{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T09:51:32Z","timestamp":1775037092872,"version":"3.50.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Future Generation Computer Systems"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.future.2025.108079","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T06:39:50Z","timestamp":1755153590000},"page":"108079","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["A dual-stream parallel architecture for robust visual tracking using scale-aware region proposals"],"prefix":"10.1016","volume":"175","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0171-0031","authenticated-orcid":false,"given":"Sudha","family":"SK","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6257-5593","authenticated-orcid":false,"given":"Aji","family":"S","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.future.2025.108079_bib0001","first-page":"610","article-title":"Pedestrian and vehicle detection in traffic scenes using a unified convolutional network","volume":"19","author":"Ye","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.future.2025.108079_bib0002","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"issue":"9","key":"10.1016\/j.future.2025.108079_bib0003","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.future.2025.108079_bib0004","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"key":"10.1016\/j.future.2025.108079_bib0005","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015"},{"key":"10.1016\/j.future.2025.108079_bib0006","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"379","article-title":"R-FCN: object Detection via Region-based Fully Convolutional Networks","author":"Dai","year":"2016"},{"key":"10.1016\/j.future.2025.108079_bib0007","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.future.2025.108079_bib0008","doi-asserted-by":"crossref","unstructured":"K. He, G. Gkioxari, P. Doll\u00e1r, R. Girshick, Mask R-CNN, arXiv preprint arXiv: 1703.06870(2017). 10.48550\/arXiv.1703.06870.","DOI":"10.1109\/ICCV.2017.322"},{"key":"10.1016\/j.future.2025.108079_bib0009","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"21","article-title":"SSD: single shot MultiBox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.future.2025.108079_bib0010","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.future.2025.108079_bib0011","unstructured":"C.-Y. Fu, W. Liu, A. Ranga, A. Tyagi, A.C. Berg, DSSD: deconvolutional single shot detector, arXiv preprint arXiv:1701.06659v1(2017)."},{"key":"10.1016\/j.future.2025.108079_bib0012","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","author":"Kalman","year":"1960","journal-title":"Trans. ASME J. Basic Eng."},{"key":"10.1016\/j.future.2025.108079_bib0013","series-title":"Proceedings of the IEEE Workshop on Applications of Computer Vision (WACV)","first-page":"214","article-title":"Real time face and object tracking as a component of a perceptual user interface","author":"Bradski","year":"1998"},{"key":"10.1016\/j.future.2025.108079_bib0014","series-title":"Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA","first-page":"3464","article-title":"Simple online and realtime tracking","author":"Bewley","year":"2016"},{"key":"10.1016\/j.future.2025.108079_bib0015","series-title":"Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP),Beijing, China","first-page":"3645","article-title":"Simple online and realtime tracking with a deep association metric","author":"Wojke","year":"2017"},{"key":"10.1016\/j.future.2025.108079_bib0016","series-title":"Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA","first-page":"14656","article-title":"RetinaTrack: online single stage joint detection and tracking","author":"Lu","year":"2020"},{"key":"10.1016\/j.future.2025.108079_bib0017","series-title":"Computer Vision - ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XI","first-page":"107-122","article-title":"Towards real-time multi-object tracking","author":"Wang","year":"2020"},{"key":"10.1016\/j.future.2025.108079_bib0018","unstructured":"C. Li, G. Dobler, X. Feng, Y. Wang, TrackNet: simultaneous object detection and tracking and its application in traffic video analysis, arXiv: 1902.01466v1 (2019). 10.48550\/arXiv.1902.01466."},{"issue":"16","key":"10.1016\/j.future.2025.108079_bib0019","doi-asserted-by":"crossref","DOI":"10.3390\/app14167071","article-title":"A robust multi-camera vehicle tracking algorithm in highway scenarios using deep learning","volume":"14","author":"Li","year":"2024","journal-title":"Appl. Sci."