{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:33:11Z","timestamp":1785857591518,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["U21B2024, 62202327"],"award-info":[{"award-number":["U21B2024, 62202327"]}]},{"name":"the China Postdoctoral Science Foundation","award":["2022M712369"],"award-info":[{"award-number":["2022M712369"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612507","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"4807-4815","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Progressive Positive Association Framework for Image and Text Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9609-6120","authenticated-orcid":false,"given":"Wenhui","family":"Li","sequence":"first","affiliation":[{"name":"Tianjin University & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6015-6099","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5165-204X","authenticated-orcid":false,"given":"Yuting","family":"Su","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7696-5330","authenticated-orcid":false,"given":"Lanjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0578-8138","authenticated-orcid":false,"given":"Weizhi","family":"Nie","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-9145","authenticated-orcid":false,"given":"An-An","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 6077--6086","author":"Anderson Peter","unstructured":"Peter Anderson, Xiaodong He, and Chris Buehler et al. 2018. Bottom-up and top-down attention for image captioning and visual question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition. 6077--6086."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0004-1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.512"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In The North American","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, and Kenton Lee et al. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In The North American Chapter of the Association for Computational Linguistics. 4171--4186."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_1_9_1","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding Ming","year":"2021","unstructured":"Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, et al. 2021. Cogview: Mastering text-to-image generation via transformers. Advances in Neural Information Processing Systems, Vol. 34 (2021), 19822--19835.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463650"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00122"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463031"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17980--17989","author":"Hu Xiaowei","year":"2022","unstructured":"Xiaowei Hu, Zhe Gan, Jianfeng Wang, Zhengyuan Yang, Zicheng Liu, Yumao Lu, and Lijuan Wang. 2022. Scaling up vision-language pre-training for image captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17980--17989."},{"key":"e_1_3_2_1_15_1","volume-title":"Learning with noisy correspondence for cross-modal matching Advances in Neural Information Processing Systems","author":"Huang Zhenyu","year":"2021","unstructured":"Zhenyu Huang, Guocheng Niu, Xiao Liu, Wenbiao Ding, Xinyan Xiao, Hua Wu, and Xi Peng. 2021. Learning with noisy correspondence for cross-modal matching Advances in Neural Information Processing Systems, Vol. 34 (2021), 29406--29419."},{"key":"e_1_3_2_1_16_1","volume-title":"Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations.","author":"Thomas","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision Vol. 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00554"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123553"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3128744"},{"key":"e_1_3_2_1_21_1","volume-title":"Zurich, Switzerland","volume":"8693","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, and James Hays et al. 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, Vol. 8693. 740--755."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00252"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093548"},{"key":"e_1_3_2_1_26_1","volume-title":"Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations. arXiv preprint arXiv:2204.09268","author":"Pishdad Leila","year":"2022","unstructured":"Leila Pishdad, Ran Zhang, Konstantinos G Derpanis, Allan Jepson, and Afsaneh Fazly. 2022. Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations. arXiv preprint arXiv:2204.09268 (2022)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the IEEE international conference on computer vision. 2641--2649","author":"Plummer Bryan A.","unstructured":"Bryan A. Plummer, Liwei Wang, and Julia et al. Hockenmaier. 2015. Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models. In Proceedings of the IEEE international conference on computer vision. 2641--2649."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547922"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"e_1_3_2_1_33_1","volume-title":"2023 a. Generative recommendation: Towards next-generation recommender paradigm. arXiv preprint arXiv:2304.03516","author":"Wang Wenjie","year":"2023","unstructured":"Wenjie Wang, Xinyu Lin, Fuli Feng, Xiangnan He, and Tat-Seng Chua. 2023 a. Generative recommendation: Towards next-generation recommender paradigm. arXiv preprint arXiv:2304.03516 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103280"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.09.079"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462924"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475380"},{"key":"e_1_3_2_1_39_1","volume-title":"Electronics and Mobile Communication Conference (IEMCON). IEEE, 0258--0265","author":"Zeng Zhixian","year":"2021","unstructured":"Zhixian Zeng, Jianjun Cao, Nianfeng Weng, Guoquan Jiang, Yizhuo Rao, and Yuxin Xu. 2021a. Softmax Pooling for Super Visual Semantic Embedding. In 2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON). IEEE, 0258--0265."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","author":"Zhang Huatian","unstructured":"Huatian Zhang, Zhendong Mao, and Kun Zhang et al. 2022a. Show Your Faith: Cross-Modal Confidence-Aware Network for Image-Text Matching. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_41_1","volume-title":"Unified adaptive relevance distinguishable attention network for image-text matching","author":"Zhang Kun","year":"2022","unstructured":"Kun Zhang, Zhendong Mao, Anan Liu, and Yongdong Zhang. 2022b. Unified adaptive relevance distinguishable attention network for image-text matching. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413760"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548058"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612507","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:54:57Z","timestamp":1755820497000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612507"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":44,"alternative-id":["10.1145\/3581783.3612507","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612507","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}