{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T23:55:43Z","timestamp":1772236543779,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T00:00:00Z","timestamp":1661472000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T00:00:00Z","timestamp":1661472000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11063-022-11016-z","type":"journal-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T08:03:09Z","timestamp":1661500989000},"page":"3411-3428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Refine-FPN: Instance Segmentation Based on a Non-local Multi-feature Aggregation Mechanism"],"prefix":"10.1007","volume":"55","author":[{"given":"Xiaolian","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7001-5775","authenticated-orcid":false,"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ke","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,26]]},"reference":[{"key":"11016_CR1","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"issue":"7","key":"11016_CR2","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1109\/TII.2018.2884211","volume":"15","author":"C Hong","year":"2018","unstructured":"Hong C, Yu J, Zhang J et al (2018) Multimodal face-pose estimation with multitask manifold deep learning. IEEE Trans Industr Inf 15(7):3952\u20133961","journal-title":"IEEE Trans Industr Inf"},{"issue":"2","key":"11016_CR3","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1109\/TPAMI.2019.2932058","volume":"44","author":"J Yu","year":"2019","unstructured":"Yu J, Tan M, Zhang H et al (2019) Hierarchical deep click feature prediction for fine-grained image recognition. IEEE Trans Pattern Anal Mach Intell 44(2):563\u2013578","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11016_CR4","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H et al (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"11016_CR5","doi-asserted-by":"crossref","unstructured":"Chen K, Pang J, Wang J et al (2019) Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 4974\u20134983","DOI":"10.1109\/CVPR.2019.00511"},{"key":"11016_CR6","doi-asserted-by":"crossref","unstructured":"Chen H, Sun K, Tian Z et al (2020) Blendmask: Top-down meets bottom-up for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 8573\u20138581","DOI":"10.1109\/CVPR42600.2020.00860"},{"issue":"4","key":"11016_CR7","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1109\/TCYB.2020.2969046","volume":"51","author":"J Yu","year":"2020","unstructured":"Yu J, Yao J, Zhang J et al (2020) SPRNet: single-pixel reconstruction for one-stage instance segmentation. IEEE Trans Cybern 51(4):1731\u20131742","journal-title":"IEEE Trans Cybern"},{"key":"11016_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107952","volume":"116","author":"J Zhang","year":"2021","unstructured":"Zhang J, Cao Y, Wu Q (2021) Vector of locally and adaptively aggregated descriptors for image feature representation. Pattern Recogn 116:107952","journal-title":"Pattern Recogn"},{"issue":"5","key":"11016_CR9","doi-asserted-by":"publisher","first-page":"3117","DOI":"10.1002\/int.22814","volume":"37","author":"J Zhang","year":"2022","unstructured":"Zhang J, Yang J, Yu J et al (2022) Semisupervised image classification by mutual learning of multiple self-supervised models. Int J Intell Syst 37(5):3117\u20133141","journal-title":"Int J Intell Syst"},{"key":"11016_CR10","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"},{"key":"11016_CR11","doi-asserted-by":"crossref","unstructured":"Lin T Y, 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":"11016_CR12","doi-asserted-by":"crossref","unstructured":"Lin T Y, Maire M, Belongie S et al (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, Cham, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"11016_CR13","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"11016_CR14","doi-asserted-by":"crossref","unstructured":"Lin T Y, Goyal P, Girshick R et al (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"11016_CR15","unstructured":"Ren S, He K, Girshick R et al (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inform Process Syst 28"},{"key":"11016_CR16","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"11016_CR17","doi-asserted-by":"crossref","unstructured":"Fang Y, Yang S, Wang X et al (2021) Instances as queries. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 6910\u20136919","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"11016_CR18","unstructured":"O Pinheiro PO, Collobert R, Doll\u00e1r P (2015) Learning to segment object candidates. Adv Neural Inform Process Syst 28"},{"key":"11016_CR19","doi-asserted-by":"crossref","unstructured":"Pinheiro PO, Lin TY, Collobert R et al (2016) Learning to refine object segments. In: European conference on computer vision. Springer, Cham, pp 75\u201391","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"11016_CR20","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Lerer A, Lin T Y et al (2016) A multipath network for object detection. arXiv preprint arXiv:1604.02135","DOI":"10.5244\/C.30.15"},{"key":"11016_CR21","doi-asserted-by":"crossref","unstructured":"Dai J, He K, Sun J (2016) Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 3150\u20133158","DOI":"10.1109\/CVPR.2016.343"},{"key":"11016_CR22","doi-asserted-by":"crossref","unstructured":"Li Y, Qi H, Dai J et al (2017) Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 2359\u20132367","DOI":"10.1109\/CVPR.2017.472"},{"key":"11016_CR23","doi-asserted-by":"crossref","unstructured":"Dai J, He K, Li Y et al (2016) Instance-sensitive fully convolutional networks. In: European conference on computer vision. Springer, Cham, pp 534\u2013549","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"11016_CR24","doi-asserted-by":"crossref","unstructured":"Chen LC, Hermans A, Papandreou G et al (2018) Masklab: instance segmentation by refining object detection with semantic and direction features. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4013\u20134022","DOI":"10.1109\/CVPR.2018.00422"},{"key":"11016_CR25","doi-asserted-by":"crossref","unstructured":"Kirillov A, Levinkov E, Andres B et al (2017) Instancecut: from edges to instances with multicut. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 5008\u20135017","DOI":"10.1109\/CVPR.2017.774"},{"key":"11016_CR26","doi-asserted-by":"crossref","unstructured":"Liu S, Jia J, Fidler S et al (2017) Sgn: sequential grouping networks for instance segmentation. In: Proceedings of the IEEE international conference on computer vision. pp. 3496\u20133504","DOI":"10.1109\/ICCV.2017.378"},{"key":"11016_CR27","doi-asserted-by":"crossref","unstructured":"Uhrig J, Cordts M, Franke U et al (2016) Pixel-level encoding and depth layering for instance-level semantic labeling. In: German conference on pattern recognition. Springer, Cham, pp 14\u201325","DOI":"10.1007\/978-3-319-45886-1_2"},{"key":"11016_CR28","doi-asserted-by":"crossref","unstructured":"De Brabandere B, Neven D, Van Gool L (2017) Semantic instance segmentation with a discriminative loss function. arXiv preprint arXiv:1708.02551","DOI":"10.1109\/CVPRW.2017.66"},{"key":"11016_CR29","unstructured":"Newell A, Huang Z, Deng J (2017) Associative embedding: end-to-end learning for joint detection and grouping. Adv Neural Inform Process Syst 30"},{"key":"11016_CR30","unstructured":"Fathi A, Wojna Z, Rathod V et al (2017) Semantic instance segmentation via deep metric learning. arXiv preprint arXiv:1703.10277"},{"key":"11016_CR31","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D et al (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"11016_CR32","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"11016_CR33","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin T Y, Le QV (2019) Nas-fpn: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 7036\u20137045","DOI":"10.1109\/CVPR.2019.00720"},{"key":"11016_CR34","doi-asserted-by":"crossref","unstructured":"Guo C, Fan B, Zhang Q et al (2020) Augfpn: improving multi-scale feature learning for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 12595\u201312604","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"11016_CR35","doi-asserted-by":"crossref","unstructured":"Qiao S, Chen LC, Yuille A (2021) Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 10213\u201310224","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"11016_CR36","doi-asserted-by":"crossref","unstructured":"Hu M, Li Y, Fang L et al (2021) A2-FPN: attention aggregation based feature pyramid network for instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 15343\u201315352","DOI":"10.1109\/CVPR46437.2021.01509"},{"key":"11016_CR37","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. Adv Neural Inform Process Systems 30"},{"key":"11016_CR38","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A et al (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"11016_CR39","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"11016_CR40","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H et al (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"11016_CR41","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Huang L et al (2019) Ccnet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"key":"11016_CR42","doi-asserted-by":"crossref","unstructured":"Cao Y, Xu J, Lin S et al (2019) Gcnet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"11016_CR43","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":"11016_CR44","doi-asserted-by":"crossref","unstructured":"Gupta A, Dollar P, Girshick R (2019) Lvis: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 5356\u20135364","DOI":"10.1109\/CVPR.2019.00550"},{"key":"11016_CR45","unstructured":"Chen K, Wang J, Pang J et al (2019) MMDetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155"},{"key":"11016_CR46","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P et al (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"key":"11016_CR47","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X et al (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-11016-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-11016-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-11016-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T12:14:26Z","timestamp":1688818466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-11016-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,26]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["11016"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-11016-z","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,26]]},"assertion":[{"value":"17 August 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}