},{"issue":"8","key":"10.1016\/j.future.2025.108079_bib0020","doi-asserted-by":"crossref","first-page":"9467","DOI":"10.1109\/TITS.2024.3360875","article-title":"Yolo-3DMM for simultaneous multiple object detection and tracking in traffic scenarios","volume":"25","author":"Liu","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"4","key":"10.1016\/j.future.2025.108079_bib0021","doi-asserted-by":"crossref","first-page":"878","DOI":"10.3390\/electronics12040878","article-title":"A multi-scale traffic object detection algorithm for road scenes based on improved YOLOv5","volume":"12","author":"Li","year":"2023","journal-title":"Electronics"},{"issue":"21","key":"10.1016\/j.future.2025.108079_bib0022","doi-asserted-by":"crossref","first-page":"3425","DOI":"10.3390\/electronics11213425","article-title":"Robust framework for object detection in a traffic surveillance system","volume":"11","author":"Akhtar","year":"2022","journal-title":"Electronics"},{"key":"10.1016\/j.future.2025.108079_bib0023","doi-asserted-by":"crossref","first-page":"3125","DOI":"10.1007\/s10489-020-01704-5","article-title":"Finding every car: a traffic surveillance multi-scale vehicle object detection method","volume":"50","author":"Mao","year":"2020","journal-title":"Appl. Intell."},{"key":"10.1016\/j.future.2025.108079_bib0024","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2022.3160424","article-title":"PAE: portable appearance extension for multiple object detection and tracking in traffic scenes","volume":"10","author":"Mohamed","year":"2022","journal-title":"IEEE Access"},{"issue":"7","key":"10.1016\/j.future.2025.108079_bib0025","doi-asserted-by":"crossref","first-page":"6989","DOI":"10.1109\/TITS.2023.3264573","article-title":"A cross-scale and illumination invariance-based model for robust object detection in traffic surveillance scenarios","volume":"24","author":"Lu","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.future.2025.108079_bib0026","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.patrec.2023.01.015","article-title":"Automated labeling of training data for improved object detection in traffic videos by fine-tuned deep convolutional neural networks","volume":"167","author":"Garc\u00eda-Aguilar","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.future.2025.108079_bib0027","article-title":"Video-based multi-camera vehicle tracking via appearance-parsing spatio-temporal trajectory matching network","volume":"PP","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.future.2025.108079_bib0028","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.1007\/s11263-023-01933-4","article-title":"FastTrack: a highly efficient and generic GPU-based multi-object tracking method with parallel Kalman filter","volume":"132","author":"Liu","year":"2024","journal-title":"Int. J. Comput. Vision"},{"key":"10.1016\/j.future.2025.108079_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"TrackFormer: multi-object tracking with transformers","author":"Meinhardt","year":"2022"},{"key":"10.1016\/j.future.2025.108079_bib0030","unstructured":"P. Sun, Y. Jiang, R. Wang, E. Xie, Y. Cao, Z. Hu, P. Luo, G. Yao, TransTrack: multiple object tracking with transformer, arXiv preprint arXiv:2012.15460(2021)."},{"key":"10.1016\/j.future.2025.108079_bib0031","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","article-title":"MOTR: end-to-end multiple-object tracking with transformers","author":"Zeng","year":"2022"},{"key":"10.1016\/j.future.2025.108079_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"MeMOTR: memory-enhanced multi-object tracking with transformers","author":"Ci","year":"2023"},{"key":"10.1016\/j.future.2025.108079_bib0033","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"TeViT: temporal vision transformer for video object detection","author":"Yang","year":"2023"},{"key":"10.1016\/j.future.2025.108079_bib0034","unstructured":"M.T. Teye, O. Moaz, M. Rottmann, LiDAR MOT-DETR: a LiDAR-based two-stage transformer for 3D multiple object tracking, arXiv preprint arXiv:2505.12753(2025)."},{"issue":"4","key":"10.1016\/j.future.2025.108079_bib0035","doi-asserted-by":"crossref","first-page":"1907","DOI":"10.3390\/app15041907","article-title":"ReTrackVLM: transformer-enhanced multi-object tracking with cross-modal embeddings and zero-shot re-identification integration","volume":"15","author":"Bayraktar","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.future.2025.108079_bib0036","doi-asserted-by":"crossref","first-page":"28347","DOI":"10.1007\/s11042-022-12715-4","article-title":"Vehicle detection and tracking method for traffic video based on faster R-CNN","volume":"81","author":"Othmani","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.future.2025.108079_bib0037","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.patrec.2021.09.002","article-title":"FFAVOD: feature fusion architecture for video object detection","volume":"151","author":"Perreaulta","year":"2021","journal-title":"Pattern Recognit. Lett."