{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:52:44Z","timestamp":1740102764260,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447040","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4975-4979","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Aided Learning Framework for Image Classification with Limited Training Images"],"prefix":"10.1109","author":[{"given":"Qi","family":"Wu","sequence":"first","affiliation":[{"name":"School Of Computer Science Aed Engineering-Sun Yat-sen University,China"}]},{"given":"Chengjia","family":"Wang","sequence":"additional","affiliation":[{"name":"Heriot-Watt University,School of Mathematical and Computer Sciences,UK"}]},{"given":"Xiaohui","family":"Li","sequence":"additional","affiliation":[{"name":"School Of Computer Science Aed Engineering-Sun Yat-sen University,China"}]},{"given":"Guangxing","family":"Wu","sequence":"additional","affiliation":[{"name":"School Of Computer Science Aed Engineering-Sun Yat-sen University,China"}]},{"given":"Marta","family":"Vallejo","sequence":"additional","affiliation":[{"name":"Heriot-Watt University,School of Mathematical and Computer Sciences,UK"}]},{"given":"Ruixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School Of Computer Science Aed Engineering-Sun Yat-sen University,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","key":"ref2"},{"article-title":"Training language models to follow instructions with human feedback","volume-title":"NeurlPS","author":"Ouyang","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-bioeng071516-044442"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.03.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-022-00793-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"article-title":"Prototypical networks for few-shot learning","volume-title":"NeurlPS","author":"Snell","key":"ref9"},{"article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"ICML","author":"Finn","key":"ref10"},{"article-title":"A closer look at few-shot classification","volume-title":"ICLR","author":"Chen","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00781"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"article-title":"Multimodal learning: A survey and taxonomy","volume-title":"PAMI","author":"Zhang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"article-title":"Hubert: How good can speech recognition be if we train on large audio datasets?","year":"2021","author":"Liu","key":"ref17"},{"article-title":"The Caltech-UCSD birds200-2011 dataset","volume-title":"CVPR","author":"Wah","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_13"},{"article-title":"Skin lesion analysis toward melanoma detection: A challenge at the 2019 international symposium on biomedical imaging","volume-title":"ISBI","author":"Codella","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447040.pdf?arnumber=10447040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:28:54Z","timestamp":1722576534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447040","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}