{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:48:13Z","timestamp":1763192893516,"version":"3.45.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227351","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["AMNET: Attention-Base Multiscale Network for Image-Text Matching"],"prefix":"10.1109","author":[{"given":"Jiabao","family":"Hai","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,School of Software,Xi’an,China"}]},{"given":"Qing","family":"Yu","sequence":"additional","affiliation":[{"name":"XinJiang University,School of Information Science and Engineering,Urumqi,China"}]},{"given":"Yutong","family":"Gan","sequence":"additional","affiliation":[{"name":"XinJiang University,School of Software,Urumqi,China"}]},{"given":"Mingshuo","family":"Wang","sequence":"additional","affiliation":[{"name":"XinJiang University,School of Software,Urumqi,China"}]},{"given":"Yuhui","family":"Zhou","sequence":"additional","affiliation":[{"name":"XinJiang University,School of Software,Urumqi,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475173"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105734"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475193"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547881"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref6"},{"key":"ref7","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3480949"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510841"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510664"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123978"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123978"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"article-title":"Semi-supervised classification with graph convolutional networks","year":"2016","author":"Kipf","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248160"},{"article-title":"Cfnet: Cascade fusion network for dense prediction","year":"2023","author":"Zhang","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-023-01998-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6290"},{"article-title":"Scalevlad: Improving multimodal sentiment analysis via multi-scale fusion of locally descriptors","year":"2021","author":"Luo","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3340870"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.01.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3128744"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227351.pdf?arnumber=11227351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:43:55Z","timestamp":1763192635000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227351\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227351","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}