{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T21:49:25Z","timestamp":1788299365550,"version":"build-2803163510"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"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":["61972121"],"award-info":[{"award-number":["61972121"]}],"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":["61971173"],"award-info":[{"award-number":["61971173"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY21F020015"],"award-info":[{"award-number":["LY21F020015"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY20F020015"],"award-info":[{"award-number":["LY20F020015"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY21F030005"],"award-info":[{"award-number":["LY21F030005"]}]},{"name":"Fundamental Research Funds for the Provincial Universities of Zhejiang"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s00521-022-08190-5","type":"journal-article","created":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T07:03:09Z","timestamp":1673506989000},"page":"9593-9606","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Adaptive receptive field U-shaped temporal convolutional network for vulgar action segmentation"],"prefix":"10.1007","volume":"35","author":[{"given":"Jin","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinnan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5036-9365","authenticated-orcid":false,"given":"Feiwei","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanli","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,12]]},"reference":[{"issue":"1\u20132","key":"8190_CR1","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1080\/10720162.2012.660431","volume":"19","author":"EW Owens","year":"2012","unstructured":"Owens EW, Behun RJ, Manning JC, Reid RC (2012) The Impact of Internet Pornography on Adolescents: A Review of the Research. Sexual Addict Compulsivity 19(1\u20132):99\u2013122","journal-title":"Sexual Addict Compulsivity"},{"key":"8190_CR2","unstructured":"Moustafa M (2015) Applying deep learning to classify pornographic images and videos. arXiv preprint arXiv:1511.08899"},{"key":"8190_CR3","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.neucom.2016.03.099","volume":"213","author":"C Caetano","year":"2016","unstructured":"Caetano C, Avila S, Schwartz WR, Guimar\u00e3es SJF, Ara\u00fajo AdA (2016) A mid-level video representation based on binary descriptors: a case study for pornography detection. Neurocomputing 213:102\u2013114","journal-title":"Neurocomputing"},{"key":"8190_CR4","doi-asserted-by":"crossref","unstructured":"Wang Y, Jin X, Tan X (2016) Pornographic image recognition by strongly-supervised deep multiple instance learning. In: 2016 IEEE international conference on Image processing (ICIP). IEEE, pp 4418\u20134422","DOI":"10.1109\/ICIP.2016.7533195"},{"issue":"5","key":"8190_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3057733","volume":"8","author":"X Ou","year":"2017","unstructured":"Ou X, Ling H, Yu H, Li P, Zou F, Liu S (2017) Adult image and video recognition by a deep multicontext network and fine-to-coarse strategy. ACM Trans Intell Syst Technol TIST 8(5):1\u201325","journal-title":"ACM Trans Intell Syst Technol TIST"},{"key":"8190_CR6","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.neucom.2016.12.017","volume":"230","author":"M Perez","year":"2017","unstructured":"Perez M, Avila S, Moreira D, Moraes D, Testoni V, Valle E, Goldenstein S, Rocha A (2017) Video pornography detection through deep learning techniques and motion information. Neurocomputing 230:279\u2013293","journal-title":"Neurocomputing"},{"key":"8190_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.jvcir.2017.12.005","volume":"50","author":"P Vitorino","year":"2018","unstructured":"Vitorino P, Avila S, Perez M, Rocha A (2018) Leveraging deep neural networks to fight child pornography in the age of social media. J Vis Commun Image Represent 50:303\u2013313","journal-title":"J Vis Commun Image Represent"},{"issue":"11","key":"8190_CR8","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2018) Temporal segment networks for action recognition in videos. IEEE Trans Pattern Anal Mach Intell 41(11):2740\u20132755","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8190_CR9","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, pp 1933\u20131941","DOI":"10.1109\/CVPR.2016.213"},{"issue":"6","key":"8190_CR10","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2017","unstructured":"Varol G, Laptev I, Schmid C (2017) Long-term temporal convolutions for action recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1510\u20131517","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8190_CR11","doi-asserted-by":"crossref","unstructured":"Lea