{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:51:12Z","timestamp":1777567872136,"version":"3.51.4"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"23","license":[{"start":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T00:00:00Z","timestamp":1725926400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T00:00:00Z","timestamp":1725926400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2022JM-20"],"award-info":[{"award-number":["2022JM-20"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xi\u2019an Science and Technology planning project","award":["21RGZN0008"],"award-info":[{"award-number":["21RGZN0008"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s10489-024-05748-9","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T10:03:40Z","timestamp":1725962620000},"page":"12177-12193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["StreamTrack: real-time meta-detector for streaming perception in full-speed domain driving scenarios"],"prefix":"10.1007","volume":"54","author":[{"given":"Weizhen","family":"Ge","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6563-9206","authenticated-orcid":false,"given":"Junge","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,10]]},"reference":[{"key":"5748_CR1","doi-asserted-by":"crossref","unstructured":"Li M, Wang YX, Ramanan D (2020) Towards streaming perception. In: Computer vision\u2013ECCV 2020: 16th european conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16, Springer, pp 473\u2013488","DOI":"10.1007\/978-3-030-58536-5_28"},{"key":"5748_CR2","doi-asserted-by":"crossref","unstructured":"Yang J, Liu S, Li Z, et al (2022) Real-time object detection for streaming perception. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5385\u20135395","DOI":"10.1109\/CVPR52688.2022.00531"},{"key":"5748_CR3","doi-asserted-by":"crossref","unstructured":"Li C, Cheng ZQ, He JY, et al (2023) Longshortnet: Exploring temporal and semantic features fusion in streaming perception. In: ICASSP 2023-2023 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10094855"},{"key":"5748_CR4","doi-asserted-by":"publisher","unstructured":"He JY, Cheng ZQ, Li C, et al (2023) Damo-streamnet: Optimizing streaming perception in autonomous driving. In: Elkind E (ed) proceedings of the thirty-second international joint conference on artificial intelligence, IJCAI-23. International Joint Conferences on Artificial Intelligence Organization, pp 810\u2013818. https:\/\/doi.org\/10.24963\/ijcai.2023\/90, main Track","DOI":"10.24963\/ijcai.2023\/90"},{"key":"5748_CR5","doi-asserted-by":"crossref","unstructured":"Wang X, Zhu Z, Zhang Y, et al (2023) Are we ready for vision-centric driving streaming perception? the asap benchmark. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9600\u20139610","DOI":"10.1109\/CVPR52729.2023.00926"},{"key":"5748_CR6","doi-asserted-by":"crossref","unstructured":"Sela GE, Gog I, Wong J, et al (2022) Context-aware streaming perception in dynamic environments. In: European conference on computer vision, Springer, pp 621\u2013638","DOI":"10.1007\/978-3-031-19839-7_36"},{"key":"5748_CR7","doi-asserted-by":"crossref","unstructured":"Thavamani C, Li M, Cebron N, et al (2021) Fovea: Foveated image magnification for autonomous navigation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 15539\u201315548","DOI":"10.1109\/ICCV48922.2021.01525"},{"key":"5748_CR8","unstructured":"Ghosh A, Nambi A, Singh A, et al (2021) Adaptive streaming perception using deep reinforcement learning. arXiv:2106.05665"},{"key":"5748_CR9","doi-asserted-by":"crossref","unstructured":"Gu Y, Wang Q, Qin X (2021) Real-time streaming perception system for autonomous driving. In: 2021 China Automation Congress (CAC), IEEE, pp 5239\u20135244","DOI":"10.1109\/CAC53003.2021.9728221"},{"key":"5748_CR10","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":"5748_CR11","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, et al (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"5748_CR12","doi-asserted-by":"crossref","unstructured":"Zheng Y, Huang D, Liu S, et al (2020) Cross-domain object detection through coarse-to-fine feature adaptation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13766\u201313775","DOI":"10.1109\/CVPR42600.2020.01378"},{"issue":"4","key":"5748_CR13","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1109\/TIV.2017.2695896","volume":"1","author":"RN Rajaram","year":"2016","unstructured":"Rajaram RN, Ohn-Bar E, Trivedi MM (2016) Refinenet: Refining object detectors for autonomous driving. IEEE Trans Intell Veh 1(4):358\u2013368. https:\/\/doi.org\/10.1109\/TIV.2017.2695896","journal-title":"IEEE Trans Intell Veh"},{"key":"5748_CR14","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, et al (2016) Ssd: Single shot multibox detector. In: Computer vision\u2013ECCV 2016: 14th european conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"5748_CR15","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, et al (2019) Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"5748_CR16","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, et al (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":"5748_CR17","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 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"5748_CR18","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv:1804.02767"},{"key":"5748_CR19","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv:2004.10934"},{"key":"5748_CR20","unstructured":"glenn jocher (2021) Yolov5. https:\/\/github.com\/ultralytics\/yolov5"},{"key":"5748_CR21","unstructured":"Li C, Li L, Jiang H, et al (2022) Yolov6: A single-stage object detection framework for industrial applications. arXiv:2209.02976"},{"key":"5748_CR22","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":"5748_CR23","unstructured":"Ge Z, Liu S, Wang F, et al (2021) Yolox: Exceeding yolo series in 