{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T19:44:36Z","timestamp":1793130276860,"version":"4.5.0"},"reference-count":121,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"RIE2020 Industry Alignment Fund\u2013Industry Collaboration Projects (IAF-ICP) Funding Initiative, as well as cash and in-kind contribution from the industry partne"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tcsvt.2024.3480691","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T13:27:53Z","timestamp":1728912473000},"page":"988-1008","source":"Crossref","is-referenced-by-count":42,"title":["Open World Object Detection: A Survey"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5871-2316","authenticated-orcid":false,"given":"Yiming","family":"Li","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8659-4724","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, SAR, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Continental-NTU Corporate Laboratory, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingbing","family":"Li","sequence":"additional","affiliation":[{"name":"Continental Automotive Singapore Pte. Ltd., Boon Keng Rd, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1933-4986","authenticated-orcid":false,"given":"Kim-Hui","family":"Yap","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref2","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_23"},{"key":"ref4","article-title":"Evidential detection and tracking collaboration: New problem, benchmark and algorithm for robust anti-UAV system","author":"Zhu","year":"2023","journal-title":"arXiv:2306.15767"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1159\/000407340"},{"key":"ref6","volume-title":"Why? What Makes Us Curious","author":"Livio","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.17763\/haer.81.4.h054131316473115"},{"key":"ref8","volume-title":"A Curious Mind: The Secret to a Bigger Life","author":"Grazer","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3552458.3556453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01885"},{"key":"ref14","article-title":"Addressing the challenges of open-world object detection","author":"Pershouse","year":"2023","journal-title":"arXiv:2303.14930"},{"key":"ref15","article-title":"Detecting the open-world objects with the help of the brain","author":"Ma","year":"2023","journal-title":"arXiv:2303.11623"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00573"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00414"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.368"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.09.030"},{"key":"ref22","article-title":"RODEO: Replay for online object detection","author":"Acharya","year":"2020","journal-title":"arXiv:2008.06439"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3124133"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_12"},{"key":"ref26","article-title":"Open-world object detection via discriminative class prototype learning","author":"Yu","year":"2023","journal-title":"arXiv:2302.11757"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3124952"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870832"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2981604"},{"key":"ref33","article-title":"A survey on few-shot class-incremental learning","author":"Tian","year":"2023","journal-title":"arXiv:2304.08130"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019801"},{"key":"ref35","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref38","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the 36th Int. Conf. Mach. Learn. (ICML)","volume":"97","author":"Tan"},{"key":"ref39","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1177352.1177355"},{"issue":"11","key":"ref42","first-page":"622","article-title":"A survey on object detection, classification and tracking methods","volume":"3","author":"Ragland","year":"2014","journal-title":"Int. J. Eng. Res. Technol"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref46","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Krizhevsky"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref55","first-page":"360","article-title":"SNIPER: Efficient multi-scale training","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Singh"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Zhu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"ref59","first-page":"6877","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zheng"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2613924"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2707495"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976236.18"},{"key":"ref66","first-page":"466","article-title":"Open set text classification using CNNs","volume-title":"Proc. 14th Int. Conf. Natural Lang. Process. (ICON)","author":"Prakhya"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1314"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7965897"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00241"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.42"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/469"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2978199"},{"key":"ref73","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"Liang","year":"2017","journal-title":"arXiv:1706.02690"},{"key":"ref74","first-page":"23631","article-title":"Mitigating neural network overconfidence with logit normalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei"},{"key":"ref75","article-title":"Deep anomaly detection with outlier exposure","author":"Hendrycks","year":"2018","journal-title":"arXiv:1812.04606"},{"key":"ref76","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Lee"},{"key":"ref77","first-page":"20827","article-title":"Out-of-distribution detection with deep nearest neighbors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/WTS.2018.8363930"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_22"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.148"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref86","first-page":"6470","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lopez-Paz"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363317"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01386"},{"key":"ref89","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01368"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00083"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref93","article-title":"Investigating the role of attribute context in vision-language models for object recognition and detection","author":"Buettner","year":"2023","journal-title":"arXiv:2303.10093"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref95","first-page":"36067","article-title":"GLIPv2: Unifying localization and vision-language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref98","first-page":"15946","article-title":"Multi-modal classifiers for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kaul"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref105","article-title":"F-VLM: Open-vocabulary object detection upon frozen vision and language models","author":"Kuo","year":"2022","journal-title":"arXiv:2209.15639"},{"key":"ref106","volume-title":"Fast OWDETR: Transformer for open world object detection","author":"Chen","year":"2022"},{"key":"ref107","article-title":"Open world DETR: Transformer based open world object detection","author":"Dong","year":"2022","journal-title":"arXiv:2212.02969"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146922"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01331"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00315"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01102"},{"key":"ref113","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","volume":"48","author":"Xie"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref115","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460700"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3322465"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02252"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10885778\/10716705.pdf?arnumber=10716705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T15:47:15Z","timestamp":1740066435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10716705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":121,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3480691","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}