{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:53:09Z","timestamp":1778824389364,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976247"],"award-info":[{"award-number":["61976247"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2022.3221017","type":"journal-article","created":{"date-parts":[[2022,11,9]],"date-time":"2022-11-09T20:41:07Z","timestamp":1668026467000},"page":"111-120","source":"Crossref","is-referenced-by-count":48,"title":["M3S: Scene Graph Driven Multi-Granularity Multi-Task Learning for Multi-Modal NER"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8690-8164","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6134-6094","authenticated-orcid":false,"given":"Yan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3188-6284","authenticated-orcid":false,"given":"Keyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiping","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaorong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"huang","year":"2015"},{"key":"ref38","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref33","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/977035.977059"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20536"},{"key":"ref37","article-title":"Layer Normalization","author":"ba","year":"2016"},{"key":"ref36","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref10","first-page":"1038","article-title":"Multi-modal representation with embedded visual guiding objects for named entity recognition in social media posts","author":"wu","year":"0","journal-title":"Proc 28th ACM Int Conf Multimedia"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1101"},{"key":"ref11","first-page":"3342","article-title":"Improving multi-modal named entity recognition via entity span detection with unified multi-modal transformer","author":"yu","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref12","first-page":"13860","article-title":"Rpbert: A text-image relation propagation-based BERT model for multi-modal NER","author":"sun","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105895"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138719"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05933-9_40"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.11.024"},{"key":"ref17","first-page":"2720","article-title":"Efficient object-level visual context modeling for multi-modal machine translation: Masking irrelevant objects helps grounding","author":"wang","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"key":"ref19","first-page":"10790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multi-modal sentiment analysis","author":"yu","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6769"},{"key":"ref4","first-page":"1524","article-title":"Named entity recognition in tweets: An experimental study","author":"ritter","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2994436"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4419"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21236\/ADA547371"},{"key":"ref8","first-page":"852","article-title":"Multi-modal named entity recognition for short social media posts","author":"moon","year":"0","journal-title":"Conf N Am Chapter Assoc Comput Linguist Human Language Technol"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"ref2","first-page":"145","article-title":"Bidirectional LSTM for named entity recognition in twitter messages","author":"limsopatham","year":"0","journal-title":"Proc 2nd Workshop Noisy User-Generated Text"},{"key":"ref9","first-page":"1990","article-title":"Visual attention model for name tagging in multi-modal social media","author":"lu","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981314"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.01.049"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992222"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107075"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/09944151.pdf?arnumber=9944151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:28:19Z","timestamp":1672082899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9944151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3221017","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}