{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T09:19:50Z","timestamp":1754558390886,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No. 2018AAA0100400"],"award-info":[{"award-number":["No. 2018AAA0100400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071466","62076242","61976208"],"award-info":[{"award-number":["62071466","62076242","61976208"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s00521-023-09325-y","type":"journal-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T05:02:45Z","timestamp":1704258165000},"page":"5367-5382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Few-shot video object segmentation with prototype evolution"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9546-2747","authenticated-orcid":false,"given":"Binjie","family":"Mao","sequence":"first","affiliation":[]},{"given":"Xiyan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Linsu","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Jiazhong","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,3]]},"reference":[{"key":"9325_CR1","doi-asserted-by":"crossref","unstructured":"Fragkiadaki K, Arbelaez P, Felsen P, Malik J (2015) Learning to segment moving objects in videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4083\u20134090","DOI":"10.1109\/CVPR.2015.7299035"},{"key":"9325_CR2","doi-asserted-by":"crossref","unstructured":"Tsai Y, Yang M, Black MJ (2016) Video segmentation via object flow. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3899\u20133908","DOI":"10.1109\/CVPR.2016.423"},{"key":"9325_CR3","unstructured":"Wang W, Zhou T, Porikli F, Crandall DJ, Gool LV (2021) A survey on deep learning technique for video segmentation. arXiv preprint arXiv: 2107.01153"},{"key":"9325_CR4","doi-asserted-by":"crossref","unstructured":"Caelles S, Maninis K, Pont-Tuset J, Leal-Taix\u00e9 L, Cremers D, Gool LV (2017) One-shot video object segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5320\u20135329","DOI":"10.1109\/CVPR.2017.565"},{"key":"9325_CR5","doi-asserted-by":"crossref","unstructured":"Perazzi F, Khoreva A, Benenson R, Schiele B, Sorkine-Hornung A (2017) Learning video object segmentation from static images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3491\u20133500","DOI":"10.1109\/CVPR.2017.372"},{"key":"9325_CR6","doi-asserted-by":"crossref","unstructured":"Oh SW, Lee J, Xu N, Kim SJ (2019) Video object segmentation using space-time memory networks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9225\u20139234","DOI":"10.1109\/ICCV.2019.00932"},{"key":"9325_CR7","doi-asserted-by":"crossref","unstructured":"Chen H, Wu H, Zhao N, Ren S, He S (2021) Delving deep into many-to-many attention for few-shot video object segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14040\u201314049","DOI":"10.1109\/CVPR46437.2021.01382"},{"key":"9325_CR8","unstructured":"Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. In: Proceedings of advances in neural information processing systems, pp 3630\u20133638"},{"key":"9325_CR9","unstructured":"Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. In: Proccedings of advances in neural information processing systems, pp 4077\u20134087"},{"key":"9325_CR10","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr PHS, Hospedales TM Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1199\u20131208"},{"key":"9325_CR11","doi-asserted-by":"crossref","unstructured":"Zhang C, Lin G, Liu F, Yao R, Shen C (2019) Canet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5217\u20135226","DOI":"10.1109\/CVPR.2019.00536"},{"key":"9325_CR12","doi-asserted-by":"crossref","unstructured":"Wang K, Liew JH, Zou Y, Zhou D, Feng J (2019) Panet: few-shot image semantic segmentation with prototype alignment. In:Proceedings of the IEEE\/CVF international conference on computer vision, pp 9196\u20139205","DOI":"10.1109\/ICCV.2019.00929"},{"key":"9325_CR13","doi-asserted-by":"crossref","unstructured":"Liu Y, Zhang X, Zhang S, He X (2020) Part-aware prototype network for few-shot semantic segmentation. In: Proceedings of European conference computer vision, pp 142\u2013158","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"9325_CR14","doi-asserted-by":"crossref","unstructured":"Liu Y, Zhang X, Zhang S, He X (2020) Part-aware prototype network for few-shot semantic segmentation. In: Proceedings of European conference computer vision, pp 142\u2013158","DOI":"10.1007\/978-3-030-58545-7_9"},{"issue":"2","key":"9325_CR15","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","volume":"44","author":"Z Tian","year":"2022","unstructured":"Tian Z, Zhao H, Shu M, Yang Z, Li R, Jia J (2022) Prior guided feature enrichment network for few-shot segmentation. IEEE Trans Pattern Anal Mach Intell 44(2):1050\u20131065","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9325_CR16","doi-asserted-by":"crossref","unstructured":"Mao B, Wang L, Xiang S, Pan C (2021) LTAF-Net: learning task-aware adaptive features and refining mask for few-shot semantic segmentation. In: Proccedings of IEEE international conference on acoustics, speech and signal processing, pp 