C, Flynn MD, Vidal R, Reiter A, Hager GD (2017) Temporal convolutional networks for action segmentation and detection. In: proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, pp 156\u2013165","DOI":"10.1109\/CVPR.2017.113"},{"key":"8190_CR12","doi-asserted-by":"crossref","unstructured":"Kim TS, Reiter A (2017) Interpretable 3D human action analysis with temporal convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 1623\u20131631","DOI":"10.1109\/CVPRW.2017.207"},{"key":"8190_CR13","doi-asserted-by":"crossref","unstructured":"Chao YW, Vijayanarasimhan S, Seybold B, Ross DA, Deng J, Sukthankar R (2018) Rethinking the faster R-CNN architecture for temporal action localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE Computer Society, Salt Lake City, pp 1130\u20131139","DOI":"10.1109\/CVPR.2018.00124"},{"key":"8190_CR14","doi-asserted-by":"crossref","unstructured":"Mavroudi E, Bhaskara D, Sefati S, Ali H, Vidal R (2018) End-to-end fine-grained action segmentation and recognition using conditional random field models and discriminative sparse coding. In: 2018 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 1558\u20131567","DOI":"10.1109\/WACV.2018.00174"},{"key":"8190_CR15","doi-asserted-by":"crossref","unstructured":"Stein S, McKenna SJ (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. Association for Computing Machinery, NY, pp 729\u2013738","DOI":"10.1145\/2493432.2493482"},{"key":"8190_CR16","doi-asserted-by":"crossref","unstructured":"Li Y, Ye Z, Rehg JM (2015) Delving into egocentric actions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 287\u2013295 10.1109\/CVPR.2015.7298625","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"8190_CR17","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TNNLS.2020.3041018","volume":"33","author":"Z Gao","year":"2020","unstructured":"Gao Z, Guo L, Ren T, Liu AA, Cheng ZY, Chen S (2020) Pairwise two-stream convnets for cross-domain action recognition with small data. IEEE Trans Neural Netw Learn Syst 33:1147\u20131167","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"8190_CR18","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TIP.2020.3038372","volume":"30","author":"Z Gao","year":"2020","unstructured":"Gao Z, Guo L, Guan W, Liu AA, Ren T, Chen S (2020) A pairwise attentive adversarial spatiotemporal network for cross-domain few-shot action recognition-r2. IEEE Trans Image Process 30:767\u2013782","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"8190_CR19","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1109\/TCYB.2017.2647904","volume":"48","author":"M Luo","year":"2017","unstructured":"Luo M, Chang X, Nie L, Yang Y, Hauptmann AG, Zheng Q (2017) An adaptive semisupervised feature analysis for video semantic recognition. IEEE Trans Cybern 48(2):648\u2013660","journal-title":"IEEE Trans Cybern"},{"issue":"4","key":"8190_CR20","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.1109\/TIP.2017.2658957","volume":"26","author":"D Zhang","year":"2017","unstructured":"Zhang D, Han J, Jiang L, Ye S, Chang X (2017) Revealing event saliency in unconstrained video collection. IEEE Trans Image Process 26(4):1746\u20131758","journal-title":"IEEE Trans Image Process"},{"key":"8190_CR21","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.forsciint.2016.09.010","volume":"268","author":"D Moreira","year":"2016","unstructured":"Moreira D, Avila S, Perez M, Moraes D, Testoni V, Valle E, Goldenstein S, Rocha A (2016) Pornography classification: the hidden clues in video space-time. Forensic Sci Int 268:46\u201361","journal-title":"Forensic Sci Int"},{"key":"8190_CR22","unstructured":"Caetano C, Avila S, Guimaraes S, Ara\u00fajo AdA (2014) Pornography detection using BossaNova video descriptor. In: 2014 22nd European signal processing conference (EUSIPCO). IEEE, pp 1681\u20131685"},{"key":"8190_CR23","doi-asserted-by":"crossref","unstructured":"da\u00a0Silva MV, Marana AN (2018) Spatiotemporal CNNs for pornography detection in videos. In: Iberoamerican congress on pattern recognition, Springer, pp 547\u2013555","DOI":"10.1007\/978-3-030-13469-3_64"},{"key":"8190_CR24","doi-asserted-by":"publisher","DOI":"10.1049\/cp:20061978","volume-title":"Multimodal periodicity analysis for illicit content detection in videos","author":"N Rea","year":"2006","unstructured":"Rea N, Lacey G, Dahyot R, Lambe C (2006) Multimodal periodicity analysis for illicit content detection in videos. IET, Lucknow"},{"key":"8190_CR25","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.future.2012.08.012","volume":"31","author":"Y Liu","year":"2014","unstructured":"Liu Y, Yang Y, Xie H, Tang S (2014) Fusing audio