{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T05:01:16Z","timestamp":1785214876893,"version":"3.55.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":"crossref","award":["62176030"],"award-info":[{"award-number":["62176030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Projects of the Special Program for Technological Innovation and Applied Development in Chongqing Municipality","award":["CSTB2023TIAD-KPX0060"],"award-info":[{"award-number":["CSTB2023TIAD-KPX0060"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3709489","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T19:05:45Z","timestamp":1784747145000},"page":"7871-7882","source":"Crossref","is-referenced-by-count":0,"title":["HDG-CLIP: Hierarchical Dual-Granularity Vision-Semantic Alignment for Open-Vocabulary Multi-Label Image Classification"],"prefix":"10.1109","volume":"35","author":[{"given":"Beiyan","family":"Liu","sequence":"first","affiliation":[{"name":"Chongqing University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5610-0826","authenticated-orcid":false,"given":"Sheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Chongqing University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8678-2271","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobin","family":"Huang","sequence":"additional","affiliation":[{"name":"Chongqing University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8126-8126","authenticated-orcid":false,"given":"Nankun","family":"Mu","sequence":"additional","affiliation":[{"name":"Chongqing University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"Norouzi","year":"2013","journal-title":"arXiv:1312.5650"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref5","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref6","first-page":"808","article-title":"Open-vocabulary multi-label classification via multi-modal knowledge transfer","volume-title":"Proc. AAAI Conf. Artif. Intell","author":"He"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref9","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn","volume":"139","author":"Jia"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01408"},{"issue":"4","key":"ref12","first-page":"3513","article-title":"TagCLIP: A local-to-global framework to enhance open-vocabulary multi-label classification of clip without training","volume-title":"Proc. AAAI Conf. Artif. Intell","volume":"38","author":"Lin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref14","article-title":"Query2Label: A simple transformer way to multi-label classification","author":"Liu","year":"2021","journal-title":"arXiv:2107.10834"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3609185"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3128054"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16472"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34298"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266161"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01345"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/208"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3546356"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3457610"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3550003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3619343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS56072.2025.11043366"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3420083"},{"key":"ref33","article-title":"CalFuse: Multi-modal continual learning via feature calibration and parameter fusion","author":"Guo","year":"2025","journal-title":"arXiv:2503.18672"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02722"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00880"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00861"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02285"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3459589"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3485518"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00438"},{"key":"ref46","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3295772"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34098"},{"key":"ref52","article-title":"Category-adaptive cross-modal semantic refinement and transfer for open-vocabulary multi-label recognition","author":"Liu","year":"2024","journal-title":"arXiv:2412.06190"},{"issue":"4","key":"ref53","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1016\/j.jcss.2004.10.006","article-title":"Performance guarantees for hierarchical clustering","volume":"70","author":"Dasgupta","year":"2005","journal-title":"J. Comput. Syst. Sci."},{"key":"ref54","first-page":"1","article-title":"On spectral clustering: Analysis and an algorithm","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"14","author":"Ng"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.ins.2022.11.139","article-title":"K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data","volume":"622","author":"Ikotun","year":"2023","journal-title":"Inf. Sci."},{"key":"ref56","first-page":"2006","article-title":"k-means++: The advantages of careful seeding","volume-title":"Stanford InfoLab","author":"Arthur","year":"2006"},{"key":"ref57","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11616587.pdf?arnumber=11616587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:42:46Z","timestamp":1785213766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11616587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3709489","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}