{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:05:19Z","timestamp":1764842719656,"version":"3.37.3"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"24","license":[{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11042-023-15022-8","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T03:40:11Z","timestamp":1679888411000},"page":"37387-37406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A deep learning model based on sequential object feature accumulation for sport activity recognition"],"prefix":"10.1007","volume":"82","author":[{"given":"Kwanghyun","family":"Ryu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heechan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5863-1188","authenticated-orcid":false,"given":"Soowon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,22]]},"reference":[{"key":"15022_CR1","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1007\/s00371-019-01722-6","volume":"36","author":"M Afrasiabi","year":"2020","unstructured":"Afrasiabi M, Khotanlou H, Mansoorizadeh M (2020) DTW-CNN: time series-based human interaction prediction in videos using CNN-extracted features. Vis Comput 36:1127\u20131139. https:\/\/doi.org\/10.1007\/s00371-019-01722-6","journal-title":"Vis Comput"},{"key":"15022_CR2","doi-asserted-by":"publisher","first-page":"107353","DOI":"10.1016\/j.patcog.2020.107353","volume":"104","author":"A Atto","year":"2020","unstructured":"Atto A, Benoit A, Lambert P (2020) Timed-image based beep learning for action recognition in video sequences. Pattern Recogn 104:107353. https:\/\/doi.org\/10.1016\/j.patcog.2020.107353","journal-title":"Pattern Recogn"},{"key":"15022_CR3","doi-asserted-by":"crossref","unstructured":"Bagautdinov T, Alahi A, Fleuret F, Fua P, Savarese S (2017) Social scene understanding: end-to-end multi-person action localization and collective activity recognition. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp. 4315-4324","DOI":"10.1109\/CVPR.2017.365"},{"key":"15022_CR4","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? A new model and the kinetics dataset. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp.6299-6308","DOI":"10.1109\/CVPR.2017.502"},{"key":"15022_CR5","doi-asserted-by":"crossref","unstructured":"Deliege A, Cioppa GS, Seilvandi MJ, Dueholm JV, Nasrollahi K, Ghanem B, Moeslund TB, Droogenbroeck MV (2021) SoccerNet-v2: A dataset and benchmarks for holistic understanding of broadcast soccer videos. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. pp. 4508\u20134519","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"15022_CR6","doi-asserted-by":"crossref","unstructured":"Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrel T (2015) Long-term recurrent convolutional networks for visual recognition and description. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp.2625-2634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"15022_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1109\/TIP.2017.2778563","volume":"27","author":"W Du","year":"2018","unstructured":"Du W, Wang Y, Qiao Y (2018) Recurrent spatial-temporal attention network for action recognition in videos. IEEE Trans Image Process 27:3\u20131360. https:\/\/doi.org\/10.1109\/TIP.2017.2778563","journal-title":"IEEE Trans Image Process"},{"key":"15022_CR8","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 (ICCV). pp. 6202-6211","DOI":"10.1109\/ICCV.2019.00630"},{"key":"15022_CR9","doi-asserted-by":"publisher","unstructured":"Gammulle H, Denman S, Sridharan S, Fookes C (2018) Multi-level sequence GAN for group activity recognition. In proceedings of the Asian conference on computer vision (ACCV). pp. 331-346. https:\/\/doi.org\/10.1007\/978-3-030-20887-5_21","DOI":"10.1007\/978-3-030-20887-5_21"},{"key":"15022_CR10","doi-asserted-by":"crossref","unstructured":"Giancola S, Amine M, Dghaily T, Ghanem B (2018) SoccerNet : a scalable dataset for action spotting in soccer videos. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. pp. 1711-1721","DOI":"10.1109\/CVPRW.2018.00223"},{"key":"15022_CR11","doi-asserted-by":"crossref","unstructured":"Girdhar R, Carreira J, Doersch C, Zisserman A (2019) Video action transformer network. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 244-253","DOI":"10.1109\/CVPR.2019.00033"},{"key":"15022_CR12","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In proceedings of the advances in neural information processing systems 27, Montr\u00e9al, Canada"},{"key":"15022_CR13","doi-asserted-by":"publisher","unstructured":"Gu X, Xue X, Wang F (2020) Fine-grained action recognition on a novel basketball datatset. CASSP IEEE international conference on acoustics, speech and signal processing (ICASSP). pp. 2563-2567 https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053928","DOI":"10.1109\/ICASSP40776.2020.9053928"},{"key":"15022_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In proceedings of the European conference in computer vision, Amsterdam, the Netherlands","DOI":"10.1007\/978-3-319-46493-0_38"},{"issue":"8","key":"15022_CR15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"issue":"1","key":"15022_CR16","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TII.2019.2929228","volume":"16","author":"T Hussain","year":"2020","unstructured":"Hussain T, Muhammad K, Ullah A, Zehong C, Baik S, Albuquerque V (2020) Cloud-assisted multiview video summarization using CNN and bidirectional LSTM. IEEE Trans Industr Inform 16(1):77\u201386. https:\/\/doi.org\/10.1109\/TII.2019.2929228","journal-title":"IEEE Trans Industr Inform"},{"key":"15022_CR17","doi-asserted-by":"crossref","unstructured":"Jones ML, Levy K (2018) Sporting chances: robot referees and the automation of enforcement. We robot. Retrieved from https:\/\/ssrn.com\/abstract=3293076","DOI":"10.2139\/ssrn.3293076"},{"key":"15022_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) large-scale video classification with convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .pp. 1725-1732","DOI":"10.1109\/CVPR.2014.223"},{"key":"15022_CR19","doi-asserted-by":"publisher","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, Viola F, Green T, Back T, Natsev P, Suleyman M, Zisserman A (2017) The kinetics human action video dataset. arXiv preprint arxiv:1705.06950. https:\/\/doi.org\/10.48550\/arXiv.1705.06950","DOI":"10.48550\/arXiv.1705.06950"},{"issue":"22","key":"15022_CR20","doi-asserted-by":"publisher","first-page":"4663","DOI":"10.3390\/app9224963","volume":"9","author":"S Khan","year":"2019","unstructured":"Khan S, Haq I, Rho S, Baik S, Lee M (2019) Cover the violence : a novel deep-learning-based approach towards violence-detection in movies. Appl Sci 9(22):4663. https:\/\/doi.org\/10.3390\/app9224963","journal-title":"Appl Sci"},{"key":"15022_CR21","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s13673-020-00240-y","volume":"10","author":"SA Khowaja","year":"2020","unstructured":"Khowaja SA, Yahya BN, Lee SL (2020) CAPHAR: context-aware personalized human activity recognition using associated learning in smart environments. Human-centric Comput Inform Sci 10:35. https:\/\/doi.org\/10.1186\/s13673-020-00240-y","journal-title":"Human-centric Comput Inform Sci"},{"key":"15022_CR22","doi-asserted-by":"publisher","first-page":"2250","DOI":"10.3390\/su13042250","volume":"13","author":"H Kim","year":"2021","unstructured":"Kim H, Lee S (2021) A video captioning method based on multi-representation switching for sustainable computing. Sustainability 13:2250. https:\/\/doi.org\/10.3390\/su13042250","journal-title":"Sustainability"},{"key":"15022_CR23","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization, in proceedings of the international conference on learning representations, San Diego, CA, USA"},{"key":"15022_CR24","doi-asserted-by":"publisher","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) HMDB: a large video database for human motion recognition. In proceedings of the international conference on computer vision (ICCV), pp. 2556-2563 https:\/\/doi.org\/10.1109\/ICCV.2011.6126543","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"15022_CR25","doi-asserted-by":"publisher","first-page":"47220","DOI":"10.1109\/ACCESS.2020.2979549","volume":"8","author":"S Liu","year":"2020","unstructured":"Liu S, Ma X, Wu H, Li Y (2020) An end to end framework with adaptive spatio-temporal attention module for human action recognition. Dig Object Ident 8:47220\u201347231. https:\/\/doi.org\/10.1109\/ACCESS.2020.2979549","journal-title":"Dig Object Ident"},{"key":"15022_CR26","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In proceedings of the international conference on machine learning 27, Haifa, Israel."