vocabulary with visual features for pornographic video detection. Future Generat Comput Syst 31:69\u201376","journal-title":"Future Generat Comput Syst"},{"key":"8190_CR26","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.neucom.2016.12.017","volume":"230","author":"M Perez","year":"2017","unstructured":"Perez M, Avila S, Moreira D, Moraes D, Testoni V, Valle E, Goldenstein S, Rocha A (2017) Video pornography detection through deep learning techniques and motion information. Neurocomputing 230:279\u2013293","journal-title":"Neurocomputing"},{"issue":"5","key":"8190_CR27","first-page":"1174","volume":"13","author":"KH Song","year":"2018","unstructured":"Song KH, Kim YS (2018) Pornographic Video Detection Scheme Using Multimodal Features. J Eng Appl Sci 13(5):1174\u20131182","journal-title":"J Eng Appl Sci"},{"key":"8190_CR28","doi-asserted-by":"publisher","first-page":"3638","DOI":"10.1049\/ipr2.12271","volume":"15","author":"M Mei","year":"2021","unstructured":"Mei M, He F (2021) Multi-label learning based target detecting from multi-frame data. IET Image Process 15:3638\u20133644","journal-title":"IET Image Process"},{"issue":"9","key":"8190_CR29","doi-asserted-by":"publisher","first-page":"11779","DOI":"10.1007\/s11042-018-6735-5","volume":"78","author":"H Yu","year":"2019","unstructured":"Yu H, He F, Pan Y (2019) A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation. Multimed Tools Appl 78(9):11779\u201311798","journal-title":"Multimed Tools Appl"},{"key":"8190_CR30","doi-asserted-by":"crossref","unstructured":"Dai X, Singh B, Zhang G, Davis LS, Qiu\u00a0Chen Y (2017) Temporal Context Network for Activity Localization in Videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp 5793\u20135802","DOI":"10.1109\/ICCV.2017.610"},{"key":"8190_CR31","doi-asserted-by":"crossref","unstructured":"Xu H, Das A, Saenko K (2017) R-C3D: region convolutional 3D network for temporal activity detection. In: Proceedings of the IEEE international conference on computer vision. pp 5783\u20135792","DOI":"10.1109\/ICCV.2017.617"},{"key":"8190_CR32","doi-asserted-by":"crossref","unstructured":"Shou Z, Chan J, Zareian A, Miyazawa K, Chang SF (2017) CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5734\u20135743","DOI":"10.1109\/CVPR.2017.155"},{"key":"8190_CR33","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Shou Z (2017) Single shot temporal action detection. In: Proceedings of the 25th ACM international conference on Multimedia. Association for Computing Machinery, NY, pp 988\u2013996","DOI":"10.1145\/3123266.3123343"},{"key":"8190_CR34","doi-asserted-by":"crossref","unstructured":"Zhao Y, Xiong Y, Wang L, Wu Z, Tang X, Lin D (2017) Temporal action detection with structured segment networks. In: Proceedings of the IEEE international conference on computer vision, pp 2914\u20132923 10.48550\/arXiv.1704.06228","DOI":"10.1109\/ICCV.2017.317"},{"key":"8190_CR35","doi-asserted-by":"crossref","unstructured":"Yang K, Qiao P, Li D, Lv S, Dou Y (2017) TPC: temporal preservation convolutional networks for precise temporal action localization. arXiv: 1708.03280","DOI":"10.1609\/aaai.v32i1.12234"},{"key":"8190_CR36","doi-asserted-by":"crossref","unstructured":"Yan Y, Xu C, Cai D, Corso JJ (2017) Weakly supervised actor-action segmentation via robust multi-task ranking. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 1298\u20131307","DOI":"10.1109\/CVPR.2017.115"},{"key":"8190_CR37","unstructured":"Xu C, Xiong C, Corso JJ (2017) Action understanding with multiple classes of actors. arXiv preprint arXiv:1704.08723"},{"key":"8190_CR38","unstructured":"Lea C, Reiter A, Vidal R, Hager GD (2016) Efficient segmental inference for spatiotemporal modeling of fine-grained actions. arXiv preprint arXiv:1602.02995"},{"key":"8190_CR39","doi-asserted-by":"crossref","unstructured":"Richard A, Kuehne H, Gall J (2017) Weakly supervised action learning with RNN based Fine-to-coarse modeling. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 754\u2013763","DOI":"10.1109\/CVPR.2017.140"},{"issue":"4","key":"8190_CR40","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1109\/TPAMI.2018.2884469","volume":"42","author":"H Kuehne","year":"2018","unstructured":"Kuehne H, Richard A, Gall J (2018) A hybrid RNN-HMM approach for weakly supervised temporal action segmentation. IEEE Trans Pattern Anal Mach Intell 42(4):765\u2013779","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8190_CR41","unstructured":"Li C, Sun S, Min X, Lin W, Nie B, Zhang X (2017) End-to-end learning of deep convolutional neural network for 3D human action recognition. In: 2017 IEEE international conference on multimedia & expo workshops (ICMEW). IEEE, pp 