{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:32:01Z","timestamp":1780104721345,"version":"3.54.0"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"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":["62106214"],"award-info":[{"award-number":["62106214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F2019203195"],"award-info":[{"award-number":["F2019203195"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11063-023-11257-6","type":"journal-article","created":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T18:01:18Z","timestamp":1689444078000},"page":"7211-7225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Guidance and Attention-Refined Network for Fast Video Object Segmentation"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1032-9910","authenticated-orcid":false,"given":"Yaqian","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moran","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cunjun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,15]]},"reference":[{"key":"11257_CR1","doi-asserted-by":"crossref","unstructured":"Bao L, Wu B, Liu w (2018) CNN in MRF: video object segmentation via inference in a CNN-based higher-order spatio-temporal MRF\u2019. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 5977\u20135986","DOI":"10.1109\/CVPR.2018.00626"},{"key":"11257_CR2","doi-asserted-by":"crossref","unstructured":"Caelles S et al (2017) One-shot video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 5320\u20135329","DOI":"10.1109\/CVPR.2017.565"},{"key":"11257_CR3","doi-asserted-by":"crossref","unstructured":"Chen X et al (2020) State-aware tracker for real-time video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 9384\u20139393","DOI":"10.1109\/CVPR42600.2020.00940"},{"key":"11257_CR4","doi-asserted-by":"crossref","unstructured":"Cheng J et al (2018) Fast and accurate online video object segmentation via tracking parts. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 7415\u20137424","DOI":"10.1109\/CVPR.2018.00774"},{"key":"11257_CR5","doi-asserted-by":"crossref","unstructured":"Ci H, Wang C, Wang Y (2018) Video object segmentation by learning location-sensitive embeddings. In: European conference on computer vision (ECCV). Springer, pp 524\u2013539","DOI":"10.1007\/978-3-030-01252-6_31"},{"key":"11257_CR6","doi-asserted-by":"crossref","unstructured":"Dai Y et al (2021) Attentional feature fusion. In: IEEE winter conference on applications of computer vision, pp 3560\u20133569","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"11257_CR7","doi-asserted-by":"crossref","unstructured":"Duarte K, Rawat YS, Shah M (2019) CapsuleVOS: semi-supervised video object segmentation using capsule routing. In: IEEE international conference on computer vision (ICCV), pp 8479\u20138488","DOI":"10.1109\/ICCV.2019.00857"},{"key":"11257_CR8","doi-asserted-by":"crossref","unstructured":"Duke B et al (2021) Sstvos: sparse spatiotemporal transformers for video object segmentation. In: EEE conference on computer vision and pattern recognition (CVPR), pp 5912\u20135921","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"11257_CR9","doi-asserted-by":"crossref","unstructured":"Ge W, Lu X, Shen J (2021) Video object segmentation using global and instance embedding learning. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 16836\u201316845","DOI":"10.1109\/CVPR46437.2021.01656"},{"key":"11257_CR10","doi-asserted-by":"crossref","unstructured":"Zhou Q et al (2019) Motion-guided spatial time attention for video object segmentation. In: IEEE international conference on computer vision (ICCV) workshops, pp 693\u2013696","DOI":"10.1109\/ICCVW.2019.00084"},{"key":"11257_CR11","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"11257_CR12","doi-asserted-by":"crossref","unstructured":"Hu L et al. (2021) \u201cLearning Position and Target Consistency for Memory-Based Video Object Segmentation\u201d. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 4144\u2013 4154","DOI":"10.1109\/CVPR46437.2021.00413"},{"key":"11257_CR13","doi-asserted-by":"crossref","unstructured":"Jampani V, Gadde R, Gehler PV (2017) Video propagation networks. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 3154\u20133164","DOI":"10.1109\/CVPR.2017.336"},{"key":"11257_CR14","unstructured":"JPont-Tuset J et al (2017) The 2017 DAVIS challenge on video object segmentation. arXiv eprints arXiv:1704.00675"},{"issue":"9","key":"11257_CR15","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1007\/s11263-019-01164-6","volume":"127","author":"A Khoreva","year":"2019","unstructured":"Khoreva A et al (2019) Lucid data dreaming for video object segmentation. Int J Comput Vis 127(9):1175\u20131197","journal-title":"Int J Comput Vis"},{"key":"11257_CR16","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. In: Computer Science"},{"issue":"6","key":"11257_CR17","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1109\/TPAMI.2018.2838670","volume":"41","author":"KK Maninis","year":"2018","unstructured":"Maninis KK et al (2018) Video object segmentation without temporal information. IEEE Trans Pattern Anal Mach Intell 41(6):1515\u20131530","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11257_CR18","doi-asserted-by":"crossref","unstructured":"Li L et al (2022) Locality-aware inter-and intra-video reconstruction for self-supervised correspondence learning. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 8709\u20138720","DOI":"10.1109\/CVPR52688.2022.00852"},{"key":"11257_CR19","doi-asserted-by":"crossref","unstructured":"Li X, Change Loy C (2018) Video object segmentation with joint re-identification and attention-aware mask propagation. In: European conference on computer vision (ECCV). Springer, pp 90\u2013105","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"11257_CR20","doi-asserted-by":"crossref","unstructured":"Li Y, Shen Z, Shan Y (2020) Fast video object segmentation using the global context module. In: European conference on computer vision (ECCV), vol 12355. Springer, pp 735\u2013750","DOI":"10.1007\/978-3-030-58607-2_43"},{"key":"11257_CR21","unstructured":"Liang Y et al (2020) Video object segmentation with adaptive feature bank and uncertain-region refinement. In: Conference and workshop on neural information processing systems (NIPS)"},{"key":"11257_CR22","doi-asserted-by":"crossref","unstructured":"Lu X et al (2020) Learning video object segmentation from unlabeled videos. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 8960\u20138970","DOI":"10.1109\/CVPR42600.2020.00898"},{"key":"11257_CR23","doi-asserted-by":"crossref","unstructured":"Lu X et al (2020) Video object segmentation with episodic graph memory networks. In: European conference on computer vision (ECCV). Springer, pp 661\u2013679","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"11257_CR24","doi-asserted-by":"crossref","unstructured":"Luiten J, Voigtlaender P, Leibe B (2018) PReMVOS: proposal-generation, refinement and merging for video object segmentation. In: Asian conference on computer vision. vol 11364. Lecture Notes in Computer Science, pp 565\u2013580","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"11257_CR25","doi-asserted-by":"crossref","unstructured":"Martin DR, Fowlkes CC, Malik J (2004) Learning to detect natural image boundaries using local brightness, color, and texture cues . In: IEEE transactions on pattern analysis and machine intelligence 26.5, pp 530\u2013549","DOI":"10.1109\/TPAMI.2004.1273918"},{"key":"11257_CR26","doi-asserted-by":"crossref","unstructured":"Misra D et al (2021) Rotate to attend: convolutional triplet attention module. In: IEEE winter conference on applications of computer vision, pp 3139\u20133148","DOI":"10.1109\/WACV48630.2021.00318"},{"key":"11257_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/b98874","volume-title":"Numerical optimization","author":"J Nocedal","year":"1999","unstructured":"Nocedal J, Wright SJ (1999) Numerical optimization. Springer, Berlin"},{"key":"11257_CR28","doi-asserted-by":"crossref","unstructured":"Oh S et al (2018) Fast video object segmentation by reference-guided mask propagation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 7376\u20137385","DOI":"10.1109\/CVPR.2018.00770"},{"key":"11257_CR29","doi-asserted-by":"crossref","unstructured":"Oh SW et al (2019) Video object segmentation using space-time memory networks. In: IEEE international conference on computer vision (ICCV), pp 9225\u20139234","DOI":"10.1109\/ICCV.2019.00932"},{"key":"11257_CR30","doi-asserted-by":"crossref","unstructured":"Ohnander J et al (2019) A generative appearance model for end-to-end video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 8953\u2013 8962","DOI":"10.1109\/CVPR.2019.00916"},{"key":"11257_CR31","doi-asserted-by":"crossref","unstructured":"Perazzi F et al (2016) A benchmark dataset and evaluation methodology for video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 724\u2013732","DOI":"10.1109\/CVPR.2016.85"},{"key":"11257_CR32","doi-asserted-by":"crossref","unstructured":"Perazzi F et al (2017) Learning video object segmentation from static images. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 3491\u20133500","DOI":"10.1109\/CVPR.2017.372"},{"key":"11257_CR33","doi-asserted-by":"crossref","unstructured":"Robinson A et al (2020) Learning fast and robust target models for video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 7406\u20137415","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"11257_CR34","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention. vol 9351. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11257_CR35","doi-asserted-by":"crossref","unstructured":"Seong H, Hyun J, Kim E (2020) Kernelized memory network for video object segmentation. In: European conference on computer vision (ECCV). Springer, pp 629\u2013645","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"11257_CR36","unstructured":"Shewchuk JR et al (1994) An introduction to the conjugate gradient method without the agonizing pain. In: Technical Report"},{"key":"11257_CR37","doi-asserted-by":"crossref","unstructured":"Yoon JS et al (2017) Pixel-level matching for video object segmentation using convolutional neural networks. In: IEEE international conference on computer vision (ICCV), pp 2186\u20132195","DOI":"10.1109\/ICCV.2017.238"},{"issue":"8","key":"11257_CR38","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.1109\/TPAMI.2018.2884990","volume":"41","author":"H Tjaden","year":"2018","unstructured":"Tjaden H et al (2018) A region-based gauss-newton approach to real-time monocular multiple object tracking. IEEE Trans Pattern Anal Mach Intell 41(8):1797\u20131812","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11257_CR39","doi-asserted-by":"crossref","unstructured":"Voigtlaender P, Leibe B (2017) Online adaptation of convolutional neural networks for video object segmentation. In: