{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T10:37:10Z","timestamp":1769942230066,"version":"3.49.0"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:00:00Z","timestamp":1739318400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:00:00Z","timestamp":1739318400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s13735-025-00355-x","type":"journal-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T08:10:03Z","timestamp":1739347803000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Optimized RT-DETR for accurate and efficient video object detection via decoupled feature aggregation"],"prefix":"10.1007","volume":"14","author":[{"given":"Hao","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,12]]},"reference":[{"key":"355_CR1","doi-asserted-by":"crossref","unstructured":"Musat V, Fursa I, Newman p, Cuzzolin F, Bradley A (2021) Multiweather city: Adverse weather stacking for autonomous driving, in Proc. IEEE\/CVF Int. Conf. Comput. Vis. Workshops (ICCVW), pp 2906\u20132915","DOI":"10.1109\/ICCVW54120.2021.00325"},{"key":"355_CR2","doi-asserted-by":"publisher","first-page":"9069","DOI":"10.1109\/TIP.2021.3122293","volume":"30","author":"Y Cai","year":"2021","unstructured":"Cai Y, Dai L, Wang H, Li Z (2021) Multi-target pan-class intrinsic relevance driven model for improving semantic segmentation in autonomous driving. IEEE Trans Image Process 30:9069\u20139084. https:\/\/doi.org\/10.1109\/TIP.2021.3122293","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"355_CR3","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/TCYB.2014.2320493","volume":"45","author":"N Liu","year":"2015","unstructured":"Liu N, Wu H, Lin L (2015) Hierarchical ensemble of background models for PTZ-based video surveillance. IEEE Trans Cybern 45(1):89\u2013102. https:\/\/doi.org\/10.1109\/TCYB.2014.2320493","journal-title":"IEEE Trans Cybern"},{"key":"355_CR4","doi-asserted-by":"publisher","first-page":"8318","DOI":"10.1109\/TIP.2021.3114986","volume":"30","author":"Y Yang","year":"2021","unstructured":"Yang Y, Kim H, Choi H, Chae S, Kim I (2021) Scene adaptive online surveillance video synopsis via dynamic tube rearrangement using octree. IEEE Trans Image Process 30:8318\u20138331. https:\/\/doi.org\/10.1109\/TIP.2021.3114986","journal-title":"IEEE Trans Image Process"},{"issue":"4","key":"355_CR5","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TIP.2018.2882155","volume":"28","author":"G Wu","year":"2018","unstructured":"Wu G, Han J, Guo Y, Liu L, Ding G, Ni Q, Shao L (2018) Unsupervised deep video hashing via balanced code for large-scale video retrieval. IEEE Trans Image Process 28(4):1993\u20132007. https:\/\/doi.org\/10.1109\/TIP.2018.2882155","journal-title":"IEEE Trans Image Process"},{"key":"355_CR6","doi-asserted-by":"publisher","first-page":"2989","DOI":"10.1109\/TIP.2020.3048680","volume":"30","author":"M Qi","year":"2021","unstructured":"Qi M, Qin J, Yang Y, Wang Y, Luo J (2021) Semantics-aware spatial\u2013temporal binaries for cross-modal video retrieval. IEEE Trans Image Process 30:2989\u20133004. https:\/\/doi.org\/10.1109\/TIP.2020.3048680","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"355_CR7","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"issue":"6","key":"355_CR8","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"SQ Ren","year":"2017","unstructured":"Ren SQ, He K, Girshick R, Sun J (2017) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"355_CR9","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You Only Look Once: Unified, Real-Time Object Detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"355_CR10","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: Better, Faster, Stronger, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6517\u20136525","DOI":"10.1109\/CVPR.2017.690"},{"key":"355_CR11","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767"},{"key":"355_CR12","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"355_CR13","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, Li Y, Zhang B, Liang Y, Zhou L, Xu X, Chu X, Wei X, Wei X (2020) YOLOv6: a single-stage object detection framework for industrial applications. arXiv Preprint arXiv:2209.02976"},{"key":"355_CR14","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HYM (2023) YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"355_CR15","doi-asserted-by":"crossref","unstructured":"Wang CY, Yeh IH, Liao HYM (2024) YOLOv9: learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"355_CR16","doi-asserted-by":"publisher","first-page":"104613","DOI":"10.1016\/j.imavis.2022.104613","volume":"130","author":"DS Bacea","year":"2023","unstructured":"Bacea DS, Oniga F (2023) Single stage architecture for improved accuracy real-time