{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:49Z","timestamp":1774419709353,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889528","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["RFEM: Remote Feature Enhancement Module for Target Detection"],"prefix":"10.1109","author":[{"given":"Feng","family":"Hu","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,College of Automation and College of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuangye","family":"Wang","sequence":"additional","affiliation":[{"name":"Stage Grid Bengbu Power,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xiong","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,College of Automation and College of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhua","family":"Zhang","sequence":"additional","affiliation":[{"name":"MIGU Co., Ltd,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haolun","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,College of Automation and College of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Gao","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,College of Automation and College of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3180737"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108438"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03540-x"},{"key":"ref6","article-title":"Docde-shadower: Frequency-aware transformer for document shadow removal","author":"Luo","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00740"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25214"},{"key":"ref9","first-page":"12 116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Raghu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref16","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref19","article-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref20","article-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref22","article-title":"Yolov10: Real-time end-to-end object detection","author":"Wang","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/s23167190"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00468"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00754"},{"key":"ref31","article-title":"Deformable detr: Deformable transformers for end-to-end object detection. arxiv 2020","author":"Zhu","year":"2010"},{"key":"ref32","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00093"},{"key":"ref36","article-title":"Sparse detr: Efficient end-to-end object detection with learnable sparsity","author":"Roh","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.204"},{"key":"ref38","article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref43","first-page":"22 690","article-title":"Vision transformer with super token sampling","volume-title":"Proc. IEEE Conf. Comput. Vision Pattern Recognit. (CVPR)","author":"Huang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746134"},{"key":"ref45","article-title":"Crowdhuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889528.pdf?arnumber=10889528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:14Z","timestamp":1774416254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889528","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}