609\u2013612"},{"key":"8190_CR42","doi-asserted-by":"crossref","unstructured":"Singh B, Marks TK, Jones M, Tuzel O, Shao M (2016) A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: IEEE conference on computer vision and pattern recognition (CVPR). pp 1961\u20131970","DOI":"10.1109\/CVPR.2016.216"},{"key":"8190_CR43","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van\u00a0Gool L (2016) Temporal segment networks: towards good practices for deep action recognition. In: European conference on computer vision. Springer, pp 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"8190_CR44","unstructured":"Ding L, Xu C (2017) TricorNet: A hybrid temporal convolutional and recurrent network for video action segmentation. arXiv preprint arXiv:1705.07818"},{"key":"8190_CR45","doi-asserted-by":"crossref","unstructured":"Tian Y, Shi J, Li B, Duan Z, Xu C (2018) Audio-visual event localization in unconstrained videos. In: Proceedings of the European conference on computer vision (ECCV), pp 247\u2013263","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"8190_CR46","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"8190_CR47","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"4","key":"8190_CR48","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) 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"},{"issue":"12","key":"8190_CR49","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8190_CR50","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi SA (2016) V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV). IEEE, pp 565\u2013571","DOI":"10.1109\/3DV.2016.79"},{"key":"8190_CR51","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek \u00d6, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 424\u2013432","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"8190_CR52","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. Las Vegas, IEEE, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8190_CR53","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, Honolulu, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"8190_CR54","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91\u201399","journal-title":"Adv Neural Inf Process Syst"},{"key":"8190_CR55","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multiBox ddetector. In: European conference on computer vision, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"8190_CR56","doi-asserted-by":"crossref","unstructured":"Mei M, He F, Xue S (2020) Attention deep residual networks for MR image analysis. Neural Computing and Applications. Springer, pp 1\u201310","DOI":"10.1007\/s00521-020-05083-3"},{"key":"8190_CR57","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, Yang J (2019) Selective kernel networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. IEEE, Long Beach, pp 510\u2013519","DOI":"10.1109\/CVPR.2019.00060"},{"key":"8190_CR58","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) SlowFast networks for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision. Elsevier Science Inc., Amsterdam, pp 6202\u20136211","DOI":"10.1109\/ICCV.2019.00630"},{"key":"8190_CR59","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"8190_CR60","doi-asserted-by":"crossref","unstructured":"Ishikawa Y, Kasai S, Aoki Y, Kataoka H (2021) Alleviating over-segmentation errors by detecting action boundaries. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision. pp 2322\u20132331","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"8190_CR61","doi-asserted-by":"crossref","unstructured":"Singh B, Marks TK, Jones M, Tuzel O, Shao M (2016) A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 1961\u20131970","DOI":"10.1109\/CVPR.2016.216"},{"key":"8190_CR62","unstructured":"Gao Y, Vedula SS, Reiley CE, Ahmidi N, Varadarajan B, Lin HC, Tao L, Zappella L, B\u00e9jar B, Yuh DD, et\u00a0al. (2014) JHU-ISI gesture and skill assessment working set ( JIGSAWS ) : a surgical activity dataset for human motion modeling. In: MICCAI workshop: M2cai, vol\u00a03. p\u00a03"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08190-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-08190-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08190-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T20:35:00Z","timestamp":1681850100000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-08190-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,12]]},"references-count":62,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["8190"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-08190-5","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,12]]},"assertion":[{"value":"18 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}