object detection on mobile devices. Image Vis Comput 130:104613. https:\/\/doi.org\/10.1016\/j.imavis.2022.104613","journal-title":"Image Vis Comput"},{"key":"355_CR17","unstructured":"Wang CY, Yeh IH, Liao HYM (2021) You only learn one representation: unified network for multiple tasks. arXiv Preprint arXiv:2105.04206"},{"key":"355_CR18","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"355_CR19","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"issue":"1","key":"355_CR20","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2015","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2015) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38(1):142\u2013158. https:\/\/doi.org\/10.1109\/TPAMI.2015.2437384","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"355_CR21","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.procs.2021.02.031","volume":"183","author":"X Han","year":"2021","unstructured":"Han X, Chang J, Wang K (2021) Real-time object detection based on YOLO-v2 for tiny vehicle object. Procedia Comput Sci 183:61\u201372. https:\/\/doi.org\/10.1016\/j.procs.2021.02.031","journal-title":"Procedia Comput Sci"},{"key":"355_CR22","doi-asserted-by":"publisher","unstructured":"Narejo S, Pandey B, Esenarro VD (2021) Weapon detection using YOLO V3 for smart surveillance system. Math Probl Eng 19975700. https:\/\/doi.org\/10.1155\/2021\/9975700","DOI":"10.1155\/2021\/9975700"},{"key":"355_CR23","doi-asserted-by":"publisher","first-page":"107116","DOI":"10.1016\/j.compag.2022.107116","volume":"198","author":"C Chen","year":"2022","unstructured":"Chen C, Lu J, Zhou M (2022) A YOLOv3-based computer vision system for identification of tea buds and the picking point. Comput Electron Agric 198:107116. https:\/\/doi.org\/10.1016\/j.compag.2022.107116","journal-title":"Comput Electron Agric"},{"issue":"3","key":"355_CR24","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s13735-022-00239-4","volume":"11","author":"S Panigrahi","year":"2022","unstructured":"Panigrahi S, Raju USN (2022) InceptionDepth-wiseYOLOv2: improved implementation of YOLO framework for pedestrian detection. Int J Multimedia Inform Retr 11(3):409\u2013430. https:\/\/doi.org\/10.1007\/s13735-022-00239-4","journal-title":"Int J Multimedia Inform Retr"},{"issue":"2","key":"355_CR25","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s13735-023-00305-5","volume":"12","author":"Z Wen","year":"2023","unstructured":"Wen Z, Su J, Zhang Y, Li M, Gan G, Zhang S, Fan D (2023) A lightweight small object detection algorithm based on improved YOLOv5 for driving scenarios. Int J Multimedia Inform Retr 12(2):38. https:\/\/doi.org\/10.1007\/s13735-023-00305-5","journal-title":"Int J Multimedia Inform Retr"},{"key":"355_CR26","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430"},{"key":"355_CR27","unstructured":"Han W, Khorrami P, Paine TL, Ramachandran P, Babaeizadeh M, Shi H, Li J, Yan S, Huang TS (2016) Seq-nms for video object detection. arXiv Preprint arXiv:1602.08465"},{"key":"355_CR28","doi-asserted-by":"crossref","unstructured":"Belhassen H, Zhang H, Fresse V, Bourennane EB (2019) Improving video object detection by Seq-Bbox matching, VISIGRAPP, pp 226\u2013233","DOI":"10.5220\/0007260002260233"},{"key":"355_CR29","doi-asserted-by":"crossref","unstructured":"Sabater A, Montesano L, Murillo AC (2020) Robust and efficient post-processing for video object detection. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp 10536\u201310542","DOI":"10.1109\/IROS45743.2020.9341600"},{"key":"355_CR30","doi-asserted-by":"crossref","unstructured":"Wu H, Chen Y, Wang N, Zhang Z (2019) Sequence level semantics aggregation for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 9217\u20139225","DOI":"10.1109\/ICCV.2019.00931"},{"key":"355_CR31","doi-asserted-by":"crossref","unstructured":"Chen Y, Cao Y, Hu H, Wang L (2020) Memory enhanced global-local aggregation for video object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10337\u201310346","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"355_CR32","doi-asserted-by":"crossref","unstructured":"Deng J, Pan Y, Yao T, Zhou W, Li H, Mei T (2019) Relation distillation networks for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 7023\u20137032","DOI":"10.1109\/ICCV.2019.00712"},{"key":"355_CR33","doi-asserted-by":"crossref","unstructured":"Han M, Wang Y, Chang X, Qiao Y (2020) Mining inter-video proposal relations for video object detection. In: European Conference on Computer Vision, Springer, pp 431\u2013446","DOI":"10.1007\/978-3-030-58589-1_26"},{"key":"355_CR34","doi-asserted-by":"crossref","unstructured":"Sun G, Hua Y, Hu G, Robertson N (2021) Mamba: Multi-level aggregation via memory bank for video object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. 