{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:53:24Z","timestamp":1771923204517,"version":"3.50.1"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccvw69036.2025.00570","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"5449-5459","source":"Crossref","is-referenced-by-count":0,"title":["Online 3D Multi-Camera Perception Through Robust 2D Tracking and Depth-Based Late Aggregation"],"prefix":"10.1109","author":[{"given":"Vu-Minh","family":"Le","sequence":"first","affiliation":[{"name":"Optoelectronics Center, Viettel Aerospace Institute, Viettel Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thao-Anh","family":"Tran","sequence":"additional","affiliation":[{"name":"Optoelectronics Center, Viettel Aerospace Institute, Viettel Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duc Huy","family":"Do","sequence":"additional","affiliation":[{"name":"Optoelectronics Center, Viettel Aerospace Institute, Viettel Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan Canh","family":"Do","sequence":"additional","affiliation":[{"name":"University of Engineering and Technology, Vietnam National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huong","family":"Ninh","sequence":"additional","affiliation":[{"name":"Optoelectronics Center, Viettel Aerospace Institute, Viettel Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Engineering and Technology, Vietnam National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00922"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00715"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.595"},{"key":"ref11","author":"Ge","year":"2021","journal-title":"Yolox: Exceeding yolo series in 2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00552"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6638-5"},{"key":"ref16","article-title":"Rtmpose: Real-time multi-person pose estimation based on mmpose","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","author":"Jocher","year":"2024","journal-title":"Ultralytics yolo11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00577"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00714"},{"key":"ref20","first-page":"12697","article-title":"Pointpillars: Fast encoders for object detection from point clouds","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Alex","year":"2019"},{"key":"ref21","volume-title":"xformers: A modular and hackable transformer modelling library","author":"Lefaudeux","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3515454"},{"key":"ref28","author":"Liao","year":"2024","journal-title":"Monodetrnext: Next-generation accurate and efficient monocular 3d object detector"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01375-2"},{"key":"ref33","author":"Lv","year":"2024","journal-title":"Rt-detr: Real-time detection transformer with efficient hybrid encoder"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222576"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00866"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00581"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref38","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref40","first-page":"28","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00208"},{"key":"ref42","author":"Somers","year":"2025","journal-title":"Cameltrack: Context-aware multi-cue exploitation for online multi-object tracking"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00719"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909670"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00579"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00018"},{"key":"ref47","author":"Tran","year":"2024","journal-title":"Advancing thermal multi-object tracking with attention and metric fusion"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref51","article-title":"Db-scan: Optimal rates for density based clustering","author":"Wang","year":"2017","journal-title":"arXiv: Statistics Theory"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00722"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00864"},{"key":"ref55","article-title":"Bev-sushi: Multi-target multi-camera 3d detection and tracking in bird\u2019s-eye view","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179319"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00694"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00697"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00374"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00710"},{"key":"ref62","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref67","article-title":"Multi-target, multi-camera tracking by hierarchical clustering: Recent progress on dukemtmc project","author":"Zhang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref68","author":"Zhou","year":"2019","journal-title":"Objects as points"},{"key":"ref69","author":"Zhu","year":"2020","journal-title":"Deformable detr: Deformable transformers for end-to-end object detection"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11375803.pdf?arnumber=11375803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:48:24Z","timestamp":1771919304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00570","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}