{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:21:10Z","timestamp":1775229670336,"version":"3.50.1"},"reference-count":80,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3596215","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:01:44Z","timestamp":1754503304000},"page":"138622-138639","source":"Crossref","is-referenced-by-count":1,"title":["Improving Token-Based Object Detection With Video"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5624-8377","authenticated-orcid":false,"given":"Abhineet","family":"Singh","sequence":"first","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7588-5400","authenticated-orcid":false,"given":"Nilanjan","family":"Ray","sequence":"additional","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pix2seq: A language modeling framework for object detection","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref2","volume-title":"P2S-Video: Extension of Pix2Seq for Video Detection and Segmentation","author":"Singh"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.02325"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref15","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref17","volume-title":"Ultralytics\/YOLOv5: V5.0-YOLOv5-P6 1280 Models, AWS, Supervise.ly and YouTube Integrations","author":"Jocher","year":"2021"},{"key":"ref18","first-page":"7464","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Wang"},{"key":"ref19","author":"Jocher","year":"2023","journal-title":"UltralyticsYOLOv8: A computer vision model architecture for detection, classification, segmentation, and more"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/make5040083"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078516"},{"key":"ref25","volume-title":"Pix2Seq Codebase: Multi-tasks With Generative Modeling (Autoregressive and Diffusion)","author":"Chen"},{"key":"ref26","article-title":"A unified sequence interface for vision tasks","volume-title":"Proc. 36th Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Chen"},{"key":"ref27","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.561"},{"key":"ref35","article-title":"Elucidating image-to-set prediction: An analysis of models, losses and datasets","author":"Pineda","year":"2019","journal-title":"arXiv:1904.05709"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00833"},{"key":"ref37","first-page":"2494","article-title":"Obj2Seq: Formatting objects as sequences with class prompt for visual tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref39","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref40","first-page":"26295","article-title":"UViM: A unified modeling approach for vision with learned guiding codes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kolesnikov"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01822"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2222"},{"key":"ref43","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref44","article-title":"Large language models: A survey","author":"Minaee","year":"2024","journal-title":"arXiv:2402.06196"},{"key":"ref45","article-title":"Improving language understanding by generative pre-training","volume-title":"Tech. Rep.","author":"Radford","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3184031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_42"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"ref49","first-page":"13388","article-title":"Identity-consistent aggregation for video object detection","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Deng"},{"issue":"6","key":"ref50","first-page":"6559","article-title":"TGBFormer: Transformer-GraphFormer blender network for video object detection","volume-title":"Proc. AAAI Conf. Artif. Intell","volume":"39","author":"Qi"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3183646"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3164253"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"93453","DOI":"10.1109\/ACCESS.2022.3203399","article-title":"DAFA: Diversity-aware feature aggregation for attention-based video object detection","volume":"10","author":"Roh","year":"2022","journal-title":"IEEE Access"},{"issue":"12","key":"ref55","doi-asserted-by":"crossref","first-page":"8165","DOI":"10.1109\/TCSVT.2021.3094533","article-title":"Class-aware feature aggregation network for video object detection","volume":"32","author":"Han","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref56","article-title":"Spatio-temporal learnable proposals for end-to-end video object detection","volume-title":"Proc. Brit. Mach. Vis. Conf","author":"Hashmi"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19965"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341600"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25320"},{"key":"ref61","article-title":"Practical video object detection via feature selection and aggregation","author":"Shi","year":"2024","journal-title":"arXiv:2407.19650"},{"key":"ref62","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_18"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref65","volume-title":"Video Detection and Segmentation With Language Modeling","author":"Singh"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102907"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"390","DOI":"10.59275\/j.melba.2023-3d9d","article-title":"Towards early prediction of human iPSC reprogramming success","volume":"2","author":"Singh","year":"2023","journal-title":"Mach. Learn. Biomed. Imag."},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.95"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref70","first-page":"3192","article-title":"Video Swin transformer","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Liu"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref72","author":"Innat","year":"2024","journal-title":"Keras 3 Implementation of Video Swin Transformers for 3D Video Modeling"},{"key":"ref73","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref74","first-page":"1427","article-title":"Animal detection in man-made environments","volume-title":"Proc. IEEE Winter Conf. Appl. Comput. Vis. (WACV)","author":"Singh"},{"key":"ref75","volume-title":"Object Detection on UA-DETRAC"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412056"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639438"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2922479"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CRV50864.2020.00038"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.09.002"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11115031.pdf?arnumber=11115031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:48:44Z","timestamp":1755197324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11115031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3596215","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}