{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T18:40:01Z","timestamp":1746470401867,"version":"3.40.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100009962","name":"Shanghai Municipal Science and Technology Major","doi-asserted-by":"publisher","award":["2021SHZDZX0102","BI5310001\/001"],"award-info":[{"award-number":["2021SHZDZX0102","BI5310001\/001"]}],"id":[{"id":"10.13039\/501100009962","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3557947","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T20:35:43Z","timestamp":1743798943000},"page":"73773-73784","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Packaging Line Object Counting by Cross-Frame Association With Wavelet Convolutions and Trajectory Compensation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9575-3755","authenticated-orcid":false,"given":"Longxuan","family":"Wei","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4727-4281","authenticated-orcid":false,"given":"Yutao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Qian","sequence":"additional","affiliation":[{"name":"Sihua Information Technology, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zuo","sequence":"additional","affiliation":[{"name":"National Technology Innovation Center of China, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhouhan","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9639-7679","authenticated-orcid":false,"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Roboflow Annotate: The Fastest Way To Label Computer Vision Datasets","year":"2024","key":"ref1"},{"key":"ref2","article-title":"BoT-SORT: Robust associations multi-pedestrian tracking","author":"Aharon","year":"2022","journal-title":"arXiv:2206.14651"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.07155"},{"key":"ref9","article-title":"YOLO-MS: Rethinking multi-scale representation learning for real-time object detection","author":"Chen","year":"2023","journal-title":"arXiv:2308.05480"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00485"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_21"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref15","first-page":"1","article-title":"As large as it gets-studying infinitely large convolutions via neural implicit frequency filters","volume":"2024","author":"Grabinski","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.148"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref19","article-title":"Bench2Drive: Towards multi-ability benchmarking of closed-loop end-to-end autonomous driving","author":"Jia","year":"2024","journal-title":"arXiv:2406.03877"},{"article-title":"Ultralytics yolov5","year":"2020","author":"Jocher","key":"ref20"},{"article-title":"Ultralytics yolov8","year":"2023","author":"Jocher","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/nav.20053"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.02976"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01583"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","year":"2020","author":"Michaelis","key":"ref31"},{"key":"ref32","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016","journal-title":"arXiv:1603.00831"},{"key":"ref33","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"arXiv:1906.07155"},{"volume-title":"Darknet: Open Source Neural Networks in C","year":"2013","author":"Redmon","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref36","article-title":"PointOBB-v2: Towards simpler, faster, and stronger single point supervised oriented object detection","author":"Ren","year":"2024","journal-title":"arXiv:2410.08210"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref39","article-title":"Multi-object tracking with Siamese track-RCNN","author":"Shuai","year":"2020","journal-title":"arXiv:2004.07786"},{"key":"ref40","article-title":"YOLOv10: Real-time end-to-end object detection","author":"Wang","year":"2024","journal-title":"arXiv:2405.14458"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref45","first-page":"1","article-title":"PatchDCT: Patch refinement for high quality instance segmentation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wen"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_40"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01593-w"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16426"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3166956"},{"key":"ref52","first-page":"11830","article-title":"Rethinking rotated object detection with Gaussian Wasserstein distance loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00832"},{"key":"ref54","first-page":"18381","article-title":"Learning high-precision bounding box for rotated object detection via Kullback\u2013Leibler divergence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref55","first-page":"1","article-title":"H2RBox: Horizontal box annotation is all you need for oriented object detection","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3197152"},{"key":"ref57","article-title":"Bench2Drive-R: Turning real world data into reactive closed-loop autonomous driving benchmark by generative model","author":"You","year":"2024","journal-title":"arXiv:2412.09647"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01588"},{"key":"ref60","first-page":"1","article-title":"H2RBox-v2: Incorporating symmetry for boosting horizontal box supervised oriented object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref62","first-page":"1","article-title":"E2e-mfd: Towards end-to-end synchronous multimodal fusion detection","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548541"},{"key":"ref67","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10949074.pdf?arnumber=10949074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:58:47Z","timestamp":1746467927000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10949074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3557947","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}