35(3): 2620\u20132627","DOI":"10.1609\/aaai.v35i3.16365"},{"key":"355_CR35","doi-asserted-by":"crossref","unstructured":"Wang H, Tang J, Liu X, Guan S, Xie R, Song L (2020) Ptseformer: Progressive temporal-spatial enhanced transformer towards video object detection. In: European Conference on Computer Vision, Springer, pp 732\u2013747","DOI":"10.1007\/978-3-031-20074-8_42"},{"key":"355_CR36","doi-asserted-by":"crossref","unstructured":"Shi Y, Wang N, Guo X (2023) YOLOV: Making still image object detectors great at video object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. 37(2): 2254\u20132262","DOI":"10.1609\/aaai.v37i2.25320"},{"key":"355_CR37","doi-asserted-by":"crossref","unstructured":"Zhu X, Xiong Y, Dai J, Yuan L, Wei Y (2017) Deep feature flow for video recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2349\u20132358","DOI":"10.1109\/CVPR.2017.441"},{"key":"355_CR38","doi-asserted-by":"crossref","unstructured":"Zhu X, Wang Y, Dai J, Yuan L, Wei Y (2017) Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 408\u2013417","DOI":"10.1109\/ICCV.2017.52"},{"key":"355_CR39","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv Preprint arXiv:1706.03762"},{"key":"355_CR40","doi-asserted-by":"publisher","first-page":"104615","DOI":"10.1016\/j.imavis.2022.104615","volume":"130","author":"H Liu","year":"2023","unstructured":"Liu H, You X, Wang T, Li Y (2023) Object detection via inner-inter relational reasoning network. Image Vis Comput 130:104615. https:\/\/doi.org\/10.1016\/j.imavis.2022.104615","journal-title":"Image Vis Comput"},{"key":"355_CR41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3328341","author":"SD Roh","year":"2023","unstructured":"Roh SD, Chung KS (2023) DiffusionVID: Denoising object boxes with Spatio-temporal conditioning for video object detection. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2023.3328341","journal-title":"IEEE Access"},{"key":"355_CR42","doi-asserted-by":"crossref","unstructured":"Zhao Y, Lv W, Xu S, Wei J, Wang G, Dang Q (2023) Detrs beat yolos on real-time object detection. arXiv Preprint arXiv:2304.08069","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"355_CR43","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Jian S (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"355_CR44","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"key":"355_CR45","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"355_CR46","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"355_CR47","first-page":"1","volume":"29","author":"J Dai","year":"2016","unstructured":"Dai J, Li Y, He K, Sun J (2016) R-fcn: object detection via region-based fully convolutional networks. Adv Neural Inf Proces Syst 29:1\u20139","journal-title":"Adv Neural Inf Proces Syst"},{"key":"355_CR48","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"issue":"9","key":"355_CR49","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916. https:\/\/doi.org\/10.1109\/TPAMI.2015.2389824","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"355_CR50","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Yang FC, Berg AC (2016) Ssd: Single shot multibox detector. In: European Conference on Computer Vision, Springer, 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"355_CR51","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: Fully convolutional one-stage object detection. arXiv preprint arXiv:1904.01355","DOI":"10.1109\/ICCV.2019.00972"},{"key":"355_CR52","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European Conference on Computer Vision, Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"355_CR53","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159"},{"key":"355_CR54","unstructured":"Liu S, Li F, Zhang H, Yang X, Qi X, Su H, Zhu J, Zhang L (2022) Dab-detr: dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329"},{"key":"355_CR55","doi-asserted-by":"crossref","unstructured":"Li F, Zhang H, Liu S, Guo J, Ni LM, Zhang L (2022) Dn-detr: Accelerate detr training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 13619\u201313627","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"355_CR56","unstructured":"Zhang H, Li F, Liu S, Zhang L, Su H, Zhu J, Ni LM, Shum HY (2022) Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv Preprint arXiv:2203.03605"},{"key":"355_CR57","doi-asserted-by":"crossref","unstructured":"Zhu X, Dai J, Yuan L, Wei Y (2018) Towards high performance video object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7210\u20137218","DOI":"10.1109\/CVPR.2018.00753"},{"issue":"10","key":"355_CR58","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TCSVT.2017.2736553","volume":"28","author":"K Kang","year":"2017","unstructured":"Kang K, Li H, Yan J, Zeng X, Yang B, Xiao T, Zhang C, Wang Z, Wang R, Wang X, Ouyang W (2017) T-cnn: tubelets with convolutional neural networks for object detection from videos. IEEE Trans Circuits Syst Video Technol 28(10):2896\u20132907. https:\/\/doi.org\/10.1109\/TCSVT.2017.2736553","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"355_CR59","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2017) Detect to track and track to detect. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3038\u20133046","DOI":"10.1109\/ICCV.2017.330"},{"key":"355_CR60","doi-asserted-by":"crossref","unstructured":"Gong T, Chen K, Wang X, Chu Q, Zhu F, Lin D, Yu N, Feng H (2021) Temporal ROI align for video object recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. 35(2): 1442\u20131450","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"355_CR61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3285136","author":"Q Qi","year":"2023","unstructured":"Qi Q, Hou T, Lu Y, Yan Y, Wang H (2023) DGRNet: a dual-level graph Relation Network for Video object detection. IEEE Trans Image Process. https:\/\/doi.org\/10.1109\/TIP.2023.3285136","journal-title":"IEEE Trans Image Process"},{"key":"355_CR62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955","author":"Q Zhou","year":"2022","unstructured":"Zhou Q, Li X, He L, Yang Y, Cheng G, Tong Y, Ma L, Tao D (2022) TransVOD: end-to-end video object detection with spatial-temporal transformers. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2022.3223955","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"355_CR63","doi-asserted-by":"publisher","first-page":"102907","DOI":"10.1016\/j.cviu.2020.102907","volume":"193","author":"L Wen","year":"2020","unstructured":"Wen L, Du D, Cai Z, Lei Z, Chang MC, Qi H, Lim J, Yang MH, Lyu S (2020) UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. Comput Vis Image Underst 193:102907. https:\/\/doi.org\/10.1016\/j.cviu.2020.102907","journal-title":"Comput Vis Image Underst"},{"key":"355_CR64","doi-asserted-by":"crossref","unstructured":"Fujitake M, Sugimoto A (2021) Temporal feature enhancement network with external memory for object detection in surveillance video, IEEE International Conference on Pattern Recognition, pp 7684\u20137691","DOI":"10.1109\/ICPR48806.2021.9412056"},{"key":"355_CR65","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. arXiv preprint arXiv:1904.07850"},{"key":"355_CR66","doi-asserted-by":"crossref","unstructured":"Kim KJ, Kim PK, Chung YS, Choi DH (2018) Performance enhancement of YOLOv3 by adding prediction layers with spatial pyramid pooling for vehicle detection. In: IEEE International Conference on Advanced Video and Signal based Surveillance, pp 1\u20136","DOI":"10.1109\/AVSS.2018.8639438"},{"key":"355_CR67","doi-asserted-by":"publisher","first-page":"78311","DOI":"10.1109\/ACCESS.2019.2922479","volume":"7","author":"KJ Kim","year":"2019","unstructured":"Kim KJ, Kim PK, Chung YS, Choi DH (2019) Multi-scale detector for accurate vehicle detection in traffic surveillance data. IEEE Access 7:78311\u201378319. https:\/\/doi.org\/10.1109\/ACCESS.2019.2922479","journal-title":"IEEE Access"},{"key":"355_CR68","doi-asserted-by":"crossref","unstructured":"Perreault H, Bilodeau GA, Saunier N, Heritier M (2020) Spotnet: Self-attention multi-task network for object detection. In: IEEE Conference on Computer and Robot Vision, pp 230\u2013237","DOI":"10.1109\/CRV50864.2020.00038"},{"key":"355_CR69","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.patrec.2021.09.002","volume":"151","author":"H Perreault","year":"2021","unstructured":"Perreault H, Bilodeau GA, Saunier N, Heritier M (2021) FFAVOD: feature fusion architecture for video object detection. Pattern Recognit Lett 151:294\u2013301. https:\/\/doi.org\/10.1016\/j.patrec.2021.09.002","journal-title":"Pattern Recognit Lett"},{"key":"355_CR70","unstructured":"Peng Y, Li H, Wu P, Zhang Y, Sun X, Wu F (2024) D-FINE: redefine regression Task in DETRs as Fine-grained distribution refinement. arXiv preprint arXiv:2410.13842"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-025-00355-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-025-00355-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-025-00355-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T07:32:48Z","timestamp":1742196768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-025-00355-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,12]]},"references-count":70,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["355"],"URL":"https:\/\/doi.org\/10.1007\/s13735-025-00355-x","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,12]]},"assertion":[{"value":"24 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"5"}}