{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T21:35:09Z","timestamp":1773264909478,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"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":[[2025,11,12]]},"DOI":"10.1109\/icdmw69685.2025.00054","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:50:39Z","timestamp":1773172239000},"page":"421-430","source":"Crossref","is-referenced-by-count":0,"title":["OTTER: Open-Tagging via Text-Image Representation for Multi-Modal Understanding"],"prefix":"10.1109","author":[{"given":"Jieer","family":"Ouyang","sequence":"first","affiliation":[{"name":"Huawei Singapore Research Center,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoneng","family":"Xiang","sequence":"additional","affiliation":[{"name":"Huawei Singapore Research Center,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Singapore Research Center,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangkai","family":"Ding","sequence":"additional","affiliation":[{"name":"Huawei Singapore Research Center,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-9423-3_26"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-021-09159-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_59"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.37"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3088605"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_39"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3561581"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref13","article-title":"What do you see? enhancing zero-shot image classification with multimodal large language models","author":"Abdelhamed","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref15","article-title":"Open vocabulary multi-label classification with dual-modal decoder on aligned visual-textual features","author":"Xu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00505"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.644"},{"key":"ref19","article-title":"Bilinear attention networks","volume":"31","author":"Kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"Norouzi","year":"2013","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/1463922X.2023.2166623"},{"key":"ref22","article-title":"Multimodal multilabel classification by clip","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPTA62886.2024.10755555"},{"key":"ref25","article-title":"Medtrinity-25m: A largescale multimodal dataset with multigranular annotations for medicine","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref27","author":"DosovitskiyA","year":"2010","journal-title":"Animageis worth 16+ 16words: Transformersforimagerecognitionat scale"},{"key":"ref28","article-title":"Siglip 2: Multilingual visionlanguage encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint"},{"issue":"1","key":"ref29","first-page":"29","article-title":"Using tf-idf to determine word relevance in document queries","volume-title":"Proceedings of the first instructional conference on machine learning","volume":"242","author":"Ramos","year":"2003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/math12091349"},{"key":"ref31","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","location":"Washington, DC, USA","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,15]]}},"container-title":["2025 IEEE International Conference on Data Mining Workshops (ICDMW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11415623\/11415713\/11415990.pdf?arnumber=11415990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T05:32:26Z","timestamp":1773207146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11415990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icdmw69685.2025.00054","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}