{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:18:06Z","timestamp":1785457086884,"version":"3.56.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY19F030005"],"award-info":[{"award-number":["LY19F030005"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY18F020008"],"award-info":[{"award-number":["LY18F020008"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1403200"],"award-info":[{"award-number":["2018YFB1403200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013100","name":"Scientific Research Funds of Jilin Province of Health and Family Planning Commission","doi-asserted-by":"publisher","award":["WKJ-ZJ-1814"],"award-info":[{"award-number":["WKJ-ZJ-1814"]}],"id":[{"id":"10.13039\/501100013100","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007566","name":"City, University of London","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007566","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602407"],"award-info":[{"award-number":["61602407"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572436"],"award-info":[{"award-number":["61572436"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972351"],"award-info":[{"award-number":["61972351"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013141","name":"Jilin Province Key R&D Plan Project","doi-asserted-by":"publisher","award":["2019C01004"],"award-info":[{"award-number":["2019C01004"]}],"id":[{"id":"10.13039\/501100013141","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013141","name":"Jilin Province Key R&D Plan Project","doi-asserted-by":"publisher","award":["2019C03002"],"award-info":[{"award-number":["2019C03002"]}],"id":[{"id":"10.13039\/501100013141","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1016\/j.patcog.2019.107158","type":"journal-article","created":{"date-parts":[[2019,12,14]],"date-time":"2019-12-14T20:36:25Z","timestamp":1576355785000},"page":"107158","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":39,"special_numbering":"C","title":["Joint temporal context exploitation and active learning for video segmentation"],"prefix":"10.1016","volume":"100","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-7416-656X","authenticated-orcid":false,"given":"Yan","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohua","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Judith","family":"Gelernter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-1754-5595","authenticated-orcid":false,"given":"Bailin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.patcog.2019.107158_bib0001","doi-asserted-by":"crossref","first-page":"1531","DOI":"10.1109\/TPAMI.2018.2840724","article-title":"A deep network solution for attention and aesthetics aware photo cropping","volume":"41","author":"Wang","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach.Intelligence"},{"issue":"4","key":"10.1016\/j.patcog.2019.107158_bib0002","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1109\/TPAMI.2018.2819173","article-title":"Semi-supervised video object segmentation with super-trajectories","volume":"41","author":"Wang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach.Intelligence"},{"issue":"12","key":"10.1016\/j.patcog.2019.107158_bib0003","doi-asserted-by":"crossref","first-page":"5933","DOI":"10.1109\/TIP.2016.2616302","article-title":"Real-time superpixel segmentation by dbscan clustering algorithm","volume":"25","author":"Shen","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2019.107158_bib0004","first-page":"1","article-title":"Traffic sign detection using a multi-scale recurrent attention network","author":"Tian","year":"2019","journal-title":"IEEE Trans. Intell. Transp.Syst."},{"key":"10.1016\/j.patcog.2019.107158_bib0005","series-title":"in: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","first-page":"233","article-title":"One shot learning for generic instance segmentation in rgbd videos","author":"Lin","year":"2019"},{"key":"10.1016\/j.patcog.2019.107158_bib0006","series-title":"in: SIBGRAPI Conference on Graphics, Patterns and Images","first-page":"370","article-title":"A meta-learning approach for recommendation of image segmentation algorithms","author":"Campos","year":"2016"},{"issue":"6","key":"10.1016\/j.patcog.2019.107158_bib0007","doi-asserted-by":"crossref","first-page":"2688","DOI":"10.1109\/TIP.2018.2795740","article-title":"Submodular trajectories for better motion segmentation in videos","volume":"27","author":"Shen","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2019.107158_bib0008","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0009","series-title":"in: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","first-page":"2663","article-title":"Learning video object segmentation from static images","author":"Perazzi","year":"2017"},{"key":"10.1016\/j.patcog.2019.107158_bib0010","series-title":"in: Proceedings of the International Conference on Machine Learning","first-page":"1183","article-title":"Deep bayesian active learning with image data","author":"Gal","year":"2017"},{"key":"10.1016\/j.patcog.2019.107158_bib0011","series-title":"in: Proceedings of the European Conference on Computer Vision","first-page":"715","article-title":"Pyramid dilated deeper convlstm for video salient object detection","author":"Song","year":"2018"},{"issue":"3","key":"10.1016\/j.patcog.2019.107158_bib0012","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1007\/s11263-018-1122-2","article-title":"Learning to segment moving objects","volume":"127","author":"Tokmakov","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2019.107158_bib0013","series-title":"in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3064","article-title":"Learning unsupervised video object segmentation through visual attention","author":"Wang","year":"2019"},{"key":"10.1016\/j.patcog.2019.107158_bib0014","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3623","article-title":"See more, know more: Unsupervised video object segmentation with co-attention siamese networks","author":"Lu","year":"2019"},{"key":"10.1016\/j.patcog.2019.107158_bib0015","series-title":"in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5977","article-title":"Cnn in mrf: Video object segmentation via inference in a cnn-based higher-order spatio-temporal mrf","author":"Bao","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0016","series-title":"in: Proceedings of the British Machine Vision Conference","first-page":"417","article-title":"Online adaptation of convolutional neural networks for the 2017 davis challenge on video object segmentation","author":"Voigtlaender","year":"2017"},{"issue":"6","key":"10.1016\/j.patcog.2019.107158_bib0017","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1109\/TPAMI.2018.2838670","article-title":"Video object segmentation without temporal information","volume":"41","author":"Maninis","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach.Intell."