{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:45:58Z","timestamp":1774453558381,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"crossref","award":["No. 2021C03151"],"award-info":[{"award-number":["No. 2021C03151"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Public Projects of Zhejiang Province of China","award":["No. LGG21G010001"],"award-info":[{"award-number":["No. LGG21G010001"]}]},{"name":"the Natural Science Foundation of Zhejiang Province of China","award":["No. Y20F020113"],"award-info":[{"award-number":["No. Y20F020113"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17834-0","type":"journal-article","created":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T04:35:35Z","timestamp":1702614935000},"page":"57187-57197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Spatiotemporal feature enhancement network for action recognition"],"prefix":"10.1007","volume":"83","author":[{"given":"Guancheng","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1773-9760","authenticated-orcid":false,"given":"Xiuhui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuesheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaru","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,15]]},"reference":[{"key":"17834_CR1","doi-asserted-by":"publisher","first-page":"2273","DOI":"10.1109\/TMM.2021.3078882","volume":"24","author":"Y Huang","year":"2022","unstructured":"Huang Y, Yang X, Gao J, Xu C (2022) Holographic feature learning of egocentric-exocentric videos for multi-domain action recognition. IEEE Trans Multimed 24:2273\u20132286","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"17834_CR2","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1109\/TNNLS.2020.3043002","volume":"33","author":"J Liu","year":"2022","unstructured":"Liu J, Akhtar N, Mian A (2022) Adversarial attack on skeleton-based human action recognition. IEEE Trans Neural Netw Learn Syst 33(4):1609\u20131622","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"17834_CR3","doi-asserted-by":"publisher","first-page":"2493","DOI":"10.1109\/TIP.2023.3269228","volume":"32","author":"W Lin","year":"2023","unstructured":"Lin W, Ding X, Huang Y, Zeng H (2023) Self-supervised video-based action recognition with disturbances. IEEE Trans Image Process 32:2493\u20132507","journal-title":"IEEE Trans Image Process"},{"key":"17834_CR4","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TIP.2022.3228156","volume":"32","author":"M Cui","year":"2023","unstructured":"Cui M, Wang W, Zhang K, Sun Z, Wang L (2023) Pose-appearance relational modeling for video action recognition. IEEE Trans Image Process 32:295\u2013308","journal-title":"IEEE Trans Image Process"},{"issue":"8","key":"17834_CR5","doi-asserted-by":"publisher","first-page":"10317","DOI":"10.1109\/TPAMI.2023.3261659","volume":"45","author":"R Yan","year":"2023","unstructured":"Yan R, Xie L, Shu X, Zhang L, Tang J (2023) Progressive instance-aware feature learning for compositional action recognition. IEEE Trans Pattern Anal Mach Intell 45(8):10317\u201310330","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"17834_CR6","doi-asserted-by":"publisher","first-page":"10317","DOI":"10.1109\/TPAMI.2023.3261659","volume":"45","author":"R Yan","year":"2023","unstructured":"Yan R, Xie L, Shu X, Zhang L, Tang J (2023) Progressive instance-aware feature learning for compositional action recognition. IEEE Trans Pattern Anal Mach Intell 45(8):10317\u201310330","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"17834_CR7","doi-asserted-by":"publisher","first-page":"3073","DOI":"10.1109\/TCSVT.2021.3100842","volume":"32","author":"H Luo","year":"2022","unstructured":"Luo H, Lin G, Yao Y, Tang Z, Wu Q, Hua X (2022) Dense semantics-assisted networks for video action recognition. IEEE Trans Circuit Syst Video Technol 32(5):3073\u20133084","journal-title":"IEEE Trans Circuit Syst Video