{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:35:19Z","timestamp":1781757319550,"version":"3.54.5"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61703268"],"award-info":[{"award-number":["61703268"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-19391-6","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T05:01:57Z","timestamp":1716440517000},"page":"11605-11623","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Lightweight and real-time semantic segmentation of UAV traffic videos based on siamese network for keyframe recognition"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9314-7383","authenticated-orcid":false,"given":"Weiwei","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingtao","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,23]]},"reference":[{"key":"19391_CR1","doi-asserted-by":"publisher","first-page":"2916","DOI":"10.1016\/j.coastaleng.2019.103527","volume":"152","author":"EWJ Bergsma","year":"2019","unstructured":"Bergsma EWJ, Almar R, Almeida LPMD, Sall M (2019) On the operational use of UAVS for video-derived bathymetry. Coast Eng 152:2916\u20132924","journal-title":"Coast Eng"},{"key":"19391_CR2","first-page":"13627","volume":"35","author":"Y Zhao","year":"2022","unstructured":"Zhao Y, Li Z, Guo X, Lu Y (2022) Alignment-guided temporal attention for video action recognition. Adv Neural Inf Process Syst 35:13627\u201313639","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"19391_CR3","first-page":"1","volume":"179","author":"Z Song","year":"2020","unstructured":"Song Z, Zhang Z, Yang S, Ding D, Ning J (2020) Identifying sunflower lodging based on image fusion and deep semantic segmentation with UAV remote sensing imaging. Comput Electron Agric 179(1):1\u201315","journal-title":"Comput Electron Agric"},{"issue":"1","key":"19391_CR4","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1109\/TCSVT.2022.3202574","volume":"33","author":"L Yan","year":"2022","unstructured":"Yan L, Wang Q, Ma S, Wang J, Yu C (2022) Solve the puzzle of instance segmentation in videos: a weakly supervised framework with spatio-temporal collaboration. IEEE Trans Circuits Syst Video Technol 33(1):393\u2013406","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"19391_CR5","first-page":"9816","volume-title":"In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","author":"D Liu","year":"2021","unstructured":"Liu D, Cui Y, Tan W, Chen Y (2021) Sg-net: Spatial granularity network for one-stage video instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp 9816\u20139825"},{"issue":"5","key":"19391_CR6","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1109\/JAS.2023.123456","volume":"10","author":"Z Qin","year":"2023","unstructured":"Qin Z, Lu X, Nie X, Liu D, Yin Y, Wang W (2023) Coarse-to-fine video instance segmentation with factorized conditional appearance flows. IEEE\/CAA J Autom Sinica 10(5):1192\u20131208","journal-title":"IEEE\/CAA J Autom Sinica"},{"key":"19391_CR7","unstructured":"Lu Y, Zhang J, Sun S, Guo Q, Cao Z, Fei S, Yang B, Chen Y (2023) Label-efficient video object segmentation with motion clues. IEEE Transactions on Circuits and Systems for Video Technology. pp 1\u201313"},{"key":"19391_CR8","doi-asserted-by":"crossref","unstructured":"Li X, Yuan H, Zhang W, Cheng G, Pang J, Loy CC (2023) Tube-link: A flexible cross tube baseline for universal video segmentation. In: Proceedings of 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). pp 13877\u201313887","DOI":"10.1109\/ICCV51070.2023.01280"},{"key":"19391_CR9","doi-asserted-by":"crossref","unstructured":"Choi J, Huang JB, Sharma G (2022) Self-supervised cross-video temporal learning for unsupervised video domain adaptation. In: Proceedings of 26th International Conference on Pattern Recognition (ICPR). pp 3464\u20133470","DOI":"10.1109\/ICPR56361.2022.9956161"},{"key":"19391_CR10","doi-asserted-by":"crossref","unstructured":"Sabokrou M, Fathy M, Huang F, Klette R (2016) STFCN: spatio-temporal fully convolutional neural network for semantic segmentation of street scenes. In: Proceedings of Asian Conference on Computer Vision (ACCV). pp 493\u2013509","DOI":"10.1007\/978-3-319-54407-6_33"},{"key":"19391_CR11","doi-asserted-by":"crossref","unstructured":"Gadde R, Jampani V, Gehler PV (2017) Semantic video CNNs through representation warping. In: Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). pp 4453\u20134462","DOI":"10.1109\/ICCV.2017.477"},{"key":"19391_CR12","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.1109\/JSTARS.2021.3069909","volume":"99","author":"S Girisha","year":"2021","unstructured":"Girisha S, Verma U, Manohara P (2021) UVid-Net: enhanced semantic segmentation of UAV aerial videos by embedding temporal information. IEEE J Sel Top Appl Earth Obs Remote Sens 99:4115\u20134127","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"key":"19391_CR13","first-page":"1","volume":"8","author":"Y Zheng","year":"2023","unstructured":"Zheng Y, Zhou F, Liang S, Song W, Bai X (2023) Semantic segmentation in thermal videos: a new benchmark and multi-granularity contrastive learning-based framework. IEEE Trans Intell Transp Syst 8:1\u201317","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"19391_CR14","doi-asserted-by":"crossref","unstructured":"Shelhamer E, Rakelly K, Hoffman J, Darrell T (2016) Clockwork convnets for video semantic segmentation. In: Proceedings of European Conference on Computer Vision (ECCV). pp 852\u2013868","DOI":"10.1007\/978-3-319-49409-8_69"},{"key":"19391_CR15","doi-asserted-by":"crossref","unstructured":"Zhu X, Xiong Y, Dai J, Yuan L, Wei YC (2017) Deep feature flow