},{"issue":"2","key":"10.1016\/j.future.2025.108079_bib0038","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/3373647","article-title":"Intelligent Intersection: two-stream convolutional networks for real-time near accident detection in traffic video","volume":"6","author":"Huang","year":"2020","journal-title":"ACM Trans. Spatial Algorithms Syst."},{"key":"10.1016\/j.future.2025.108079_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2020.102907","article-title":"UA-DETRAC: a new benchmark and protocol for multi-object tracking","volume":"193","author":"Wen","year":"2020","journal-title":"Comput. Vision Image Understanding"},{"key":"10.1016\/j.future.2025.108079_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2636","article-title":"BDD100K: a diverse driving dataset for heterogeneous multitask learning","author":"Yu","year":"2020"},{"issue":"10","key":"10.1016\/j.future.2025.108079_bib0041","doi-asserted-by":"crossref","DOI":"10.3390\/electronics14102009","article-title":"Vehicle detection in videos leveraging multi-scale feature and memory information","volume":"14","author":"Yang","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.future.2025.108079_bib0042","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/s11760-025-04313-2","article-title":"CEM-YOLO: multi-branch residual feature fusion and convolutional maxpooling downsampling for real-time vehicle detection in night scenarios","volume":"19","author":"Liu","year":"2025","journal-title":"Signal Image Video Process."},{"key":"10.1016\/j.future.2025.108079_bib0043","doi-asserted-by":"crossref","unstructured":"L. Wang, K. Lu, N. Zhang, X. Qu, J. Wang, J. Wan, G. Li, J. Xiao, Shoggoth: towards efficient edge-cloud collaborative real-time video inference via adaptive online learning, arXiv preprint arXiv: 2306.15333(2023). 10.48550\/arXiv.2306.15333.","DOI":"10.1109\/DAC56929.2023.10247821"},{"issue":"5","key":"10.1016\/j.future.2025.108079_bib0044","first-page":"17","article-title":"Real-Time Vehicle Detection for Surveillance of River Dredging Areas Using Convolutional Neural Networks","volume":"15","author":"Bayati","year":"2023","journal-title":"I.J. Image Graph. Signal Process."},{"key":"10.1016\/j.future.2025.108079_bib0045","article-title":"Improved vision-based vehicle detection and classification by optimized YOLOv4","author":"Zhao","year":"2022","journal-title":"IEEE Access"},{"issue":"6","key":"10.1016\/j.future.2025.108079_bib0046","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1016\/j.dcan.2022.10.013","article-title":"Enhancing the robustness of object detection via 6G vehicular edge computing","volume":"8","author":"Chen","year":"2022","journal-title":"Digit. Commun. Netw."},{"key":"10.1016\/j.future.2025.108079_bib0047","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10781","article-title":"EfficientDet: scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"10.1016\/j.future.2025.108079_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7464","article-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"10.1016\/j.future.2025.108079_bib0049","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.aej.2024.07.011","article-title":"Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios","volume":"106","author":"Zhao","year":"2024","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.future.2025.108079_bib0050","unstructured":"Z. Ge, S. Liu, F. Wang, Z. Li, J. Sun, YOLOX: exceeding YOLO series in 2021, arXiv preprint arXiv:2107.08430(2021)."},{"issue":"9","key":"10.1016\/j.future.2025.108079_bib0051","doi-asserted-by":"crossref","first-page":"12625","DOI":"10.1109\/TVT.2024.3394350","article-title":"You only look at once for real-time and generic multi-task","volume":"73","author":"Wang","year":"2024","journal-title":"IEEE Trans. Veh. Technol."}],"container-title":["Future Generation Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X25003735?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X25003735?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:36:25Z","timestamp":1762256185000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167739X25003735"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":51,"alternative-id":["S0167739X25003735"],"URL":"https:\/\/doi.org\/10.1016\/j.future.2025.108079","relation":{},"ISSN":["0167-739X"],"issn-type":[{"value":"0167-739X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A dual-stream parallel architecture for robust visual tracking using scale-aware region proposals","name":"articletitle","label":"Article Title"},{"value":"Future Generation Computer Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.future.2025.108079","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108079"}}