Technol"},{"issue":"7","key":"17834_CR8","first-page":"8477","volume":"45","author":"S Li","year":"2023","unstructured":"Li S, He X, Song W, Hao A, Qin H (2023) Graph diffusion convolutional network for skeleton based semantic recognition of two-person actions. IEEE Trans Pattern Anal Mach Intell 45(7):8477\u20138493","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"17834_CR9","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1109\/TCSVT.2021.3070688","volume":"32","author":"N Nigam","year":"2022","unstructured":"Nigam N, Dutta T, Gupta HP (2022) Factornet: Holistic actor, object, and scene factorization for action recognition in videos. IEEE Trans Circuits Syst Video Technol 32(3):976\u2013991","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"17834_CR10","doi-asserted-by":"publisher","first-page":"5484","DOI":"10.1109\/TIP.2022.3196175","volume":"31","author":"T Geng","year":"2022","unstructured":"Geng T, Zheng F, Hou X, Lu K, Qi G-J, Shao L (2022) Spatial-temporal pyramid graph reasoning for action recognition. IEEE Trans Image Process 31:5484\u20135497","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"17834_CR11","doi-asserted-by":"publisher","first-page":"5332","DOI":"10.1109\/TNNLS.2021.3070179","volume":"33","author":"Y Wang","year":"2022","unstructured":"Wang Y, Xiao Y, Lu J, Tan B, Cao Z, Zhang Z, Zhou JT (2022) Discriminative multi-view dynamic image fusion for cross-view 3-d action recognition. IEEE Trans Neural Netw Learn Syst 33(10):5332\u20135345","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"10","key":"17834_CR12","doi-asserted-by":"publisher","first-page":"7010","DOI":"10.1109\/TPAMI.2021.3100277","volume":"44","author":"W Hu","year":"2022","unstructured":"Hu W, Liu H, Du Y, Yuan C, Li B, Maybank S (2022) Interaction-aware spatio-temporal pyramid attention networks for action classification. IEEE Trans Pattern Anal Mach Intell 44(10):7010\u20137028","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17834_CR13","doi-asserted-by":"crossref","unstructured":"Wang F, Geng S, Zhang D, Zhou M, Nian W, Li L (2022) A fine-grained classification method of thangka image based on senet. In: 2022 International Conference on Cyberworlds (CW), pp 23\u201330","DOI":"10.1109\/CW55638.2022.00013"},{"key":"17834_CR14","doi-asserted-by":"publisher","first-page":"16644","DOI":"10.1109\/ACCESS.2023.3246730","volume":"11","author":"MP Paing","year":"2023","unstructured":"Paing MP, Pintavirooj C (2023) Adenoma dysplasia grading of colorectal polyps using fast fourier convolutional resnet (ffc-resnet). IEEE Access 11:16644\u201316656","journal-title":"IEEE Access"},{"issue":"5","key":"17834_CR15","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1109\/TBME.2022.3225261","volume":"70","author":"A Svecic","year":"2023","unstructured":"Svecic A, Francoeur J, Soulez G, Monet F, Kashyap R, Kadoury S (2023) Shape and flow sensing in arterial image guidance from uv exposed optical fibers based on spatio-temporal networks. IEEE Trans Biomed Eng 70(5):1692\u20131703","journal-title":"IEEE Trans Biomed Eng"},{"key":"17834_CR16","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1109\/JSTARS.2023.3235535","volume":"16","author":"H Zhang","year":"2023","unstructured":"Zhang H, Lei L, Ni W, Yang X, Tang T, Cheng K, Xiang D, Kuang G (2023) Optical and sar image dense registration using a robust deep optical flow framework. IEEE J Sel Top Appl Earth Obs Remote Sens 16:1269\u20131294","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"key":"17834_CR17","doi-asserted-by":"publisher","first-page":"8003","DOI":"10.3390\/app13148003","volume":"13","author":"S Khan","year":"2023","unstructured":"Khan S, Hassan A, Hussain F, Perwaiz A, Riaz F, Alsabaan M, Abdul W (2023) Enhanced spatial stream of two-stream network using optical flow for human action recognition. Appl Sci 13:8003","journal-title":"Appl Sci"},{"key":"17834_CR18","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. 