The British machine vision conference (BMVC), pp 116.1\u2013116.13","DOI":"10.5244\/C.31.116"},{"key":"11257_CR40","doi-asserted-by":"crossref","unstructured":"Voigtlaender P et al (2019) FEELVOS: fast end-to-end embedding learning for video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 9481\u2013 9490","DOI":"10.1109\/CVPR.2019.00971"},{"issue":"4","key":"11257_CR41","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/TPAMI.2018.2819173","volume":"41","author":"W Wang","year":"2018","unstructured":"Wang W et al (2018) Semi-supervised video object segmentation with super-trajectories. IEEE Trans Pattern Anal Mach Intell 41(4):985\u2013998","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11257_CR42","doi-asserted-by":"crossref","unstructured":"Wang Z et al (2019) RANet: ranking attention network for fast video object segmentation. In: IEEE international conference on computer vision (ICCV), pp 3977\u20133986","DOI":"10.1109\/ICCV.2019.00408"},{"key":"11257_CR43","doi-asserted-by":"crossref","unstructured":"Woo S et al (2018) CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11257_CR44","doi-asserted-by":"crossref","unstructured":"Xiao H et al (2018) MoNet: deep motion exploitation for video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1140\u20131148","DOI":"10.1109\/CVPR.2018.00125"},{"issue":"5","key":"11257_CR45","first-page":"1205","volume":"42","author":"H Xiao","year":"2019","unstructured":"Xiao H et al (2019) Online meta adaptation for fast video object segmentation. IEEE Trans Pattern Anal Mach Intell 42(5):1205\u20131217","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11257_CR46","unstructured":"Xu N et al (2018) YouTube-VOS: a large-scale video object segmentation benchmark. arXiv e-prints , arXiv: 1809.03327"},{"key":"11257_CR47","doi-asserted-by":"crossref","unstructured":"Yang C et al (2021) Self-supervised video object segmentation by motion grouping. In: IEEE international conference on computer vision (CVPR), pp 7177\u20137188","DOI":"10.1109\/ICCV48922.2021.00709"},{"key":"11257_CR48","doi-asserted-by":"crossref","unstructured":"Yang L et al (2018) Efficient video object segmentation via network modulation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6499\u20136507","DOI":"10.1109\/CVPR.2018.00680"},{"key":"11257_CR49","doi-asserted-by":"crossref","unstructured":"Yang L et al (2018) Efficient video object segmentation via network modulation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6499\u20136507","DOI":"10.1109\/CVPR.2018.00680"},{"issue":"8","key":"11257_CR50","doi-asserted-by":"publisher","first-page":"3884","DOI":"10.1109\/TNNLS.2021.3054769","volume":"33","author":"Y Yin","year":"2021","unstructured":"Yin Y et al (2021) Directional deep embedding and appearance learning for fast video object segmentation. IEEE Trans Neural Netw Learn Syst 33(8):3884\u20133894","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"11257_CR51","doi-asserted-by":"crossref","unstructured":"Zhang L et al (2019) Fast video object segmentation via dynamic targeting network. In: IEEE international conference on computer vision (ICCV), pp 5581\u20135590","DOI":"10.1109\/ICCV.2019.00568"},{"key":"11257_CR52","doi-asserted-by":"crossref","unstructured":"Zhang Y et al (2020) A transductive approach for video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6947\u20136956","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"11257_CR53","doi-asserted-by":"crossref","unstructured":"Zhang Y et al (2020) A transductive approach for video object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6949\u20136958","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"11257_CR54","unstructured":"Zhou T et al (2022) A survey on deep learning technique for video segmentation. In: IEEE transactions on pattern analysis and machine intelligence, pp 1\u201320"},{"key":"11257_CR55","doi-asserted-by":"publisher","first-page":"8326","DOI":"10.1109\/TIP.2020.3013162","volume":"29","author":"Tianfei Zhou","year":"2020","unstructured":"Zhou Tianfei et al (2020) MATNet: motion-attentive transition network for zero-shot video object segmentation. IEEE Trans Image Process 29:8326\u20138338","journal-title":"IEEE Trans Image Process"},{"key":"11257_CR56","doi-asserted-by":"crossref","unstructured":"Zhou T et al (2021) Target-aware object discovery and association for unsupervised video multi- object segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6985\u20136994","DOI":"10.1109\/CVPR46437.2021.00691"},{"key":"11257_CR57","doi-asserted-by":"crossref","unstructured":"Zhou Z et al (2019) Enhanced memory network for video segmentation. In: IEEE international conference on computer vision (ICCV) workshops, pp 689\u2013692","DOI":"10.1109\/ICCVW.2019.00083"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11257-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-023-11257-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11257-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T19:22:12Z","timestamp":1698520932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-023-11257-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,15]]},"references-count":57,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["11257"],"URL":"https:\/\/doi.org\/10.1007\/s11063-023-11257-6","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,15]]},"assertion":[{"value":"13 March 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}