{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:57:03Z","timestamp":1763060223666,"version":"3.45.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3607812","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:33:09Z","timestamp":1757439189000},"page":"8618-8627","source":"Crossref","is-referenced-by-count":0,"title":["Boosting Long-Tailed Recognition With Label Descriptor and Beyond"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4620-9187","authenticated-orcid":false,"given":"Zhengzhuo","family":"Xu","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruikang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3709-4947","authenticated-orcid":false,"given":"Zenghao","family":"Chai","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyan","family":"Qi","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4514-3617","authenticated-orcid":false,"given":"Lei","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-476X","authenticated-orcid":false,"given":"Haiqin","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3590-6676","authenticated-orcid":false,"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3106096"},{"key":"ref3","first-page":"7139","article-title":"Towards calibrated model for long-tailed visual recognition from prior perspective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3179902"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2701645"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"ref7","first-page":"1","article-title":"Long-tail learning via logit adjustment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Menon","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120642"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref11","first-page":"1","article-title":"Filip: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2021"},{"key":"ref12","first-page":"1","article-title":"Visual classification via description from large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Menon","year":"2023"},{"key":"ref13","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref14"},{"key":"ref15","first-page":"1","article-title":"LPT: Long-tailed prompt tuning for image classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dong","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01868-w"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_5"},{"article-title":"A simple long-tailed recognition baseline via vision-language model","year":"2021","author":"Ma","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00075"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01516"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00682"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref26","first-page":"1565","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Adv. Conf. Neural Inf. Process. Syst.","author":"Cao","year":"2019"},{"key":"ref27","first-page":"1","article-title":"Decoupling representation and classifier for long-tailed recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kang","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16458"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref31","first-page":"1513","article-title":"Long-tailed classification by keeping the good and removing the bad momentum causal effect","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2966863"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_41"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00517"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00676"},{"key":"ref36","first-page":"1","article-title":"Long-tailed recognition by routing diverse distribution-aware experts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02269"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3314980"},{"key":"ref39","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref40","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref42","first-page":"16795","article-title":"Conditional prompt learning for vision-language models","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kaiyang","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref44","first-page":"26342","article-title":"Chils: Zero-shot image classification with hierarchical label sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Novack","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00042"},{"key":"ref48","first-page":"34077","article-title":"Self-supervised aggregation of diverse experts for test-agnostic long-tailed recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20258"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref56","first-page":"1","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00678"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_3"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_11"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3181789"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11154136.pdf?arnumber=11154136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:45:01Z","timestamp":1763059501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11154136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3607812","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}