{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T07:11:32Z","timestamp":1771657892400,"version":"3.50.1"},"reference-count":56,"publisher":"Zhejiang University Press","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front Inform Technol Electron Eng"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1631\/fitee.2500429","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T09:59:38Z","timestamp":1766483978000},"page":"2623-2637","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GMCoT: a graph-augmented multimodal chain-of-thought reasoning framework for multi-label zero-shot learning"],"prefix":"10.1631","volume":"26","author":[{"given":"Xiang","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haobo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7483-0045","authenticated-orcid":false,"given":"Gang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"635","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2015.2487986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw60793.2023.00505"},{"key":"ref3","volume-title":"Sketch-of-thought: efficient LLM reasoning with adaptive cognitive-inspired sketching","author":"Aytes","year":"2025"},{"key":"ref4","volume-title":"The landmark selection method for multiple output prediction","author":"Balasubramanian","year":"2012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00068"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.575"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.376"},{"key":"ref8","first-page":"1529","article-title":"Feature-aware label space dimension reduction for multi-label classification","author":"Chen","year":"2012","journal-title":"Proc 26th Int Conf on Neural Information Processing Systems"},{"key":"ref9","volume-title":"See, think, confirm: interactive prompting between vision and language models for knowledge-based visual reasoning","author":"Chen","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00532"},{"key":"ref11","volume-title":"MlTr: multi-label classification with Transformer","author":"Cheng","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_4"},{"key":"ref14","volume-title":"Transductive multiclass and multi-label zero-shot learning","author":"Fu","year":"2015"},{"key":"ref15","volume-title":"Deep convolutional ranking for multilabel image annotation","author":"Gong","year":"2014"},{"key":"ref16","volume-title":"Generative multilabel zero-shot learning","author":"Gupta","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.323"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00880"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01157"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2009.5206594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2013.140"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01621"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00170"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.325"},{"key":"ref28","first-page":"5184","article-title":"Improving multi-label classification with missing labels by learning visual and semantic embeddings","author":"Li","year":"2017","journal-title":"Proc IEEE Conf on Computer Vision and Pattern Recognition"},{"key":"ref29","volume-title":"Query2Label: a simple Transformer way to multi-label classification","author":"Liu","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02324"},{"key":"ref31","volume-title":"The more you know: using knowledge graphs for image classification","author":"Marino","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2014.313"},{"key":"ref33","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013","journal-title":"Proc 27th Int Conf on Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44851-9_28"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00861"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5256-5"},{"key":"ref37","volume-title":"Multi-instance visualsemantic embedding","author":"Ren","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00012"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00320"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_17"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-59904-951-9.ch006"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.251"},{"key":"ref45","volume-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022"},{"key":"ref46","volume-title":"CNN: single-label to multi-label","author":"Wei","year":"2014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.328"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3531452"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096726"},{"key":"ref50","author":"Yao","year":"2023","journal-title":"Thinking like an expert: multimodal hypergraph-of-thought (HoT) reasoning to boost foundation modals"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10769"},{"key":"ref52","volume-title":"CoCoT: contrastive chain-of-thought prompting for large multimodal models with multiple image inputs","author":"Zhang","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2006.162"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.644"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.474"},{"key":"ref56","volume-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2023"}],"container-title":["Frontiers of Information Technology & Electronic Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2500429.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1631\/FITEE.2500429","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2500429.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:40:25Z","timestamp":1771656025000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1631\/FITEE.2500429"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":56,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2145"],"URL":"https:\/\/doi.org\/10.1631\/fitee.2500429","relation":{},"ISSN":["2095-9184","2095-9230"],"issn-type":[{"value":"2095-9184","type":"print"},{"value":"2095-9230","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"23 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All the authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}