{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:52:59Z","timestamp":1761126779776,"version":"3.37.3"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,3,2]],"date-time":"2022-03-02T00:00:00Z","timestamp":1646179200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,2]],"date-time":"2022-03-02T00:00:00Z","timestamp":1646179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100011789","name":"Department of Science and Technology of Jilin Province","doi-asserted-by":"publisher","award":["20210201077GX","20200401086GX","20200401081GX","20200201199JC"],"award-info":[{"award-number":["20210201077GX","20200401086GX","20200401081GX","20200201199JC"]}],"id":[{"id":"10.13039\/501100011789","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61907007","62107009"],"award-info":[{"award-number":["61907007","62107009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2020YFA0714102"],"award-info":[{"award-number":["2020YFA0714102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2412020FZ029","2412020FZ031","2412019FZ049"],"award-info":[{"award-number":["2412020FZ029","2412020FZ031","2412019FZ049"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s10489-022-03382-x","type":"journal-article","created":{"date-parts":[[2022,3,2]],"date-time":"2022-03-02T13:02:51Z","timestamp":1646226171000},"page":"14053-14069","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Bottom-up improved multistage temporal convolutional network for action segmentation"],"prefix":"10.1007","volume":"52","author":[{"given":"Wenhe","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yuan","family":"Chai","sequence":"additional","affiliation":[]},{"given":"Miao","family":"Qi","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Pu","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Kong","sequence":"additional","affiliation":[]},{"given":"Caixia","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,2]]},"reference":[{"key":"3382_CR1","first-page":"34","volume-title":"European Conference on Computer Vision (ECCV)","author":"Z Wang","year":"2020","unstructured":"Wang Z, Gao Z, Wang L, Li Z, Wu G (2020) Boundary-Aware Cascade Networks for Temporal Action Segmentation. In: European Conference on Computer Vision (ECCV), pp 34\u201351"},{"key":"3382_CR2","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.jnca.2015.11.016","volume":"60","author":"M Ahmed","year":"2016","unstructured":"Ahmed M, Mahmood AN, Hu J (2016) A survey of network anomaly detection techniques. J Netw Comput Appl 60:19\u201331","journal-title":"J Netw Comput Appl"},{"doi-asserted-by":"crossref","unstructured":"Liu H, Fang S, Zhang Z, Li D, Lin K, Wang J (2021) MFDNet: collaborative poses perception and matrix fisher distribution for head pose estimation. IEEE Transactions on Multimedia:1\u20131","key":"3382_CR3","DOI":"10.1109\/TMM.2021.3081873"},{"key":"3382_CR4","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.neucom.2021.03.122","volume":"455","author":"D Li","year":"2021","unstructured":"Li D, Liu H, Zhang Z, Lin K, Fang S, Li Z, Xiong NN (2021) CARM: confidence-aware recommender model via review representation learning and historical rating behavior in the online platforms. Neurocomputing 455:283\u2013296","journal-title":"Neurocomputing"},{"key":"3382_CR5","first-page":"1906","volume":"33","author":"X Shen","year":"2021","unstructured":"Shen X, Yi B, Liu H, Zhang W, Zhang Z, Liu S et al (2021) Deep Variational matrix factorization with knowledge embedding for recommendation system. IEEE Trans Knowl Data Eng 33:1906\u20131918","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3382_CR6","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1109\/TMECH.2018.2870056","volume":"24","author":"T Liu","year":"2019","unstructured":"Liu T, Liu H, Li Y, Zhang Z, Liu S (2019) Efficient blind signal reconstruction with wavelet transforms regularization for educational robot infrared vision sensing. IEEE\/ASME Transactions on Mechatronics 24:384\u2013394","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"key":"3382_CR7","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1109\/TII.2019.2934728","volume":"16","author":"T Liu","year":"2020","unstructured":"Liu T, Liu H, Li Y, Chen Z, Zhang Z-l, Liu S (2020) Flexible FTIR spectral imaging enhancement for industrial robot infrared vision sensing. IEEE Transactions on Industrial Informatics 16:544\u2013554","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"3382_CR8","doi-asserted-by":"publisher","first-page":"4941","DOI":"10.1109\/TIP.2019.2917283","volume":"28","author":"B Xu","year":"2019","unstructured":"Xu B, Ye H, Zheng Y, Wang H, Luwang T, Jiang Y (2019) Dense dilated network for video action recognition. IEEE Trans Image Process 28:4941\u20134953","journal-title":"IEEE Trans Image Process"},{"key":"3382_CR9","first-page":"3468","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"C Feichtenhofer","year":"2016","unstructured":"Feichtenhofer C, Pinz A, Wildes R (2016) Spatiotemporal residual networks for video action recognition. In: Advances in Neural Information Processing Systems (NIPS), pp 3468\u20133476"},{"key":"3382_CR10","doi-asserted-by":"publisher","first-page":"4724","DOI":"10.1109\/CVPR.2017.502","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"J Carreira","year":"2017","unstructured":"Carreira J, Zisserman A (2017) Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4724\u20134733"},{"key":"3382_CR11","doi-asserted-by":"publisher","first-page":"6201","DOI":"10.1109\/ICCV.2019.00630","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"C Feichtenhofer","year":"2019","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) SlowFast Networks for Video Recognition. