{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:35:55Z","timestamp":1783528555786,"version":"3.55.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"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":["61672190"],"award-info":[{"award-number":["61672190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["CSC202306120290"],"award-info":[{"award-number":["CSC202306120290"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s13042-024-02251-y","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T10:02:06Z","timestamp":1718704926000},"page":"567-581","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["MSLID-TCN: multi-stage linear-index dilated temporal convolutional network for temporal action segmentation"],"prefix":"10.1007","volume":"16","author":[{"given":"Suo","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songbo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"U\u011fur","family":"Erkan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdurrahim","family":"Toktas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,18]]},"reference":[{"issue":"2","key":"2251_CR1","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s13042-022-01572-0","volume":"14","author":"J Cheng","year":"2023","unstructured":"Cheng J, Zhang F, Wang G et al (2023) A multi-stage fusion instance learning method for anomalous event detection in videos. Int J Mach Learn Cybern 14(2):445\u2013454","journal-title":"Int J Mach Learn Cybern"},{"issue":"9","key":"2251_CR2","doi-asserted-by":"publisher","first-page":"2745","DOI":"10.1007\/s13042-022-01560-4","volume":"13","author":"Z Lu","year":"2022","unstructured":"Lu Z, Zhang G, Huang G et al (2022) Video person re-identification using key frame screening with index and feature reorganization based on inter-frame relation. Int J Mach Learn Cybern 13(9):2745\u20132761","journal-title":"Int J Mach Learn Cybern"},{"key":"2251_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115295","volume":"183","author":"J Espejel-Cabrera","year":"2021","unstructured":"Espejel-Cabrera J, Cervantes J, Garc\u00eda-Lamont F et al (2021) Mexican sign language segmentation using color based neuronal networks to detect the individual skin color. Expert Syst Appl 183:115295","journal-title":"Expert Syst Appl"},{"key":"2251_CR4","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo Vadis, action recognition? A new model and the kinetics dataset. In: IEEE conference on computer vision and pattern recognition, pp 4724\u20134733","DOI":"10.1109\/CVPR.2017.502"},{"key":"2251_CR5","first-page":"3468","volume":"2","author":"R Christoph","year":"2016","unstructured":"Christoph R, Pinz A, Wildes RP (2016) Spatiotemporal residual networks for video action recognition. Adv Neural Inf Process Syst 2:3468\u20133476","journal-title":"Adv Neural Inf Process Syst"},{"key":"2251_CR6","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong YJ, Wang Z et al (2016) Temporal segment networks: towards good practices for deep action recognition. In: European conference on computer vision, vol 9912, pp 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"2251_CR7","doi-asserted-by":"crossref","unstructured":"Wang L, Li W, Li W, et al (2018) Appearance-and-relation networks for video classification. In: IEEE conference on computer vision and pattern recognition, pp 1430\u20131439","DOI":"10.1109\/CVPR.2018.00155"},{"key":"2251_CR8","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, et al (2015) Learning spatiotemporal features with 3D convolutional networks. In: IEEE international conference on computer vision, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"2251_CR9","doi-asserted-by":"crossref","unstructured":"Bhattacharya S, Kalayeh MM, Sukthankar R, et al (2014) Recognition of complex events: exploiting temporal dynamics between underlying concepts. In: IEEE conference on computer vision and pattern recognition, pp 2243\u20132250","DOI":"10.1109\/CVPR.2014.287"},{"key":"2251_CR10","unstructured":"Karaman S, Seidenari L, Del Bimbo A (2014) Fast saliency based pooling of fisher encoded dense trajectories. In: European conference on computer vision, vol 1, no 2, p 5"},{"key":"2251_CR11","doi-asserted-by":"crossref","unstructured":"Shou Z, Wang D, Chang SF (2016) Temporal action localization in untrimmed videos via multi-stage CNNs. In: IEEE conference on computer vision and pattern recognition, pp 1049\u20131058","DOI":"10.1109\/CVPR.2016.119"},{"key":"2251_CR12","doi-asserted-by":"crossref","unstructured":"Shou Z, Chan J, Zareian A, et al (2017) CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: IEEE conference on computer vision and pattern recognition, pp 1417\u20131426","DOI":"10.1109\/CVPR.2017.155"},{"key":"2251_CR13","doi-asserted-by":"crossref","unstructured":"Singh B, Marks TK, Jones M, et al (2016) A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: IEEE conference on computer vision and pattern recognition, pp 1961\u20131970","DOI":"10.1109\/CVPR.2016.216"},{"key":"2251_CR14","doi-asserted-by":"crossref","unstructured":"Ni B, Yang X, Gao S (2016) Progressively parsing interactional objects for fine grained action detection. In: IEEE conference on computer vision and pattern recognition, pp 1020\u20131028","DOI":"10.1109\/CVPR.2016.116"},{"key":"2251_CR15","doi-asserted-by":"crossref","unstructured":"Kuehne H, Gall J, Serre T (2016) An end-to-end generative framework for video segmentation and recognition. In: IEEE winter conference on applications of computer vision, pp 1\u20138","DOI":"10.1109\/WACV.2016.7477701"},{"key":"2251_CR16","doi-asserted-by":"crossref","unstructured":"Richard A, Kuehne H, Gall J (2017) Weakly supervised