{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:32:11Z","timestamp":1776843131527,"version":"3.51.2"},"reference-count":20,"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\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005046","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\/icassp48485.2024.10446146","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6740-6744","source":"Crossref","is-referenced-by-count":5,"title":["PECR:Parameter-Efficient Transfer Learning with Cross-Modal Representation Learning for Remote Sensing Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Pengfei","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlong","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenjun","family":"Zhong","sequence":"additional","affiliation":[{"name":"Monash University,Monash Biomedical Imaging,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3173811"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3237606"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10281674"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3192460"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Li"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"ref12","article-title":"Pefomed: Parameter efficient fine-tuning on multimodal large language models for medical visual question answering","author":"He","year":"2024"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref14","article-title":"St-adapter: Parameter-efficient imageto-video transfer learning for action recognition","volume":"abs\/2206.13559","author":"Pan","year":"2022","journal-title":"CoRR"},{"key":"ref15","article-title":"Advancing plain vision transformer towards remote sensing foundation model","volume":"abs\/2208.03987","author":"Wang","year":"2022","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref18","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref19","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10446146.pdf?arnumber=10446146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:50:32Z","timestamp":1746467432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446146","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}