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 6201\u20136210"},{"key":"3382_CR12","doi-asserted-by":"publisher","first-page":"2589","DOI":"10.1007\/s10489-020-01905-y","volume":"51","author":"X Zhang","year":"2021","unstructured":"Zhang X, Huang Y, Mi Y, Pei Y, Zou Q, Wang S (2021) Video sketch: a middle-level representation for action recognition. Appl Intell 51:2589\u20132608","journal-title":"Appl Intell"},{"key":"3382_CR13","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1007\/s10489-018-1347-3","volume":"49","author":"G Yao","year":"2018","unstructured":"Yao G, Lei T, Zhong J, Jiang P (2018) Learning multi-temporal-scale deep information for action recognition. Appl Intell 49:2017\u20132029","journal-title":"Appl Intell"},{"key":"3382_CR14","doi-asserted-by":"publisher","first-page":"2515","DOI":"10.1007\/s10489-018-1395-8","volume":"49","author":"M Majd","year":"2018","unstructured":"Majd M, Safabakhsh R (2018) A motion-aware ConvLSTM network for action recognition. Appl Intell 49:2515\u20132521","journal-title":"Appl Intell"},{"key":"3382_CR15","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1007\/s10489-020-01803-3","volume":"51","author":"C Ding","year":"2020","unstructured":"Ding C, Liu K, Cheng F, Belyaev E (2020) Spatio-temporal attention on manifold space for 3D human action recognition. Appl Intell 51:560\u2013570","journal-title":"Appl Intell"},{"key":"3382_CR16","doi-asserted-by":"publisher","first-page":"9451","DOI":"10.1109\/CVPR42600.2020.00947","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"M-H Chen","year":"2020","unstructured":"Chen M-H, Li B, Bao SY-Z, Al-Regib G, Kira Z (2020) Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9451\u20139460"},{"key":"3382_CR17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2020.2973153","volume":"PP","author":"S Li","year":"2020","unstructured":"Li S, Farha YA, Liu Y, Cheng M-M, Gall J (2020) MS-TCN++: multi-stage temporal convolutional network for action segmentation. IEEE Trans Pattern Anal Mach Intell PP:1","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3382_CR18","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1109\/CVPR.2017.113","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"CS Lea","year":"2017","unstructured":"Lea CS, Flynn MD, Vidal R, Reiter A, Hager G (2017) Temporal Convolutional Networks for Action Segmentation and Detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1003\u20131012"},{"key":"3382_CR19","first-page":"68","volume-title":"European conference on computer vision (ECCV)","author":"J Gao","year":"2018","unstructured":"Gao J, Chen K, Nevatia R (2018) Ctap: Complementary temporal action proposal generation. In: European conference on computer vision (ECCV), pp 68\u201383"},{"key":"3382_CR20","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.imavis.2019.04.007","volume":"87","author":"Hendry","year":"2019","unstructured":"Hendry, Chen RC (2019) Automatic License Plate Recognition via sliding-window darknet-YOLO deep learning. Image Vis. Comput 87:47\u201356","journal-title":"Image Vis. Comput"},{"key":"3382_CR21","first-page":"36","volume-title":"European Conference on Computer Vision (ECCV)","author":"C Lea","year":"2016","unstructured":"Lea C, Reiter A, Vidal R, Hager GD (2016) Segmental spatiotemporal CNNs for fine-grained action segmentation. In: European Conference on Computer Vision (ECCV), pp 36\u201352"},{"key":"3382_CR22","doi-asserted-by":"publisher","first-page":"5987","DOI":"10.1109\/CVPR.2018.00627","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A Richard","year":"2018","unstructured":"Richard A, Kuehne H, Gall J (2018) Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 5987\u20135996"},{"key":"3382_CR23","first-page":"1","volume-title":"2016 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"H Kuehne","year":"2016","unstructured":"Kuehne H, Gall J, Serre T (2016) An end-to-end generative framework for video segmentation and recognition. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp 1\u20138"},{"key":"3382_CR24","doi-asserted-by":"publisher","first-page":"3570","DOI":"10.1109\/CVPR.2019.00369","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"YA Farha","year":"2019","unstructured":"Farha YA, Gall J (2019) MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 3570\u20133579"},{"key":"3382_CR25","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/WACV48630.2021.00237","volume-title":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Y Ishikawa","year":"2021","unstructured":"Ishikawa Y, Kasai S, Aoki Y, Kataoka H (2021) Alleviating Over-segmentation Errors by Detecting Action Boundaries. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp 2321\u20132330"},{"key":"3382_CR26","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2018","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille A (2018) DeepLab: semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40:834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3382_CR27","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1109\/WACV.2018.00163","volume-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"P Wang","year":"2018","unstructured":"Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X et al (2018) Understanding Convolution for Semantic Segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp 1451\u20131460"},{"key":"3382_CR28","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1109\/WACV.2018.00162","volume-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"R Hamaguchi","year":"2018","unstructured":"Hamaguchi R, Fujita A, Nemoto K, Imaizumi T, Hikosaka S (2018) Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp 1442\u20131450"},{"key":"3382_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10618-021-00765-5","volume":"35","author":"Z Wang","year":"2021","unstructured":"Wang Z, Ji S (2021) Smoothed dilated convolutions for improved dense prediction. Data Min Knowl Disc 35:1\u201327","journal-title":"Data Min Knowl Disc"},{"key":"3382_CR30","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1109\/ICME.2019.00166","volume-title":"2019 IEEE International Conference on Multimedia and Expo (ICME)","author":"T Wu","year":"2019","unstructured":"Wu T, Tang S, Zhang R, Cao J, Li J (2019) Tree-Structured Kronecker Convolutional Network for Semantic Segmentation. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp 940\u2013945"},{"key":"3382_CR31","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1109\/CVPR.2017.75","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"F Yu","year":"2017","unstructured":"Yu F, Koltun V, Funkhouser T (2017) Dilated Residual Networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 636\u2013644"},{"key":"3382_CR32","volume-title":"Rethinking Atrous Convolution for Semantic Image Segmentation","author":"L-C Chen","year":"2017","unstructured":"L.-C. Chen, G. Papandreou, F. Schroff, and H. Adam, \"Rethinking Atrous Convolution for Semantic Image Segmentation,\" ArXiv, vol. abs\/1706.05587, 2017"},{"key":"3382_CR33","doi-asserted-by":"publisher","first-page":"12592","DOI":"10.1109\/CVPR42600.2020.01261","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"C Guo","year":"2020","unstructured":"Guo C, Fan B, Zhang Q, Xiang S, Pan C (2020) AugFPN: Improving Multi-Scale Feature Learning for Object Detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 12592\u201312601"},{"key":"3382_CR34","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"T-Y Lin","year":"2020","unstructured":"Lin T-Y, Goyal P, Girshick RB, He K, Doll\u00e1r P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42:318\u2013327","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3382_CR35","first-page":"3281","volume-title":"2011 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A Fathi","year":"2011","unstructured":"Fathi A, Ren X, Rehg JM (2011) Learning to recognize objects in egocentric activities. In: 2011 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 3281\u20133288"},{"key":"3382_CR36","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1145\/2493432.2493482","volume-title":"Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing","author":"S Stein","year":"2013","unstructured":"Stein S, McKenna S (2013) Combining embedded accelerometers with computer vision for recognizing food preparation activities. In: Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing, pp 729\u2013738"},{"key":"3382_CR37","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1109\/CVPR.2014.105","volume-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition","author":"H Kuehne","year":"2014","unstructured":"Kuehne H, Arslan AB, Serre T (2014) The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp 780\u2013787"},{"key":"3382_CR38","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/j.neucom.2020.09.068","volume":"433","author":"H Liu","year":"2021","unstructured":"Liu H, Nie H, Zhang Z, Li Y (2021) Anisotropic angle distribution learning for head pose estimation and attention understanding in human-computer interaction. Neurocomputing 433:310\u2013322","journal-title":"Neurocomputing"},{"doi-asserted-by":"crossref","unstructured":"Li Z, Liu H, Zhang Z, Liu T, Xiong NN (2021) Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Transactions on Neural Networks and Learning Systems","key":"3382_CR39","DOI":"10.1109\/TNNLS.2021.3055147"},{"unstructured":"Zhang Z, Li Z, Liu H, Xiong NN (2020) Multi-scale dynamic convolutional network for knowledge graph embedding. IEEE Ann Hist Comput:1","key":"3382_CR40"},{"key":"3382_CR41","doi-asserted-by":"publisher","first-page":"6742","DOI":"10.1109\/CVPR.2018.00705","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"P Lei","year":"2018","unstructured":"Lei P, Todorovic S (2018) Temporal Deformable Residual Networks for Action Segmentation in Videos. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6742\u20136751"},{"key":"3382_CR42","first-page":"6508","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Ding","year":"2018","unstructured":"Ding L, Xu C (2018) Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6508\u20136516"},{"key":"3382_CR43","doi-asserted-by":"publisher","first-page":"1961","DOI":"10.1109\/CVPR.2016.216","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"B Singh","year":"2016","unstructured":"Singh B, Marks TK, Jones MJ, Tuzel O, Shao M (2016) A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1961\u20131970"},{"key":"3382_CR44","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1109\/CVPR.2017.140","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A Richard","year":"2017","unstructured":"Richard A, Kuehne H, Gall J (2017) Weakly Supervised Action Learning with RNN Based Fine-to-Coarse Modeling. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1273\u20131282"},{"key":"3382_CR45","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1109\/TPAMI.2018.2884469","volume":"42","author":"H Kuehne","year":"2020","unstructured":"Kuehne H, Richard A, Gall J (2020) A hybrid RNN-HMM approach for weakly supervised temporal action segmentation. IEEE Trans Pattern Anal Mach Intell 42:765\u2013779","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3382_CR46","doi-asserted-by":"publisher","first-page":"3131","DOI":"10.1109\/CVPR.2016.341","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A Richard","year":"2016","unstructured":"Richard A, Gall J (2016) Temporal Action Detection Using a Statistical Language Model. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3131\u20133140"},{"key":"3382_CR47","doi-asserted-by":"publisher","first-page":"6281","DOI":"10.1109\/ICCV.2019.00638","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"K-NC Mac","year":"2019","unstructured":"Mac K-NC, Joshi D, Yeh RA, Xiong J, Feris R, Do M (2019) Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 6281\u20136290"},{"key":"3382_CR48","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.cviu.2017.06.004","volume":"163","author":"H Kuehne","year":"2017","unstructured":"Kuehne H, Richard A, Gall J (2017) Weakly supervised learning of actions from transcripts. Comput Vis Image Underst 163:78\u201389","journal-title":"Comput Vis Image Underst"},{"key":"3382_CR49","first-page":"6054","volume-title":"IEEE\/CVF International Conference on Computer Vision (CVPR)","author":"Y Li","year":"2019","unstructured":"Li Y, Chen Y, Wang N, Zhang Z (2019) Scale-aware trident networks for object detection. In: IEEE\/CVF International Conference on Computer Vision (CVPR), pp 6054\u20136063"},{"key":"3382_CR50","first-page":"379","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"J Dai","year":"2016","unstructured":"Dai J, Li Y, He K, Sun J (2016) R-fcn: Object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems (NIPS), pp 379\u2013387"},{"key":"3382_CR51","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39:640\u2013651","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3382_CR52","doi-asserted-by":"publisher","first-page":"18689","DOI":"10.1007\/s11042-018-5653-x","volume":"77","author":"DM Vo","year":"2018","unstructured":"Vo DM, Lee S-W (2018) Semantic image segmentation using fully convolutional neural networks with multi-scale images and multi-scale dilated convolutions. Multimed Tools Appl 77:18689\u201318707","journal-title":"Multimed Tools Appl"},{"key":"3382_CR53","doi-asserted-by":"publisher","first-page":"7151","DOI":"10.1109\/CVPR.2018.00747","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"H Zhang","year":"2018","unstructured":"Zhang H, Dana K, Shi J, Zhang Z, Wang X, Tyagi A et al (2018) Context Encoding for Semantic Segmentation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7151\u20137160"},{"key":"3382_CR54","doi-asserted-by":"publisher","first-page":"4877","DOI":"10.1109\/CVPR.2017.518","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"MA Islam","year":"2017","unstructured":"Islam MA, Rochan M, Bruce NDB, Wang Y (2017) Gated Feedback Refinement Network for Dense Image Labeling. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4877\u20134885"},{"doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, and T. Brox, \"U-net: convolutional networks for biomedical image segmentation,\" in MICCAI, 2015","key":"3382_CR55","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3382_CR56","doi-asserted-by":"publisher","first-page":"5168","DOI":"10.1109\/CVPR.2017.549","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"G Lin","year":"2017","unstructured":"Lin G, Milan A, Shen C, Reid I (2017) RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5168\u20135177"},{"key":"3382_CR57","first-page":"801","volume-title":"European Conference on Computer Vision (ECCV)","author":"L-C Chen","year":"2018","unstructured":"Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: European Conference on Computer Vision (ECCV), pp 801\u2013818"},{"key":"3382_CR58","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1109\/CVPR.2016.91","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"J Redmon","year":"2016","unstructured":"Redmon J, Divvala S, Girshick RB, Farhadi A (2016) You Only Look Once: Unified, Real-Time Object Detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 779\u2013788"},{"key":"3382_CR59","doi-asserted-by":"publisher","first-page":"6517","DOI":"10.1109\/CVPR.2017.690","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"J Redmon","year":"2017","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: Better, Faster, Stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 6517\u20136525"},{"key":"3382_CR60","first-page":"21","volume-title":"European Conference on Computer Vision (ECCV)","author":"W Liu","year":"2016","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed SE, Fu C-Y et al (2016) SSD: Single Shot MultiBox Detector. In: European Conference on Computer Vision (ECCV), pp 21\u201337"},{"key":"3382_CR61","first-page":"3339","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Y Chen","year":"2018","unstructured":"Chen Y, Li W, Sakaridis C, Dai D, Van Gool L (2018) Domain adaptive faster r-cnn for object detection in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3339\u20133348"},{"key":"3382_CR62","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick RB (2020) Mask R-CNN. IEEE Trans Pattern Anal Mach Intell 42:386\u2013397","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3382_CR63","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/CVPR.2017.106","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"T-Y Lin","year":"2017","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick RB, He K, Hariharan B, Belongie SJ (2017) Feature Pyramid Networks for Object Detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 936\u2013944"},{"key":"3382_CR64","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1109\/CVPR.2016.89","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A Shrivastava","year":"2016","unstructured":"Shrivastava A, Gupta A, Girshick RB (2016) Training Region-Based Object Detectors with Online Hard Example Mining. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 761\u2013769"},{"key":"3382_CR65","doi-asserted-by":"publisher","first-page":"7082","DOI":"10.1109\/CVPR.2017.749","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"SR Bul\u00f2","year":"2017","unstructured":"Bul\u00f2 SR, Neuhold G, Kontschieder P (2017) Loss Max-Pooling for Semantic Image Segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 7082\u20137091"},{"key":"3382_CR66","first-page":"8577","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"B Li","year":"2019","unstructured":"Li B, Liu Y, Wang X (2019) Gradient harmonized single-stage detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 8577\u20138584"},{"key":"3382_CR67","doi-asserted-by":"publisher","first-page":"1800","DOI":"10.1109\/CVPR.2017.195","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"F Chollet","year":"2017","unstructured":"Chollet F (2017) Xception: Deep Learning with Depthwise Separable Convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1800\u20131807"},{"key":"3382_CR68","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1109\/ICRA.2016.7487305","volume-title":"2016 IEEE International Conference on Robotics and Automation (ICRA)","author":"CS Lea","year":"2016","unstructured":"Lea CS, Vidal R, Hager G (2016) Learning convolutional action primitives for fine-grained action recognition. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp 1642\u20131649"},{"key":"3382_CR69","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03382-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03382-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03382-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T08:50:01Z","timestamp":1700297401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03382-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,2]]},"references-count":69,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["3382"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03382-x","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2022,3,2]]},"assertion":[{"value":"11 February 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}