{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:41Z","timestamp":1740108041900,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"27","license":[{"start":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T00:00:00Z","timestamp":1717545600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T00:00:00Z","timestamp":1717545600000},"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":["62072110"],"award-info":[{"award-number":["62072110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s00521-024-09920-7","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T04:01:42Z","timestamp":1717560102000},"page":"17095-17106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pose-aware video action segmentation"],"prefix":"10.1007","volume":"36","author":[{"given":"Meijing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"9920_CR1","doi-asserted-by":"crossref","unstructured":"Rohrbach M, Amin S, Andriluka M, Schiele B (2012) A database for fine grained activity detection of cooking activities. In: IEEE conference on computer vision and pattern recognition, pp 1194\u20131201","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"9920_CR2","doi-asserted-by":"crossref","unstructured":"Bhattacharya S, Kalayeh MM, Sukthankar R, Shah M (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":"9920_CR3","unstructured":"Karaman S, Seidenari L, Del Bimbo A (2014) Fast saliency based pooling of fisher encoded dense trajectories. In: ECCV THUMOS workshop, vol 1, no 2, p 5"},{"key":"9920_CR4","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":"9920_CR5","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"},{"issue":"4","key":"9920_CR6","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":"9920_CR7","doi-asserted-by":"crossref","unstructured":"Farha YA, 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"},{"key":"9920_CR8","doi-asserted-by":"publisher","first-page":"6647","DOI":"10.1109\/TPAMI.2020.3021756","volume":"45","author":"S Li","year":"2020","unstructured":"Li S, Abu Farha Y, Liu Y, Cheng M-M, Gall J (2020) MS-TCN++: multi-stage temporal convolutional network for action segmentation. IEEE Trans Pattern Anal Mach Intell 45:6647\u20136658","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9920_CR9","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D, (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 32, no 1","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"9920_CR10","unstructured":"Filtjens B, Vanrumste B, Slaets P (2022) Skeleton-based action segmentation with multi-stage spatial-temporal graph convolutional neural networks. arXiv:2202.01727"},{"key":"9920_CR11","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 winter conference on applications of computer vision, pp 2322\u20132331","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"9920_CR12","doi-asserted-by":"crossref","unstructured":"Liu C, Hu Y, Li Y, Song S, Liu J (2017) PKU-MMD: a large scale benchmark for skeleton-based human action understanding. In: Proceedings of the workshop on visual analysis in smart and connected communities, pp 1\u20138","DOI":"10.1145\/3132734.3132739"},{"key":"9920_CR13","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":"9920_CR14","unstructured":"van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior AW, Kavukcuoglu K (2016) WaveNet: a generative model for raw audio. In: ISCA speech synthesis workshop"},{"key":"9920_CR15","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: IEEE conference on computer vision and pattern recognition, pp 1003\u20131012","DOI":"10.1109\/CVPR.2017.113"},{"key":"9920_CR16","doi-asserted-by":"crossref","unstructured":"Wang D, Hu D, Li X, Dou D (2021) Temporal relational modeling with self-supervision for action segmentation. In: AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v35i4.16377"},{"key":"9920_CR17","unstructured":"Yi F, Wen H, Jiang T (2021) ASFormer: transformer for action segmentation. In: British machine vision conference"},{"key":"9920_CR18","unstructured":"Wang J, Wang Z, Zhuang S, Wang H (2022) Cross-enhancement transformer for action segmentation. arXiv:2205.09445"},{"key":"9920_CR19","unstructured":"Du D, Su B, Li Y, Qi Z, Si L, Shan Y (2022) Efficient U-transformer with boundary-aware loss for action segmentation. arXiv:2205.13425"},{"key":"9920_CR20","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":"9920_CR21","doi-asserted-by":"crossref","unstructured":"Wang J, Liu Z, Wu Y, Yuan J (2012) Mining actionlet ensemble for action recognition with depth cameras. In: IEEE conference on computer vision and pattern recognition, pp 1290\u20131297","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"9920_CR22","doi-asserted-by":"crossref","unstructured":"Fernando B, Gavves E, Jos\u00e9 Oramas M, Ghodrati A, Tuytelaars T (2015) Modeling video evolution for action recognition. In: IEEE conference on computer vision and pattern recognition, pp 5378\u20135387","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"9920_CR23","unstructured":"Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. arXiv:1606.09375"},{"key":"9920_CR24","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907"},{"key":"9920_CR25","doi-asserted-by":"publisher","first-page":"9532","DOI":"10.1109\/TIP.2020.3028207","volume":"29","author":"L Shi","year":"2020","unstructured":"Shi L, Zhang Y, Cheng J, Lu H (2020) Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans Image Process 29:9532\u20139545","journal-title":"IEEE Trans Image Process"},{"key":"9920_CR26","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2017) Squeeze-and-excitation networks. arXiv:1709.01507","DOI":"10.1109\/CVPR.2018.00745"},{"key":"9920_CR27","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) CBAM: convolutional block attention module. arXiv:1807.06521","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"9920_CR28","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q (2019) ECA-net: efficient channel attention for deep convolutional neural networks. arXiv:1910.03151","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"9920_CR29","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (2018) Dual attention network for scene segmentation. arXiv:1809.02983","DOI":"10.1109\/CVPR.2019.00326"},{"key":"9920_CR30","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly Sn, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: International conference on learning representations"},{"key":"9920_CR31","doi-asserted-by":"crossref","unstructured":"Liu Z, Hu H, Lin Y, Yao Z, Xie Z, Wei Y, Ning J, Cao Y, Zhang Z, Dong L, Wei F, Guo B (2022) Swin transformer V2: scaling up capacity and resolution. In: IEEE conference on computer vision and pattern recognition, pp 11999\u201312009","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"9920_CR32","doi-asserted-by":"crossref","unstructured":"Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. In: IEEE conference on computer vision and pattern recognition, pp 5686\u20135696","DOI":"10.1109\/CVPR.2019.00584"},{"key":"9920_CR33","unstructured":"Ding L, Xu C (2018) Weakly-supervised action segmentation with iterative soft boundary assignment. In: IEEE conference on computer vision and pattern recognition, pp 6508\u20136516"},{"key":"9920_CR34","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":"9920_CR35","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 14021\u201314031","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"9920_CR36","doi-asserted-by":"crossref","unstructured":"Wang D, Hu D, Li X, Dou D (2021) Temporal relational modeling with self-supervision for action segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, no 4","DOI":"10.1609\/aaai.v35i4.16377"},{"issue":"5","key":"9920_CR37","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18(5):602\u2013610","journal-title":"Neural Netw"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09920-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-09920-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09920-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T10:15:22Z","timestamp":1724494522000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-09920-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,5]]},"references-count":37,"journal-issue":{"issue":"27","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["9920"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-09920-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2024,6,5]]},"assertion":[{"value":"18 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}