},{"issue":"4","key":"15022_CR27","doi-asserted-by":"publisher","first-page":"1491","DOI":"10.1016\/j.patcog.2009.11.011","volume":"43","author":"M Per\u0161e","year":"2010","unstructured":"Per\u0161e M, Kristan M, Per\u0161 J, Mu\u0161i\u010d G, Vu\u010dkovi\u010d G, Kova\u010di\u010d S (2010) Analysis of multi-agent activity using perti nets. Pattern Recog 43(4):1491\u20131501. https:\/\/doi.org\/10.1016\/j.patcog.2009.11.011","journal-title":"Pattern Recog"},{"key":"15022_CR28","doi-asserted-by":"crossref","unstructured":"Piergiovanni AJ, Ryoo MS (2018) fine-grained activity recognition in baseball videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops .pp. 1740-1748","DOI":"10.1109\/CVPRW.2018.00226"},{"key":"15022_CR29","doi-asserted-by":"crossref","unstructured":"Piergiovanni AJ, Ryoo MS (2019) Representation flow for action recognition. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 9945-9953","DOI":"10.1109\/CVPR.2019.01018"},{"key":"15022_CR30","doi-asserted-by":"crossref","unstructured":"Piergiovanni AJ, Fan C, Ryoo M (2017) Learning latent subevents in activity using temporal attention filters. Thirty-First AAAI Conference on Artificial Intelligence 31:1. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/11240","DOI":"10.1609\/aaai.v31i1.11240"},{"key":"15022_CR31","doi-asserted-by":"publisher","unstructured":"Qi S, Ning X, Yang G, Zhang L, Long P, Cai W (2021) Review of multi-view 3D object recognition methods based on deep learning. Displays, 69, 102053. https:\/\/doi.org\/10.1016\/j.displa.2021.102053","DOI":"10.1016\/j.displa.2021.102053"},{"key":"15022_CR32","doi-asserted-by":"publisher","unstructured":"Rahmad NA, As\u2019ari MA, Ghazali NF, Sufri NAJ (2018) A survey of video based action recognition in sports. Indonesian Journal of Electrical Engineering and Computer Science 987\u2013993. https:\/\/doi.org\/10.11591\/ijeecs.v11.i3.pp987-993","DOI":"10.11591\/ijeecs.v11.i3.pp987-993"},{"issue":"3","key":"15022_CR33","doi-asserted-by":"publisher","first-page":"556","DOI":"10.3745\/JIPS.02.0156","volume":"17","author":"Q Ren","year":"2021","unstructured":"Ren Q (2021) A video expression recognition method based on multi-mode convolution neural network and multiplicative feature fusion. J Inform Proc Syst 17(3):556\u2013570. https:\/\/doi.org\/10.3745\/JIPS.02.0156","journal-title":"J Inform Proc Syst"},{"key":"15022_CR34","unstructured":"Robertson MR (2015) 500 hours of video uploaded to YouTube every minute. Tubular insights. Retrieved from https:\/\/tubularinsights.com\/hours-minute-uploaded-youtube\/"},{"key":"15022_CR35","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1109\/TCSVT.2017.2655624","volume":"28","author":"H Shih","year":"2017","unstructured":"Shih H (2017) A survey of content-aware video analysis for sports. IEEE Trans Circ Syst Video Technol 28:1212\u20131231. https:\/\/doi.org\/10.1109\/TCSVT.2017.2655624","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"15022_CR36","doi-asserted-by":"crossref","unstructured":"Shim M, Kim YH, Kim K, Kim SJ (2018) Teaching machines to understand baseball games: large-scale baseball video database for multiple video understanding tasks. Proceedings of the European conference on computer vision (ECCV). pp. 404-420","DOI":"10.1007\/978-3-030-01267-0_25"},{"key":"15022_CR37","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In proceedings of the advances in neural information processing systems 27, Montr\u00e9al, Canada"},{"key":"15022_CR38","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s00530-019-00635-7","volume":"26","author":"R Singh","year":"2020","unstructured":"Singh R, Sonawane A, Srivastava R (2020) Recent evolution of modern datasets for human activity recognition: a deep survey. Multimedia Systems 26:83\u2013106. https:\/\/doi.org\/10.1007\/s00530-019-00635-7","journal-title":"Multimedia Systems"},{"key":"15022_CR39","doi-asserted-by":"publisher","unstructured":"Soomro