{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:15:55Z","timestamp":1773843355390,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","award":["HR20C0021"],"award-info":[{"award-number":["HR20C0021"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003693","name":"Korea Institute of Science and Technology","doi-asserted-by":"publisher","award":["421025-04"],"award-info":[{"award-number":["421025-04"]}],"id":[{"id":"10.13039\/501100003693","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Neubla"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3293532","type":"journal-article","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T19:29:04Z","timestamp":1689017344000},"page":"78623-78643","source":"Crossref","is-referenced-by-count":13,"title":["Recurrent DETR: Transformer-Based Object Detection for Crowded Scenes"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2090-9273","authenticated-orcid":false,"given":"Hyeong Kyu","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong Keun","family":"Paik","sequence":"additional","affiliation":[{"name":"Samsung Electro-Mechanics, Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun Woo","family":"Ko","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8575-085X","authenticated-orcid":false,"given":"Min-Chul","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2181-9264","authenticated-orcid":false,"given":"Hyunwoo J.","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref12","first-page":"1","article-title":"An image is worth 16 × 16 words: Transformers for image recognition at scale","author":"kolesnikov","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref15","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"chu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref52","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"bochkovskiy","year":"2020","journal-title":"arXiv 2004 10934"},{"key":"ref11","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"shao","year":"2018","journal-title":"arXiv 1805 00123"},{"key":"ref10","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","author":"jaegle","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","volume":"139","author":"d\u2019ascoli","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref51","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref46","first-page":"1","article-title":"Universal transformers","author":"dehghani","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","first-page":"2363","article-title":"Deciding how to decide: Dynamic routing in artificial neural networks","volume":"70","author":"mcgill","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref48","article-title":"AdaViT: Adaptive tokens for efficient vision transformer","author":"yin","year":"2021","journal-title":"arXiv 2112 07658"},{"key":"ref47","first-page":"1","article-title":"PonderNet: Learning to ponder","author":"banino","year":"2021","journal-title":"Proc 8th ICML Workshop Automated Mach Learn (AutoML)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy12092023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCE55724.2022.10046623"},{"key":"ref44","article-title":"Adaptive computation time for recurrent neural networks","author":"graves","year":"2016","journal-title":"arXiv 1603 08983"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-222954"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.255"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","first-page":"1","article-title":"Sparse DETR: Efficient end-to-end object detection with learnable sparsity","author":"roh","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/s22197224"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01223"},{"key":"ref34","first-page":"14138","article-title":"Nyströmformer: A nyström-based algorithm for approximating self-attention","author":"xiong","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00093"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73973-7_33"},{"key":"ref31","first-page":"1","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00109"},{"key":"ref33","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume":"139","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"1","article-title":"Lite transformer with long-short range attention","author":"wu","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3825532"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/s22134833"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref23","article-title":"Efficient DETR: Improving end-to-end object detector with dense prior","author":"yao","year":"2021","journal-title":"arXiv 2104 01318"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00297"},{"key":"ref20","article-title":"NMS strikes back","author":"ouyang-zhang","year":"2022","journal-title":"arXiv 2212 06137"},{"key":"ref22","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref21","first-page":"1","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"zhang","year":"2022","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10177153.pdf?arnumber=10177153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:04:27Z","timestamp":1692641067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10177153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3293532","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}