action learning with RNN based fine-to-coarse modeling. In: IEEE conference on computer vision and pattern recognition, pp 1273\u20131282","DOI":"10.1109\/CVPR.2017.140"},{"key":"2251_CR17","doi-asserted-by":"crossref","unstructured":"Lea C, Reiter A, Vidal R et al (2016) Segmental spatiotemporal CNNS for fine-grained action segmentation. In: European conference on computer vision, vol 9907, pp 36\u201352","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"2251_CR18","doi-asserted-by":"crossref","unstructured":"Lea C, Flynn MD, Vidal R, et al (2017) Temporal convolutional networks for action segmentation and detection. In: IEEE conference on computer vision and pattern recognition, pp 1003\u20131012","DOI":"10.1109\/CVPR.2017.113"},{"key":"2251_CR19","doi-asserted-by":"crossref","unstructured":"Lei P, Todorovic S (2018) Temporal deformable residual networks for action segmentation in videos. In: IEEE conference on computer vision and pattern recognition, pp 6742\u20136751","DOI":"10.1109\/CVPR.2018.00705"},{"key":"2251_CR20","unstructured":"Ding L, Xu CL (2018) Weakly-supervised action segmentation with iterative soft boundary assignment. In: IEEE conference on computer vision and pattern recognition, pp 6508\u20136516"},{"key":"2251_CR21","doi-asserted-by":"crossref","unstructured":"Abu Farha Y, Gall J (2019) MS-TCN: multi-stage temporal convolutional network for action segmentation. In: IEEE conference on computer vision and pattern recognition, pp 3570\u20133579","DOI":"10.1109\/CVPR.2019.00369"},{"issue":"6","key":"2251_CR22","doi-asserted-by":"publisher","first-page":"6647","DOI":"10.1109\/TPAMI.2020.3021756","volume":"45","author":"SJ Li","year":"2023","unstructured":"Li SJ, Abu Farha Y, Liu Y et al (2023) MS-TCN++: multi-stage temporal convolutional network for action segmentation. IEEE Trans Pattern Anal Mach Intell 45(6):6647\u20136658","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2251_CR23","doi-asserted-by":"crossref","unstructured":"Stein S, McKenna SJ (2013) Combining embedded accelerometers with computer vision for recognizing food preparation activities. In: ACM international joint conference on pervasive and ubiquitous computing, pp 729\u2013738","DOI":"10.1145\/2493432.2493482"},{"key":"2251_CR24","doi-asserted-by":"crossref","unstructured":"Fathi A, Ren XF, Rehg JM (2011) Learning to recognize objects in egocentric activities. In: IEEE conference on computer vision and pattern recognition, pp 3281\u20133288","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"2251_CR25","doi-asserted-by":"crossref","unstructured":"Kuehne H, Arslan A, Serre T (2014) the language of actions: recovering the syntax and semantics of goal-directed human activities. In: IEEE conference on computer vision and pattern recognition, pp 780\u2013787","DOI":"10.1109\/CVPR.2014.105"},{"key":"2251_CR26","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.neucom.2021.04.121","volume":"454","author":"YH Li","year":"2021","unstructured":"Li YH, Dong ZB, Liu KY et al (2021) Efficient two-step networks for temporal action segmentation. Neurocomputing 454:373\u2013381","journal-title":"Neurocomputing"},{"key":"2251_CR27","doi-asserted-by":"publisher","first-page":"5848","DOI":"10.1109\/TIP.2021.3089361","volume":"30","author":"WF Yang","year":"2021","unstructured":"Yang WF, Zhang TZ, Mao ZD et al (2021) Multi-scale structure-aware network for weakly supervised temporal action detection. IEEE Trans Image Process 30:5848\u20135861","journal-title":"IEEE Trans Image Process"},{"key":"2251_CR28","doi-asserted-by":"crossref","unstructured":"Ishikawa Y, Kasai S, Aoki Y, et al (2021) Alleviating over-segmentation errors by detecting action boundaries. In: IEEE winter conference on applications of computer vision, pp 2321\u20132330","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"2251_CR29","doi-asserted-by":"crossref","unstructured":"Huang Y, Sugano Y, Sato Y (2020) Improving action segmentation via graph-based temporal reasoning. In: IEEE conference on computer vision and pattern recognition, pp 14024\u201314034","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"2251_CR30","doi-asserted-by":"crossref","unstructured":"He KM, Zhang XY, Ren SQ, et al (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2251_CR31","doi-asserted-by":"crossref","unstructured":"Gao SH, Han Q, Li Z, et al (2021) Global2Local: efficient structure search for video action segmentation. In: IEEE conference on computer vision and pattern recognition, pp 16805\u201316814","DOI":"10.1109\/CVPR46437.2021.01653"},{"key":"2251_CR32","doi-asserted-by":"crossref","unstructured":"Wang D, Hu D, Li XJ et al (2021) Temporal relational modeling with self-supervision for action segmentation. In: AAAI conference on artificial intelligence, vol 35, pp 2729\u20132737","DOI":"10.1609\/aaai.v35i4.16377"},{"key":"2251_CR33","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"},{"issue":"4","key":"2251_CR34","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(4):765\u2013779","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02251-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02251-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02251-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T07:39:43Z","timestamp":1737531583000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02251-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,18]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["2251"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02251-y","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,18]]},"assertion":[{"value":"15 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}