2320\u20132324","DOI":"10.1109\/ICASSP39728.2021.9414786"},{"issue":"1","key":"9325_CR17","first-page":"273","volume":"44","author":"L Zhu","year":"2022","unstructured":"Zhu L, Yang Y (2022) Label independent memory for semi-supervised few-shot video classification. IEEE Trans Pattern Anal Mach Intell 44(1):273\u2013285","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9325_CR18","doi-asserted-by":"crossref","unstructured":"Voigtlaender P, Leibe B (2017) Online adaptation of convolutional neural networks for video object segmentation. In: British machine vision conference 2017","DOI":"10.5244\/C.31.116"},{"key":"9325_CR19","doi-asserted-by":"crossref","unstructured":"Cheng J, Tsai Y, Wang S, Yang M (2017) Segflow: Joint learning for video object segmentation and optical flow. In: Proceedings of the IEEE international conference on computer vision, pp 686\u2013695","DOI":"10.1109\/ICCV.2017.81"},{"key":"9325_CR20","doi-asserted-by":"crossref","unstructured":"Oh SW, Lee J-Y, Sunkavalli K, Kim SJ (2018) Fast video object segmentation by reference-guided mask propagation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7376\u20137385","DOI":"10.1109\/CVPR.2018.00770"},{"key":"9325_CR21","doi-asserted-by":"crossref","unstructured":"Jampani V, Gadde R, Gehler PV (2017) Video propagation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3154\u20133164","DOI":"10.1109\/CVPR.2017.336"},{"key":"9325_CR22","doi-asserted-by":"crossref","unstructured":"Xiao H, Feng J, Lin G, Liu Y, Zhang M (2018) Monet: deep motion exploitation for video object segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1140\u20131148","DOI":"10.1109\/CVPR.2018.00125"},{"issue":"9","key":"9325_CR23","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1007\/s11263-019-01164-6","volume":"127","author":"A Khoreva","year":"2019","unstructured":"Khoreva A, Benenson R, Ilg E, Brox T, Schiele B (2019) Lucid data dreaming for video object segmentation. Int J Comput Vis 127(9):1175\u20131197","journal-title":"Int J Comput Vis"},{"issue":"8","key":"9325_CR24","doi-asserted-by":"publisher","first-page":"1957","DOI":"10.1109\/TPAMI.2019.2906175","volume":"42","author":"P Hu","year":"2020","unstructured":"Hu P, Wang G, Kong X, Kuen J, Tan Y (2020) Motion-guided cascaded refinement network for video object segmentation. IEEE Trans Pattern Anal Mach Intell 42(8):1957\u20131967","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"9325_CR25","doi-asserted-by":"publisher","first-page":"4781","DOI":"10.1109\/TCSVT.2019.2961267","volume":"30","author":"Y Gui","year":"2020","unstructured":"Gui Y, Tian Y, Zeng D, Xie Z, Cai Y (2020) Reliable and dynamic appearance modeling and label consistency enforcing for fast and coherent video object segmentation with the bilateral grid. IEEE Trans Circuits Syst Video Technol 30(12):4781\u20134795","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"4","key":"9325_CR26","doi-asserted-by":"publisher","first-page":"1607","DOI":"10.1109\/TCSVT.2020.3010293","volume":"31","author":"W Liu","year":"2021","unstructured":"Liu W, Lin G, Zhang T, Liu Z (2021) Guided co-segmentation network for fast video object segmentation. IEEE Trans Circuits Syst Video Technol 31(4):1607\u20131617","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"1","key":"9325_CR27","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1109\/TCSVT.2020.2971641","volume":"31","author":"Z Tan","year":"2021","unstructured":"Tan Z, Liu B, Chu Q, Zhong H, Wu Y, Li W, Yu N (2021) Real time video object segmentation in compressed domain. IEEE Trans Circuits Syst Video Technol 31(1):175\u2013188","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"9325_CR28","doi-asserted-by":"crossref","unstructured":"Li Y, Shen Z, Shan Y (2020) Fast video object segmentation using the global context module. In: Proceedings of European conference on computer vision, pp 735\u2013750","DOI":"10.1007\/978-3-030-58607-2_43"},{"key":"9325_CR29","doi-asserted-by":"crossref","unstructured":"Lu X, Wang W, Danelljan M, Zhou T, Shen J, Gool LV (2020) Video object segmentation with episodic graph memory networks. In: Proceedings of European conference on computer vision, pp 661\u2013679","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"9325_CR30","doi-asserted-by":"crossref","unstructured":"Seong H, Hyun J, Kim E (2020) Kernelized memory network for video object segmentation. In: Proceedings of European conference on computer vision, pp 629\u2013645","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"9325_CR31","doi-asserted-by":"crossref","unstructured":"Yoon JS, Rameau F, Kim J, Lee S, Shin S, Kweon IS (2017) Pixel-level matching for video object segmentation using convolutional neural networks. In: Proceedings of the IEEE international conference on computer vision, pp 2186\u20132195","DOI":"10.1109\/ICCV.2017.238"},{"key":"9325_CR32","doi-asserted-by":"crossref","unstructured":"Voigtlaender P, Chai Y, Schroff F, Adam H, Leibe B, Chen L (2019) FEELVOS: fast end-to-end embedding learning for video object segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9481\u20139490","DOI":"10.1109\/CVPR.2019.00971"},{"key":"9325_CR33","doi-asserted-by":"crossref","unstructured":"Wang Z, Xu J, Liu L, Zhu F, Shao L (2019) Ranet: ranking attention network for fast video object segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 3977\u20133986","DOI":"10.1109\/ICCV.2019.00408"},{"key":"9325_CR34","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wu Z, Peng H, Lin S (2020) A transductive approach for video object segmentation. In: Proceedings of the IEEE international conference on computer vision, pp. 6947\u20136956","DOI":"10.1109\/CVPR42600.2020.00698"},{"issue":"1","key":"9325_CR35","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1109\/TCSVT.2021.3060015","volume":"32","author":"W Zhu","year":"2022","unstructured":"Zhu W, Li J, Lu J, Zhou J (2022) Separable structure modeling for semi-supervised video object segmentation. IEEE Trans Circuits Syst Video Technol 32(1):330\u2013344","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"9325_CR36","doi-asserted-by":"crossref","unstructured":"Shaban A, Bansal S, Liu Z, Essa I, Boots B (2017) One-shot learning for semantic segmentation. In: British machine vision conference 2017","DOI":"10.5244\/C.31.167"},{"issue":"9","key":"9325_CR37","doi-asserted-by":"publisher","first-page":"3855","DOI":"10.1109\/TCYB.2020.2992433","volume":"50","author":"X Zhang","year":"2020","unstructured":"Zhang X, Wei Y, Yang Y, Huang TS (2020) Sg-one: similarity guidance network for one-shot semantic segmentation. IEEE Trans Cybern 50(9):3855\u20133865","journal-title":"IEEE Trans Cybern"},{"key":"9325_CR38","doi-asserted-by":"crossref","unstructured":"Li G, Jampani V, Sevilla-Lara L, Sun D, Kim J, Kim J (2021) Adaptive prototype learning and allocation for few-shot segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8334\u20138343","DOI":"10.1109\/CVPR46437.2021.00823"},{"key":"9325_CR39","doi-asserted-by":"crossref","unstructured":"Liu W, Zhang C, Lin G, Liu F (2020) Crnet: cross-reference networks for few-shot segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4164\u20134172","DOI":"10.1109\/CVPR42600.2020.00422"},{"key":"9325_CR40","unstructured":"Yang X, Wang B, Zhou X, Chen K, Yi S, Ouyang W, Zhou L (2020) Brinet: towards bridging the intra-class and inter-class gaps in one-shot segmentation. In: British machine vision conference 2020"},{"key":"9325_CR41","doi-asserted-by":"crossref","unstructured":"Zhang C, Lin G, Liu F, Guo J, Wu Q, Yao R (2019) Pyramid graph networks with connection attentions for region-based one-shot semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9586\u20139594","DOI":"10.1109\/ICCV.2019.00968"},{"key":"9325_CR42","doi-asserted-by":"crossref","unstructured":"Wang H, Zhang X, Hu Y, Yang Y, Cao X, Zhen X (2020) Few-shot semantic segmentation with democratic attention networks. In: Proceedings of Europe conference on computer vision, pp 730\u2013746","DOI":"10.1007\/978-3-030-58601-0_43"},{"key":"9325_CR43","doi-asserted-by":"crossref","unstructured":"Boudiaf M, Kervadec H, Ziko IM, Piantanida P, Ayed IB, Dolz J (2021) Few-shot segmentation without meta-learning: A good transductive inference is all you need? In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 13979\u201313988","DOI":"10.1109\/CVPR46437.2021.01376"},{"key":"9325_CR44","doi-asserted-by":"crossref","unstructured":"Lu Z, He S, Zhu X, Zhang L, Song Y, Xiang T (2021) Simpler is better: Few-shot semantic segmentation with classifier weight transformer. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8721\u20138730","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"9325_CR45","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (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"},{"issue":"4","key":"9325_CR46","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2018","unstructured":"Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9325_CR47","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 315\u2013323"},{"key":"9325_CR48","doi-asserted-by":"crossref","unstructured":"Yang L, Fan Y, Xu N (2019) Video instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5187\u20135196","DOI":"10.1109\/ICCV.2019.00529"},{"key":"9325_CR49","doi-asserted-by":"crossref","unstructured":"Caelles S, Montes A, Maninis K, Chen Y, Gool LV, Perazzi F, Pont-Tuset J (2018) The 2018 DAVIS challenge on video object segmentation. arXiv preprint arXiv:1803.00557","DOI":"10.1109\/CVPR.2017.565"},{"key":"9325_CR50","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09325-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-09325-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09325-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T20:11:22Z","timestamp":1709842282000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-09325-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,3]]},"references-count":50,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["9325"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-09325-y","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2024,1,3]]},"assertion":[{"value":"9 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}