 2002. On Spectral Clustering: Analysis and an Algorithm. In Proceedings of the Neural Information Processing Systems Conference. MIT Press, 849--856."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the Neural Information Processing Systems Conference. MIT Press, 91--99","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Proceedings of the Neural Information Processing Systems Conference. MIT Press, 91--99."},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of the Neural Information Processing Systems Conference. MIT Press, 1--11","author":"Song Lin","year":"2020","unstructured":"Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Hongbin Sun, Jian Sun, and Nanning Zheng. 2020. Fine-Grained Dynamic Head for Object Detection. In Proceedings of the Neural Information Processing Systems Conference. MIT Press, 1--11."},{"key":"e_1_3_2_2_29_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9, 86 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of the Neural Information Processing Systems Conference. MIT Press, 5998--6008","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. In Proceedings of the Neural Information Processing Systems Conference. MIT Press, 5998--6008."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462829","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:16Z","timestamp":1750193236000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462829"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":42,"alternative-id":["10.1145\/3404835.3462829","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462829","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}