for video recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 2349\u20132358","DOI":"10.1109\/CVPR.2017.441"},{"key":"19391_CR16","doi-asserted-by":"crossref","unstructured":"Xu YS, Fu TJ, Yang HK, Lee CY (2018) Dynamic video segmentation network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 6556\u20136565","DOI":"10.1109\/CVPR.2018.00686"},{"key":"19391_CR17","doi-asserted-by":"crossref","unstructured":"Li Y, Shi J, Lin D (2018) Low-latency video semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 5997\u20136005","DOI":"10.1109\/CVPR.2018.00628"},{"key":"19391_CR18","doi-asserted-by":"crossref","unstructured":"Liu Y, Chang G, Fu G, Wei Y, Lan J, Liu J (2022) Self-Attention based Siamese Neural Network recognition Model. In: Proceedings of 2022 34th Chinese Control and Decision Conference (CCDC). pp 721\u2013724","DOI":"10.1109\/CCDC55256.2022.10034228"},{"issue":"1","key":"19391_CR19","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1080\/08839514.2022.2032924","volume":"36","author":"I Ulku","year":"2022","unstructured":"Ulku I, Akagunduz E (2022) A survey on deep learning-based architectures for semantic segmentation on 2D images. Appl Artif Intell 36(1):47\u201358","journal-title":"Appl Artif Intell"},{"key":"19391_CR20","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1021\/acs.jcim.1c01497","volume":"17","author":"AT Mcnutt","year":"2022","unstructured":"Mcnutt AT, Koes DR (2022) Improving Delta Delta G predictions with a multitask convolut ional siamese network. J Chem Inf Model 17:1819\u20131829","journal-title":"J Chem Inf Model"},{"key":"19391_CR21","doi-asserted-by":"crossref","unstructured":"Tang Y, Zhang X, Zhu C, Westermann R, Kong X, Lin C (2019) A pruning method based on feature abstraction capability of filters. In: Proceedings of Image and Graphics: 10th International Conference (ICIG 2019). pp 642\u2013654","DOI":"10.1007\/978-3-030-34110-7_54"},{"issue":"11","key":"19391_CR22","first-page":"12747","volume":"45","author":"H Duan","year":"2023","unstructured":"Duan H, Long Y, Wang S, Zhang H, Willcocks CG, Shao L (2023) Dynamic unary convolution in transformers. IEEE Trans Pattern Anal Mach Intell 45(11):12747\u201312759","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"19391_CR23","first-page":"21","volume":"37","author":"B Fan","year":"2023","unstructured":"Fan B, Gao WW, Shan MT (2023) Lightweight semantic segmentation of UAV traffic scene objects combining attention mechanism and ghost feature mapping. J Electron Meas Instrum 37(3):21\u201328 (In Chinese)","journal-title":"J Electron Meas Instrum"},{"key":"19391_CR24","doi-asserted-by":"crossref","unstructured":"Nigam I, Huang C, Ramanan D (2018) Ensemble knowledge transfer for semantic segmentation. In: Proceedings of 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). pp 1499\u20131508","DOI":"10.1109\/WACV.2018.00168"},{"key":"19391_CR25","doi-asserted-by":"crossref","unstructured":"Chen Y, Wang Y, Lu P, Chen YS, Wang GP (2018) Large-scale structure from motion with semantic constraints of aerial images. In: Proceedings of Pattern Recognition and Computer Vision: First Chinese Conference (PRCV 2018). pp 347\u2013359","DOI":"10.1007\/978-3-030-03398-9_30"},{"key":"19391_CR26","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.isprsjprs.2020.05.009","volume":"165","author":"Y Lyu","year":"2020","unstructured":"Lyu Y, Vosselman G, Xia GS, Yilmaz A, Yang MY (2020) UAVid: a semantic segmentation dataset for UAV imagery. ISPRS J Photogramm Remote Sens 165:108\u2013119","journal-title":"ISPRS J Photogramm Remote Sens"},{"issue":"7","key":"19391_CR27","first-page":"1609","volume":"50","author":"Z Zhang","year":"2022","unstructured":"Zhang Z, Liu T (2022) Real-time semantic segmentation for road scene based on data enhancement and dual-path fusion network. Acta Electron Sin 50(7):1609\u20131620","journal-title":"Acta Electron Sin"},{"key":"19391_CR28","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A, Fischer P, Ilg E, Haeusser P, Hazirbas C, Golkov V, van der Cremers P, Brox T (2015) FlowNet: Learning optical flow with convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV). pp 2758\u20132766","DOI":"10.1109\/ICCV.2015.316"},{"key":"19391_CR29","doi-asserted-by":"crossref","unstructured":"Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T (2017) FlowNet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 2462\u20132470","DOI":"10.1109\/CVPR.2017.179"},{"key":"19391_CR30","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Qi XJ, Wang XG, Jia JY (2017) Pyramid scene parsing network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. pp 6230\u20136239","DOI":"10.1109\/CVPR.2017.660"},{"key":"19391_CR31","doi-asserted-by":"crossref","unstructured":"Orsic M, Kreso I, Bevandic P, Segvic S (2019) In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 12607\u201312616","DOI":"10.1109\/CVPR.2019.01289"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19391-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19391-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19391-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T03:28:42Z","timestamp":1746156522000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19391-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":31,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["19391"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19391-6","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,23]]},"assertion":[{"value":"12 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors agreed to publish.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}