{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T05:23:25Z","timestamp":1739510605754,"version":"3.37.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s11760-024-03805-x","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T08:30:52Z","timestamp":1737621052000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Capturing captivating moments: a multi-model approach for identifying baseball strikeout highlights"],"prefix":"10.1007","volume":"19","author":[{"given":"Qiaoyun","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Chih-Yung","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Cuijuan","family":"Shang","sequence":"additional","affiliation":[]},{"given":"Hsiang-Chuan","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Diptendu Sinha","family":"Roy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,23]]},"reference":[{"issue":"2","key":"3805_CR1","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1109\/TMM.2018.2862341","volume":"21","author":"D Li","year":"2019","unstructured":"Li, D., Yao, T., et al.: Unified spatio-temporal attention networks for action recognition in videos. IEEE Trans. Multimed. 21(2), 416\u2013428 (2019)","journal-title":"IEEE Trans. Multimed."},{"issue":"8","key":"3805_CR2","doi-asserted-by":"publisher","first-page":"2405","DOI":"10.1109\/TCSVT.2018.2864148","volume":"29","author":"Z Yang","year":"2019","unstructured":"Yang, Z., Li, Y., et al.: Action recognition with spatio\u2013temporal visual attention on skeleton image sequences. IEEE Trans. Circuits Syst. Video Technol. 29(8), 2405\u20132415 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"3805_CR3","doi-asserted-by":"publisher","first-page":"9434","DOI":"10.1109\/TPAMI.2021.3126682","volume":"44","author":"M Monfort","year":"2022","unstructured":"Monfort, M., Pan, B., et al.: Multi-moments in time: learning and interpreting models for multi-action video understanding. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9434\u20139445 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"3805_CR4","doi-asserted-by":"publisher","first-page":"2855","DOI":"10.1080\/08839514.2022.2093705","volume":"36","author":"V Sharma","year":"2022","unstructured":"Sharma, V., Gupta, M., et al.: A review of deep learning-based human activity recognition on benchmark video datasets. Appl. Artif. Intell. 36(1), 2855\u20132901 (2022)","journal-title":"Appl. Artif. Intell."},{"key":"3805_CR5","doi-asserted-by":"crossref","unstructured":"R. Girshick, J. Donahue, et al, 2014. \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, pp. 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"3805_CR6","doi-asserted-by":"crossref","unstructured":"R. Girshick, 2015. \u201cFast r-cnn,\u201d IEEE International Conference on Computer Vision, Beijing, China, pp. 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"issue":"7","key":"3805_CR7","first-page":"2096","volume":"43","author":"H Zhao","year":"2021","unstructured":"Zhao, H., Li, Z., et al.: Attention based single shot multibox detector. J. Electron. Inf. Technol. 43(7), 2096\u20132104 (2021)","journal-title":"J. Electron. Inf. Technol."},{"key":"3805_CR8","doi-asserted-by":"crossref","unstructured":"J. Redmon, S. Divvala, et al, 2016. \u201cYou only look once: unified, real-time object detection,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA, pp. 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"issue":"12","key":"3805_CR9","doi-asserted-by":"publisher","first-page":"25345","DOI":"10.1109\/TITS.2022.3158253","volume":"23","author":"S Liang","year":"2022","unstructured":"Liang, S., Wu, H., et al.: Edge YOLO: real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 23(12), 25345\u201325360 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"15","key":"3805_CR10","doi-asserted-by":"publisher","first-page":"15435","DOI":"10.1109\/JSEN.2022.3167251","volume":"22","author":"Y Song","year":"2022","unstructured":"Song, Y., Xie, Z., et al.: MS-YOLO: object detection based on YOLOv5 optimized fusion millimeter-wave radar and machine vision. IEEE Sens. J. 22(15), 15435\u201315447 (2022)","journal-title":"IEEE Sens. J."},{"issue":"7","key":"3805_CR11","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TMM.2017.2666540","volume":"19","author":"Y Shi","year":"2017","unstructured":"Shi, Y., Tian, Y., et al.: Sequential deep trajectory descriptor for action recognition with three-stream CNN. IEEE Trans. Multimedia 19(7), 1510\u20131520 (2017)","journal-title":"IEEE Trans. Multimedia"},{"issue":"10","key":"3805_CR12","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2020","unstructured":"Liu, J., Shahroudy, A., et al.: NTU RGB+D: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3805_CR13","doi-asserted-by":"crossref","unstructured":"A. Yao, J. Gall, G. Fanelli, and L. J. Van Gool, 2011 \u201cDoes human action recognition benefit from pose estimation?