{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T18:10:02Z","timestamp":1748542202127,"version":"3.41.0"},"reference-count":60,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271281","62441235"],"award-info":[{"award-number":["62271281","62441235"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557700","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:59:13Z","timestamp":1743710353000},"page":"3023-3033","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Modality Prompts: Few-Shot Multi-Label Recognition With Single-Label Training"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2362-6802","authenticated-orcid":false,"given":"Zixuan","family":"Ding","sequence":"first","affiliation":[{"name":"State Key Laboratory of Electromechanical Integrated Manufacturing of High-Performance Electronic Equipments, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3658-1002","authenticated-orcid":false,"given":"Zihan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4180-5801","authenticated-orcid":false,"given":"Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1952-6083","authenticated-orcid":false,"given":"Tianxiang","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5233-9466","authenticated-orcid":false,"given":"Yizhe","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5843-6411","authenticated-orcid":false,"given":"Sicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2828-9905","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electromechanical Integrated Manufacturing of High-Performance Electronic Equipments, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref3","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref4","article-title":"A closer look at few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2019"},{"key":"ref5","article-title":"Self-supervised knowledge distillation for few-shot learning","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Rajasegaran","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02258"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346405"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00042"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20205"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref16","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref22","article-title":"P-tuning V2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Liu","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref27","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref31","article-title":"Adaptive cross-modal few-shot learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Xing","year":"2019"},{"key":"ref32","article-title":"Model-agnostic multitask fine-tuning for few-shot vision-language transfer learning","volume-title":"Proc. 1st Workshop Performance Interpretability Eval. Multimodal","author":"Wang","year":"2022"},{"key":"ref33","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Vinyals","year":"2016"},{"key":"ref34","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Tsimpoukelli","year":"2021"},{"key":"ref35","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17047"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2763441"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00034"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01345"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3025814"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00010"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_35"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107935"},{"article-title":"Differentiable prompt makes pre-trained language models better few-shot learners","year":"2021","author":"Zhang","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463641"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00832"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00053"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref51","first-page":"719","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Oreshkin","year":"2018"},{"key":"ref52","article-title":"Subspace regularizers for few-shot class incremental learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Akyrek","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413890"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432099"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3365104"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00270"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2400250"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115815"},{"key":"ref59","article-title":"Learning to propagate labels: Transductive propagation network for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2019"},{"key":"ref60","article-title":"Few-shot learning with graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Satorras","year":"2018"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10948337.pdf?arnumber=10948337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:54Z","timestamp":1748539854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557700","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}