{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:22Z","timestamp":1738128442180,"version":"3.33.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,8]]},"DOI":"10.1109\/vcip63160.2024.10849846","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:36:57Z","timestamp":1738003017000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Proposal-level Correction Guided by CLIP for Few-shot Object Detection"],"prefix":"10.1109","author":[{"given":"Ruihang","family":"Wang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Taijin","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Hefei","family":"Mei","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Heqian","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Lanxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref4","first-page":"28","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks[J]","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP56404.2022.10008820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11716"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"journal-title":"Frustratingly simple few-shot object detection[J]","year":"2020","author":"Wang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_27"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"ref14","first-page":"16570","article-title":"Few-shot object detection via association and discrimination[J]","volume":"34","author":"Cao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00943"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00325"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_34"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01384"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.103956"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision[C]","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision[C]","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref24","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision[C]","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref25","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation[J]","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","first-page":"10965","article-title":"Grounded language-image pretraining[C]","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref30","first-page":"30","article-title":"Attention is all you need[J]","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale[J]","year":"2020","author":"Dosovitskiy","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"}],"event":{"name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","start":{"date-parts":[[2024,12,8]]},"location":"Tokyo, Japan","end":{"date-parts":[[2024,12,11]]}},"container-title":["2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10849624\/10849781\/10849846.pdf?arnumber=10849846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:10:54Z","timestamp":1738044654000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849846\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/vcip63160.2024.10849846","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]}}}