\u201dBritish Machine Vision Conference, Dundee, Scotland, pp. 67.1\u201367.11,","DOI":"10.5244\/C.25.67"},{"key":"3805_CR14","unstructured":"Z. Ge, S. Liu, F. Wang, et al, 2021 \u201cYOLOX: Exceeding YOLO series in 2021,\u201d arXiv preprint arXiv:2107.08430, pp. 1\u20137"},{"issue":"5","key":"3805_CR15","doi-asserted-by":"publisher","first-page":"2600","DOI":"10.1007\/s40815-022-01267-2","volume":"24","author":"M Sadiq","year":"2022","unstructured":"Sadiq, M., Masood, S., Pal, O.: Fd-yolov5: a fuzzy image enhancement based robust object detection model for safety helmet detection. Int. J. Fuzzy Syst. 24(5), 2600\u20132616 (2022)","journal-title":"Int. J. Fuzzy Syst."},{"issue":"7","key":"3805_CR16","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1162\/neco_a_01199","volume":"31","author":"Y Yu","year":"2019","unstructured":"Yu, Y., Si, X., Hu, C., Zhang, J.: A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 31(7), 1235\u20131270 (2019)","journal-title":"Neural Comput."},{"key":"3805_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jvcir.2021.103386","volume":"82","author":"X Shen","year":"2022","unstructured":"Shen, X., Ding, Y.: Human skeleton representation for 3D action recognition based on complex network coding and LSTM. J. Vis. Commun. Image Represent. 82, 1\u20139 (2022)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"3805_CR18","first-page":"4171","volume-title":"\u201cBERT: Pre-training of deep bidirectional transformers for language understanding\u201d, Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"J Devlin","year":"2019","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: \u201cBERT: Pre-training of deep bidirectional transformers for language understanding\u201d, Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 4171\u20134186. Minneapolis, Minnesota (2019)"},{"key":"3805_CR19","doi-asserted-by":"crossref","unstructured":"T. H. Le, T. M. Le, and T. A. Nguyen, 2023. \u201cAction identification with fusion of BERT and 3DCNN for smart home systems,\u201d Internet of Things, pp. 1\u201320, vol. 22","DOI":"10.1016\/j.iot.2023.100811"},{"key":"3805_CR20","doi-asserted-by":"crossref","unstructured":"D. Tran, L. Bourdev, R. Fergus, L. Torresani, and M. Paluri, 2015, \u201cLearning spatiotemporal features with 3D convolutional networks,\u201d IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp. 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"3805_CR21","doi-asserted-by":"crossref","unstructured":"K. Liu, W. Liu, C. Gan, M. Tan, and H. Ma, 2018 \u201cT-C3D: Temporal convolutional 3D network for real-time action recognition,\u201d Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, pp. 7138\u20137145","DOI":"10.1609\/aaai.v32i1.12333"},{"key":"3805_CR22","doi-asserted-by":"crossref","unstructured":"V.-M. Khong and T.-H. Tran, 2018. \u201cImproving human action recognition with two-stream 3D convolutional neural network,\u201d IEEE 1st International Conference on Multimedia Analysis and Pattern Recognition (MAPR), Ho Chi Minh City, Vietnam, pp. 1\u20136","DOI":"10.1109\/MAPR.2018.8337518"},{"key":"3805_CR23","doi-asserted-by":"crossref","unstructured":"Z. Zhao, W. Zou, and J. Wang, 2020. \u201cAction recognition based on C3D network and adaptive keyframe extraction,\u201d IEEE 6th International Conference on Computer and Communications (ICCC), Chengdu, China, pp. 2441\u20132447","DOI":"10.1109\/ICCC51575.2020.9345274"},{"issue":"7","key":"3805_CR24","doi-asserted-by":"publisher","first-page":"3010","DOI":"10.1109\/TIP.2016.2552404","volume":"25","author":"Y Du","year":"2016","unstructured":"Du, Y., Fu, Y., Wang, L.: Representation learning of temporal dynamics for skeleton-based action recognition. IEEE Trans. Image Process. 25(7), 3010\u20133022 (2016)","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"3805_CR25","doi-asserted-by":"publisher","first-page":"2330","DOI":"10.1109\/TMM.2018.2802648","volume":"20","author":"S Zhang","year":"2018","unstructured":"Zhang, S., Yang, Y., et al.: Fusing geometric features for skeleton-based action recognition using multilayer LSTM networks. IEEE Trans. Multimedia 20(9), 2330\u20132343 (2018)","journal-title":"IEEE Trans. Multimedia"},{"issue":"8","key":"3805_CR26","doi-asserted-by":"publisher","first-page":"1963","DOI":"10.1109\/TPAMI.2019.2896631","volume":"41","author":"P Zhang","year":"2019","unstructured":"Zhang, P., Lan, C., Xing, J., et al.: View adaptive neural networks for high performance skeleton-based human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1963\u20131978 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"3805_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3472722","volume":"18","author":"Y Tang","year":"2022","unstructured":"Tang, Y., Liu, X., Yu, X., et al.: Learning from temporal spatial cubism for cross-dataset skeleton-based action recognition. ACM Trans. Multimed. Comput. Commun. Appl. 18(2), 1\u201324 (2022)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"3805_CR28","doi-asserted-by":"crossref","unstructured":"S. Yan, Y. Xiong, and D. Lin, \u201cSpatial temporal graph convolutional networks for skeleton-based action recognition,\u201d Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, pp. 7444\u20137452, Apr. 2018.