{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:20:55Z","timestamp":1775578855652,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61966004, 61866004"],"award-info":[{"award-number":["61966004, 61866004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Gusngxi Natural Science Foundation","award":["2019GXNSFDA245018"],"award-info":[{"award-number":["2019GXNSFDA245018"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548058","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:46Z","timestamp":1665416566000},"page":"395-403","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["Image-Text Matching with Fine-Grained Relational Dependency and Bidirectional Attention-Based Generative Networks"],"prefix":"10.1145","author":[{"given":"Jianwei","family":"Zhu","sequence":"first","affiliation":[{"name":"Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufei","family":"Zeng","sequence":"additional","affiliation":[{"name":"Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Wei","sequence":"additional","affiliation":[{"name":"Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huifang","family":"Ma","sequence":"additional","affiliation":[{"name":"Northwest Normal University, Lanzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"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\/CVPR42600.2020.01267"},{"key":"e_1_3_2_2_3_1","volume-title":"Improving Object Detection with Relation Mining Network. In 2020 IEEE International Conference on Data Mining. IEEE, 52--61","author":"Chen Shengjia","year":"2020","unstructured":"Shengjia Chen , Zhixin Li , Feicheng Huang , Canlong Zhang , and Huifang Ma . 2020 c. Improving Object Detection with Relation Mining Network. In 2020 IEEE International Conference on Data Mining. IEEE, 52--61 . Shengjia Chen, Zhixin Li, Feicheng Huang, Canlong Zhang, and Huifang Ma. 2020c. Improving Object Detection with Relation Mining Network. In 2020 IEEE International Conference on Data Mining. IEEE, 52--61."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025128"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"e_1_3_2_2_6_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly etal 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).  Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_7_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri , David J Fleet , Jamie Ryan Kiros, and Sanja Fidler . 2017 a. Vse : Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017). Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017a. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_2_8_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri , David J Fleet , Jamie Ryan Kiros, and Sanja Fidler . 2017 b. Vse : Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017). Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017b. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.926652"},{"key":"e_1_3_2_2_13_1","volume-title":"Image captioning: Transforming objects into words. arXiv preprint arXiv:1906.05963","author":"Herdade Simao","year":"2019","unstructured":"Simao Herdade , Armin Kappeler , Kofi Boakye , and Joao Soares . 2019. Image captioning: Transforming objects into words. arXiv preprint arXiv:1906.05963 ( 2019 ). Simao Herdade, Armin Kappeler, Kofi Boakye, and Joao Soares. 2019. Image captioning: Transforming objects into words. arXiv preprint arXiv:1906.05963 (2019)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02804-6"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05919-y"},{"key":"e_1_3_2_2_17_1","volume-title":"Step-Wise Hierarchical Alignment Network for Image-Text Matching. arXiv preprint arXiv:2106.06509","author":"Ji Zhong","year":"2021","unstructured":"Zhong Ji , Kexin Chen , and Haoran Wang . 2021. Step-Wise Hierarchical Alignment Network for Image-Text Matching. arXiv preprint arXiv:2106.06509 ( 2021 ). Zhong Ji, Kexin Chen, and Haoran Wang. 2021. Step-Wise Hierarchical Alignment Network for Image-Text Matching. arXiv preprint arXiv:2106.06509 (2021)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/89.568732"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_2_20_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 ( 2016 ). Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_2_21_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros , Ruslan Salakhutdinov , and Richard S Zemel . 2014a. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 ( 2014 ). Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. 2014a. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)."},{"key":"e_1_3_2_2_22_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros , Ruslan Salakhutdinov , and Richard S Zemel . 2014b. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 ( 2014 ). Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. 2014b. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)."},{"key":"e_1_3_2_2_23_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , and Radu Soricut . 2019 . Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019). Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104475"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_31_1","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","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 . Advances in Neural Information Processing Systems , Vol. 28 (2015), 91 -- 99 . Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems , Vol. 28 (2015), 91--99.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","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 , 11 (2008). Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research , Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_2_33_1","first-page":"5998","article-title":"Attention is all you need","volume":"30","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 . Advances in Neural Information Processing Systems , Vol. 30 (2017), 5998 -- 6008 . Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems , Vol. 30 (2017), 5998--6008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"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":"10.1109\/WACV45572.2020.9093614"},{"key":"e_1_3_2_2_37_1","volume-title":"Position focused attention network for image-text matching. arXiv preprint arXiv:1907.09748","author":"Wang Yaxiong","year":"2019","unstructured":"Yaxiong Wang , Hao Yang , Xueming Qian , Lin Ma , Jing Lu , Biao Li , and Xin Fan . 2019b. Position focused attention network for image-text matching. arXiv preprint arXiv:1907.09748 ( 2019 ). Yaxiong Wang, Hao Yang, Xueming Qian, Lin Ma, Jing Lu, Biao Li, and Xin Fan. 2019b. Position focused attention network for image-text matching. arXiv preprint arXiv:1907.09748 (2019)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.01.011"},{"key":"e_1_3_2_2_40_1","volume-title":"Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853","author":"Xu Bing","year":"2015","unstructured":"Bing Xu , Naiyan Wang , Tianqi Chen , and Mu Li. 2015b. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 ( 2015 ). Bing Xu, Naiyan Wang, Tianqi Chen, and Mu Li. 2015b. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)."},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu , Jimmy Ba , Ryan Kiros , Kyunghyun Cho , Aaron Courville , Ruslan Salakhudinov , Rich Zemel , and Yoshua Bengio . 2015 a. Show, attend and tell: Neural image caption generation with visual attention . In Proceedings of the International Conference on Machine Learning. PMLR , 2048--2057. Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015a. Show, attend and tell: Neural image caption generation with visual attention. In Proceedings of the International Conference on Machine Learning. PMLR, 2048--2057."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_2_45_1","volume-title":"PBGN: Phased bidirectional generation network in text-to-image synthesis. Neural Processing Letters","author":"Zhu Jianwei","year":"2022","unstructured":"Jianwei Zhu , Zhixin Li , Jiahui Wei , and Huifang Ma . 2022 . PBGN: Phased bidirectional generation network in text-to-image synthesis. Neural Processing Letters (2022), 1--21.iogr Jianwei Zhu, Zhixin Li, Jiahui Wei, and Huifang Ma. 2022. PBGN: Phased bidirectional generation network in text-to-image synthesis. Neural Processing Letters (2022), 1--21.iogr"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548058","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:29Z","timestamp":1750186949000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":45,"alternative-id":["10.1145\/3503161.3548058","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548058","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}