2021. arXiv:2107.08430"},{"key":"5748_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127206","volume":"572","author":"J Zhang","year":"2024","unstructured":"Zhang J, Shi Y, Yang J et al (2024) Kd-scfnet: Towards more accurate and lightweight salient object detection via knowledge distillation. Neurocomputing 572:127206","journal-title":"Neurocomputing"},{"key":"5748_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127060","volume":"566","author":"P Ju","year":"2024","unstructured":"Ju P, Zhang Y (2024) Knowledge distillation for object detection based on inconsistency-based feature imitation and global relation imitation. Neurocomputing 566:127060","journal-title":"Neurocomputing"},{"key":"5748_CR26","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.neucom.2020.12.055","volume":"433","author":"Z Liu","year":"2021","unstructured":"Liu Z, Zheng T, Xu G et al (2021) Ttfnext for real-time object detection. Neurocomputing 433:59\u201370","journal-title":"Neurocomputing"},{"issue":"10","key":"5748_CR27","doi-asserted-by":"publisher","first-page":"11916","DOI":"10.1007\/s10489-021-03026-6","volume":"52","author":"H Wu","year":"2022","unstructured":"Wu H, Ma D, Mao Z et al (2022) Ssrfd: single shot real-time face detector. Appl Intell 52(10):11916\u201311927","journal-title":"Appl Intell"},{"key":"5748_CR28","doi-asserted-by":"crossref","unstructured":"Bakkouri I, Bakkouri S (2024) 2mgas-net: multi-level multi-scale gated attentional squeezed network for polyp segmentation. Signal, Image and Video Processing, pp 1\u201310","DOI":"10.1007\/s11760-024-03240-y"},{"key":"5748_CR29","doi-asserted-by":"crossref","unstructured":"Zhao Y, Lv W, Xu S, et al (2024) Detrs beat yolos on real-time object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16965\u201316974","DOI":"10.1109\/CVPR52733.2024.01605"},{"issue":"20","key":"5748_CR30","doi-asserted-by":"publisher","first-page":"24603","DOI":"10.1007\/s10489-023-04740-z","volume":"53","author":"T Yu","year":"2023","unstructured":"Yu T, Zhang C, Ma M et al (2023) Recursive least squares method for training and pruning convolutional neural networks. Appl Intell 53(20):24603\u201324618","journal-title":"Appl Intell"},{"key":"5748_CR31","doi-asserted-by":"crossref","unstructured":"Bakkouri I, Afdel K (2018) Convolutional neural-adaptive networks for melanoma recognition. In: Image and signal processing: 8th international conference, ICISP 2018, Cherbourg, France, July 2-4, 2018, Proceedings 8, Springer, pp 453\u2013460","DOI":"10.1007\/978-3-319-94211-7_49"},{"key":"5748_CR32","doi-asserted-by":"crossref","unstructured":"Wojke N, Bewley A, Paulus D (2017) Simple online and realtime tracking with a deep association metric. In: 2017 IEEE international conference on image processing (ICIP), IEEE, pp 3645\u20133649","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"5748_CR33","doi-asserted-by":"crossref","unstructured":"Yang J, Ge H, Su S, et al (2022) Transformer-based two-source motion model for multi-object tracking. Appl Intell pp 1\u201313","DOI":"10.1007\/s10489-021-03012-y"},{"key":"5748_CR34","unstructured":"Zhang J, Zhou S, Chang X, et al (2020) Multiple object tracking by flowing and fusing. arXiv:2001.11180"},{"key":"5748_CR35","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A, Fischer P, Ilg E, et al (2015) Flownet: Learning optical flow with convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 2758\u20132766","DOI":"10.1109\/ICCV.2015.316"},{"key":"5748_CR36","doi-asserted-by":"crossref","unstructured":"Xu J, Cao Y, Zhang Z, et al (2019) Spatial-temporal relation networks for multi-object tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3988\u20133998","DOI":"10.1109\/ICCV.2019.00409"},{"key":"5748_CR37","unstructured":"Liu S, Yu H, Liao C, et al (2021) Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In: International conference on learning representations"},{"key":"5748_CR38","first-page":"22419","volume":"34","author":"H Wu","year":"2021","unstructured":"Wu H, Xu J, Wang J et al (2021) Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Adv Neural Inf Process Syst 34:22419\u201322430","journal-title":"Adv Neural Inf Process Syst"},{"key":"5748_CR39","doi-asserted-by":"crossref","unstructured":"Zeng A, Chen M, Zhang L, et al (2023) Are transformers effective for time series forecasting? In: Proceedings of the AAAI conference on artificial intelligence, pp 11121\u201311128","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"5748_CR40","unstructured":"Nie Y, Nguyen NH, Sinthong P, et al (2022) A time series is worth 64 words: Long-term forecasting with transformers. arXiv:2211.14730"},{"key":"5748_CR41","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al (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":"5748_CR42","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, et al (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05748-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05748-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05748-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T13:09:27Z","timestamp":1727701767000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05748-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,10]]},"references-count":42,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["5748"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05748-9","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,10]]},"assertion":[{"value":"4 August 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2024","order":2,"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 that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study does not involve the collection or use of private data. All data used in this study were obtained from the open literature, statistics or results of simulation experiments. Therefore, ethical approval and informed consent were not required for this study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}]}}