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"3805_CR29","doi-asserted-by":"crossref","unstructured":"M. Li, S. Chen, X. Chen, Y. Zhang, et al, 2019. \u201cActional-structural graph convolutional networks for skeleton-based action recognition,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, USA, pp. 3590\u20133598","DOI":"10.1109\/CVPR.2019.00371"},{"issue":"8","key":"3805_CR30","doi-asserted-by":"publisher","first-page":"3047","DOI":"10.1109\/TNNLS.2019.2935173","volume":"31","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Xu, C., Tian, X., Tao, D.: Graph edge convolutional neural networks for skeleton-based action recognition. IEEE Trans. Neural Netw. Learning Syst. 31(8), 3047\u20133060 (2020)","journal-title":"IEEE Trans. Neural Netw. Learning Syst."},{"key":"3805_CR31","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., et al.: Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans. Image Process. 29, 9532\u20139545 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"3805_CR32","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/TIP.2021.3129117","volume":"31","author":"H Yang","year":"2021","unstructured":"Yang, H., Yan, D., et al.: Feedback graph convolutional network for skeleton-based action recognition. IEEE Trans. Image Process. 31, 164\u2013175 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"3805_CR33","doi-asserted-by":"publisher","first-page":"1868","DOI":"10.1109\/TCSVT.2022.3217763","volume":"33","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Qin, Y., et al.: Motion-driven spatial and temporal adaptive high-resolution graph convolutional networks for skeleton-based action recognition. IEEE Trans. Circuits Syst. Video Technol. 33(4), 1868\u20131883 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"5","key":"3805_CR34","doi-asserted-by":"publisher","first-page":"2575","DOI":"10.1109\/TVCG.2023.3247075","volume":"29","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Zhang, H., et al.: Skeleton-based human action recognition via large-kernel attention graph convolutional network. IEEE Trans. Visual Comput. Graphics 29(5), 2575\u20132585 (2023)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"issue":"6","key":"3805_CR35","doi-asserted-by":"publisher","first-page":"3316","DOI":"10.1109\/TPAMI.2021.3053765","volume":"44","author":"M Li","year":"2022","unstructured":"Li, M., Chen, S., Chen, X., et al.: Symbiotic graph neural networks for 3D skeleton-based human action recognition and motion prediction. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3316\u20133333 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3805_CR36","first-page":"1","volume-title":"\u201cMediapipe: A framework for perceiving and processing reality\u201d, IEEE Computer Vision and Pattern Recognition (CVPR)","author":"C Lugaresi","year":"2019","unstructured":"Lugaresi, C., Tang, J., et al.: \u201cMediapipe: A framework for perceiving and processing reality\u201d, IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1\u20134. Long Beach, California, USA (2019)"},{"key":"3805_CR37","doi-asserted-by":"crossref","unstructured":"N. Crasto, P. Weinzaepfel, K. Alahari, and C. Schmid, 2019. \u201cMARS: Motion-augmented rgb stream for action recognition,\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 7882\u20137891","DOI":"10.1109\/CVPR.2019.00807"},{"key":"3805_CR38","doi-asserted-by":"crossref","unstructured":"B. Yang, X. Zhang, et al., 2024. \u201cFast Multiview Anchor-Graph Clustering,\u201d IEEE Transactions on Neural Networks and Learning Systems, early access","DOI":"10.1109\/TNNLS.2024.3359690"},{"key":"3805_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102097","volume":"103","author":"B Yang","year":"2024","unstructured":"Yang, B., Wu, J., et al.: Discrete correntropy-based multi-view anchor-graph clustering. Inform. Fusion 103, 102097 (2024)","journal-title":"Inform. Fusion"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03805-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03805-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03805-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T14:56:10Z","timestamp":1739458570000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03805-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,23]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["3805"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03805-x","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,1,23]]},"assertion":[{"value":"22 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2025","order":4,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"232"}}