K, Zamir A, Shah M (2012) UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arxiv:1212.0402. https:\/\/doi.org\/10.48550\/arXiv.1212.0402","DOI":"10.48550\/arXiv.1212.0402"},{"key":"15022_CR40","doi-asserted-by":"publisher","first-page":"108563","DOI":"10.1016\/j.patcog.2022.108563","volume":"126","author":"B Sun","year":"2022","unstructured":"Sun B, Kong D, Wang S, Li J, Yin B, Luo X (2022) GAN for vision, KG for relation: a two-stage network for zero-shot action recognition. Pattern Recogn 126:108563. https:\/\/doi.org\/10.1016\/j.patcog.2022.108563","journal-title":"Pattern Recogn"},{"key":"15022_CR41","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wonja Z (2016) Rethinking the inception architecture for computer vision. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.308"},{"key":"15022_CR42","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In proceedings of the IEEE international conference on computer vision (ICCV), pp. 4489-4497","DOI":"10.1109\/ICCV.2015.510"},{"key":"15022_CR43","doi-asserted-by":"publisher","first-page":"5576369","DOI":"10.1155\/2021\/5576369","volume":"2021","author":"H Tu","year":"2021","unstructured":"Tu H, Xu R, Chi R, Peng Y (2021) Multiperson interactive activity recognition based on interaction relation model. J Mathma 2021:5576369. https:\/\/doi.org\/10.1155\/2021\/5576369","journal-title":"J Mathma"},{"key":"15022_CR44","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp.7794-7803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"15022_CR45","doi-asserted-by":"publisher","first-page":"108498","DOI":"10.1016\/j.patcog.2021.108498","volume":"124","author":"C Wang","year":"2022","unstructured":"Wang C, Wang X, Zhang J, Zhang L, Bai X, Ning X, Zhou J, Hancock E (2022) Uncertainty estimation for stereo matching based on evidential deep learning. Pattern Recogn 124:108498. https:\/\/doi.org\/10.1016\/j.patcog.2021.108498","journal-title":"Pattern Recogn"},{"key":"15022_CR46","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.pmcj.2018.10.004","volume":"51","author":"Z Wemlinger","year":"2018","unstructured":"Wemlinger Z, Holder L (2018) Cross-environment activity recognition using a shared semantic vocabulary. Pervasive Mob Comput 51:150\u2013159. https:\/\/doi.org\/10.1016\/j.pmcj.2018.10.004","journal-title":"Pervasive Mob Comput"},{"key":"15022_CR47","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J, Kweon I (2018) CBAM: convolutional block attention module. In proceedings of the European conference on computer vision (ECCV), pp. 3-19","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"15022_CR48","doi-asserted-by":"publisher","first-page":"107396","DOI":"10.1016\/j.patcog.2020.107396","volume":"106","author":"D Yoon","year":"2020","unstructured":"Yoon D, Cho N, Lee S (2020) A novel online action detection framework from untrimmed video streams. Pattern Recogn 106:107396. https:\/\/doi.org\/10.1016\/j.patcog.2020.107396","journal-title":"Pattern Recogn"},{"issue":"2","key":"15022_CR49","doi-asserted-by":"publisher","first-page":"337","DOI":"10.3745\/JIPS.01.0067","volume":"17","author":"X Zhou","year":"2021","unstructured":"Zhou X (2021) Video expression recognition method based on spatiotemporal recurrent neural network and feature fusion. J Inform Proc Syst 17(2):337\u2013351. https:\/\/doi.org\/10.3745\/JIPS.01.0067","journal-title":"J Inform Proc Syst"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15022-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15022-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15022-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,3]],"date-time":"2023-10-03T09:30:22Z","timestamp":1696325422000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15022-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,22]]},"references-count":49,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["15022"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15022-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,3,22]]},"assertion":[{"value":"16 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2023","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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}