{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:13:18Z","timestamp":1777655598338,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62072281"],"award-info":[{"award-number":["No.62072281"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100017054","name":"National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization","doi-asserted-by":"publisher","award":["No.U22A2033"],"award-info":[{"award-number":["No.U22A2033"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100017054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681424","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"5074-5082","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Bridging the Modality Gap: Dimension Information Alignment and Sparse Spatial Constraint for Image-Text Matching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4963-8705","authenticated-orcid":false,"given":"Xiang","family":"Ma","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5064-7425","authenticated-orcid":false,"given":"Xuemei","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3243-851X","authenticated-orcid":false,"given":"Lexin","family":"Fang","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0217-1543","authenticated-orcid":false,"given":"Caiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"e_1_3_2_1_6_1","first-page":"6704","article-title":"Cyclip: Cyclic contrastive language-image pretraining","volume":"35","author":"Goel Shashank","year":"2022","unstructured":"Shashank Goel, Hritik Bansal, Sumit Bhatia, Ryan Rossi, Vishwa Vinay, and Aditya Grover. 2022. Cyclip: Cyclic contrastive language-image pretraining. Advances in Neural Information Processing Systems, Vol. 35 (2022), 6704--6719.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547881"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00740"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Jingyu Li Zhendong Mao Shancheng Fang and Hao Li. 2022. ER-SAN: Enhanced-Adaptive Relation Self-Attention Network for Image Captioning.. In IJCAI. 1081--1087.","DOI":"10.24963\/ijcai.2022\/151"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_1_14_1","volume-title":"2022 d. Image-text embedding learning via visual and textual semantic reasoning","author":"Li Kunpeng","year":"2022","unstructured":"Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, and Yun Fu. 2022 d. Image-text embedding learning via visual and textual semantic reasoning. IEEE transactions on pattern analysis and machine intelligence, Vol. 45, 1 (2022), 641--656."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_11"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings, Part XXX 16","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXX 16. Springer, 121--137."},{"key":"e_1_3_2_1_17_1","first-page":"7","article-title":"Multi-View Visual Semantic Embedding","volume":"2","author":"Li Zheng","year":"2022","unstructured":"Zheng Li, Caili Guo, Zerun Feng, Jenq-Neng Hwang, and Xijun Xue. 2022. Multi-View Visual Semantic Embedding.. In IJCAI, Vol. 2. 7.","journal-title":"IJCAI"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103480"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 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, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_26_1","volume-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren Shaoqing","year":"2016","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2016. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 6 (2016), 1137--1149."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_28_1","volume-title":"Soft similarity and soft cosine measure: Similarity of features in vector space model. Computaci\u00f3n y Sistemas","author":"Sidorov Grigori","year":"2014","unstructured":"Grigori Sidorov, Alexander Gelbukh, Helena G\u00f3mez-Adorno, and David Pinto. 2014. Soft similarity and soft cosine measure: Similarity of features in vector space model. Computaci\u00f3n y Sistemas, Vol. 18, 3 (2014), 491--504."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1348\/000711005X48266"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings, Part XXIV 16","author":"Wang Haoran","year":"2020","unstructured":"Haoran Wang, Ying Zhang, Zhong Ji, Yanwei Pang, and Lin Ma. 2020. Consensus-aware visual-semantic embedding for image-text matching. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXIV 16. Springer, 18--34."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"e_1_3_2_1_34_1","volume-title":"Learning dual semantic relations with graph attention for image-text matching","author":"Wen Keyu","year":"2020","unstructured":"Keyu Wen, Xiaodong Gu, and Qingrong Cheng. 2020. Learning dual semantic relations with graph attention for image-text matching. IEEE transactions on circuits and systems for video technology, Vol. 31, 7 (2020), 2866--2879."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28538"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547883"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611703"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681424","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:46Z","timestamp":1750294666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":41,"alternative-id":["10.1145\/3664647.3681424","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681424","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}