},{"key":"10.1016\/j.patcog.2019.107158_bib0018","series-title":"In: The 2018\u00a0DAVIS Challenge on Video Object Segmentation-CVPR Workshops","first-page":"6","article-title":"Premvos: Proposal-generation, refinement and merging for the davis challenge on video object segmentation 2018","author":"Luiten","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_sbref0019","series-title":"in: Proceedings of the International Conference on Computer Vision","article-title":"Ranet: Ranking attention network for fast video object segmentation","author":"Wang","year":"2019"},{"issue":"1","key":"10.1016\/j.patcog.2019.107158_bib0020","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2019.107158_bib0021","series-title":"in: Proceedings of the International Conference on Machine Learning","first-page":"1050","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"Gal","year":"2016"},{"issue":"6","key":"10.1016\/j.patcog.2019.107158_bib0022","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1109\/TFUZZ.2017.2717803","article-title":"Incorporating diversity and informativeness in multiple-instance active learning","volume":"25","author":"Wang","year":"2017","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"1","key":"10.1016\/j.patcog.2019.107158_bib0023","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TCYB.2015.2496974","article-title":"Exploring representativeness and informativeness for active learning","volume":"47","author":"Du","year":"2017","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2019.107158_bib0024","series-title":"in: Proceedings of the European Conference on Computer Vision","first-page":"307","article-title":"Unsupervised hard example mining from videos for improved object detection","author":"Jin","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0025","series-title":"in: Proceedings of the European Conference on Computer Vision","first-page":"355","article-title":"Contour knowledge transfer for salient object detection","author":"Li","year":"2018"},{"issue":"8","key":"10.1016\/j.patcog.2019.107158_bib0026","doi-asserted-by":"crossref","first-page":"3919","DOI":"10.1109\/TIP.2016.2579306","article-title":"Deepsaliency: multi-task deep neural network model for salient object detection","volume":"25","author":"Li","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2019.107158_bib0027","series-title":"in: AAAI Conference on Artificial Intelligence","first-page":"420","article-title":"Multi-scale bidirectional fcn for object skeleton extraction","author":"Yang","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0028","series-title":"in: Proceedings of the ACM international conference on Multimedia","first-page":"439","article-title":"Multi-scale cascade network for salient object detection","author":"Li","year":"2017"},{"key":"10.1016\/j.patcog.2019.107158_bib0029","series-title":"In: International Joint Conferences on Artificial Intelligence","first-page":"3411","article-title":"Saliency transfer: an example-based method for salient object detection","author":"Li","year":"2016"},{"issue":"1","key":"10.1016\/j.patcog.2019.107158_bib0030","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/TIP.2017.2754941","article-title":"Video salient object detection via fully convolutional networks","volume":"27","author":"Wang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2019.107158_bib0034","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/j.patcog.2018.02.006","article-title":"A deeply supervised residual network for hep-2 cell classification via cross-modal transfer learning","volume":"79","author":"Lei","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2019.107158_bib0035","series-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","first-page":"201","article-title":"Models matter, so does training: an empirical study of cnns for optical flow estimation","author":"Sun","year":"2019"},{"key":"10.1016\/j.patcog.2019.107158_bib0036","series-title":"Proceedings of the British Machine Vision Conference","first-page":"278","article-title":"Light-weight refinenet for real-time semantic segmentation","author":"Nekrasov","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0037","series-title":"Proceedings of the International Conference on Pattern Recognition","first-page":"3365","article-title":"Multimodal gesture recognition using densely connected convolution and BLSTM","author":"Li","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0039","series-title":"Symposium on Operating Systems Design and Implementation","first-page":"265","article-title":"Tensorflow","author":"Abadi","year":"2016"},{"key":"10.1016\/j.patcog.2019.107158_bib0040","series-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","first-page":"724","article-title":"A benchmark dataset and evaluation methodology for video object segmentation","author":"Perazzi","year":"2016"},{"key":"10.1016\/j.patcog.2019.107158_bib0041","unstructured":"Shining3d dental data set, 2019, https:\/\/2.zoppoz.workers.dev:443\/https\/drive.google.com\/drive\/folders\/1Jds1LFVK0xuCJ7X9MU0iu97fmeIWuFLu?usp=sharing."},{"key":"10.1016\/j.patcog.2019.107158_bib0042","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"1527","article-title":"Adaptive temporal encoding network for video instance-level human parsing","author":"Zhou","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0043","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"585","article-title":"Youtube-vos: Sequence-to-sequence video object segmentation","author":"Xu","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0044","series-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","first-page":"7376","article-title":"Fast video object segmentation by reference-guided mask propagation","author":"Oh","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0045","series-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","first-page":"1140","article-title":"Monet: Deep motion exploitation for video object segmentation","author":"Xiao","year":"2018"},{"key":"10.1016\/j.patcog.2019.107158_bib0046","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.patrec.2018.08.015","article-title":"Effective integration of morphological analysis and named entity recognition based on a recurrent neural network","volume":"112","author":"Lee","year":"2018","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2019.107158_bib0047","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.patcog.2019.04.025","article-title":"Human trajectory prediction in crowded scene using social-affinity long short-term memory","volume":"93","author":"Pei","year":"2019","journal-title":"Pattern Recognit."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0031320319304583?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0031320319304583?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:45:14Z","timestamp":1777434314000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320319304583"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":43,"alternative-id":["S0031320319304583"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.patcog.2019.107158","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2020,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Joint temporal context exploitation and active learning for video segmentation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.patcog.2019.107158","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2019 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"107158"}}