{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:33:51Z","timestamp":1772908431268,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651087","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["SAMNER: Image Screening and Cross-Modal Alignment Networks for Multimodal Named Entity Recognition"],"prefix":"10.1109","author":[{"given":"Luyi","family":"Yang","sequence":"first","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Xinjiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1078"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.168"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_12"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00867"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447410"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.093"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3402886"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3361474\/mm1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1609"},{"key":"ref15","article-title":"Bidirectional lstm-crf models for sequence tagging","author":"Huang","year":"2015"},{"key":"ref16","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342066"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref19","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.wnut-1.11"},{"key":"ref21","article-title":"Improving depth gradient continuity in transformers: A comparative study on monocular depth estimation with cnn","author":"Yao","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73197-7_12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103546"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref29","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/977035.977059"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548228"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1101"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3323402"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651087.pdf?arnumber=10651087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T07:06:41Z","timestamp":1725952001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651087","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}