9912","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"17834_CR19","doi-asserted-by":"crossref","unstructured":"Zhu W, Tan Y (2023) A moving infrared small target detection method based on optical flow-guided neural networks. In: 2023 4th International conference on computer vision, image and deep learning (CVIDL), pp 531\u2013535","DOI":"10.1109\/CVIDL58838.2023.10166466"},{"issue":"4","key":"17834_CR20","doi-asserted-by":"publisher","first-page":"2071","DOI":"10.1109\/TAFFC.2022.3197622","volume":"13","author":"M Alkaddour","year":"2022","unstructured":"Alkaddour M, Tariq U, Dhall A (2022) Self-supervised approach for facial movement based optical flow. IEEE Trans Affect Comput 13(4):2071\u20132085","journal-title":"IEEE Trans Affect Comput"},{"key":"17834_CR21","doi-asserted-by":"crossref","unstructured":"Khairallah MZ, Bonardi F, Roussel D, Bouchafa S (2022) Pca event-based optical flow: a fast and accurate 2d motion estimation. In: 2022 IEEE International conference on image processing (ICIP), pp 3521\u20133525","DOI":"10.1109\/ICIP46576.2022.9897875"},{"key":"17834_CR22","doi-asserted-by":"crossref","unstructured":"Luo Y, Ying X, Li R, Wan Y, Hu B, Ling Q (2022) Multi-scale optical flow estimation for video infrared small target detection. In: 2022 2nd International conference on computer science, electronic information engineering and intelligent control technology (CEI), pp 129\u2013132","DOI":"10.1109\/CEI57409.2022.9950186"},{"key":"17834_CR23","doi-asserted-by":"crossref","unstructured":"Dobri\u010dki T, Zhuang X, Won KJ, Hong B-W (2022) Survey on unsupervised learning methods for optical flow estimation. In: 2022 13th International conference on information and communication technology convergence (ICTC), pp 591\u2013594","DOI":"10.1109\/ICTC55196.2022.9952910"},{"key":"17834_CR24","doi-asserted-by":"crossref","unstructured":"Owoyemi J, Hashimoto K (2017) Learning human motion intention with 3d convolutional neural network. In: 2017 IEEE International conference on mechatronics and automation (ICMA), pp 1810\u20131815","DOI":"10.1109\/ICMA.2017.8016092"},{"key":"17834_CR25","doi-asserted-by":"crossref","unstructured":"Lai Y-C, Huang R-J, Kuo Y-P, Tsao C-Y, Wang J-H, Chang C-C Underwater target tracking via 3d convolutional networks. In: 2019 IEEE 6th International conference on industrial engineering and applications (ICIEA), pp 485\u2013490","DOI":"10.1109\/IEA.2019.8715217"},{"key":"17834_CR26","doi-asserted-by":"crossref","unstructured":"Anshu AK, Arya KV, Gupta A (2020) View invariant gait feature extraction using temporal pyramid pooling with 3d convolutional neural network. In: 2020 IEEE 15th International conference on industrial and information systems (ICIIS), pp 242\u2013246","DOI":"10.1109\/ICIIS51140.2020.9342689"},{"issue":"3","key":"17834_CR27","first-page":"3347","volume":"45","author":"M Wang","year":"2023","unstructured":"Wang M, Xing J, Su J, Chen J, Liu Y (2023) Learning spatiotemporal and motion features in a unified 2d network for action recognition. IEEE Trans Pattern Anal Mach Intell 45(3):3347\u20133362","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17834_CR28","doi-asserted-by":"crossref","unstructured":"Miao X, Ke X (2022) Real-time action detection method based on multi-scale spatiotemporal feature. In: 2022 International conference on image processing, computer vision and machine learning (ICICML), pp 245\u2013248","DOI":"10.1109\/ICICML57342.2022.10009833"},{"issue":"8","key":"17834_CR29","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","volume":"42","author":"J Hu","year":"2020","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011\u20132023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"17834_CR30","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"S-H Gao","year":"2021","unstructured":"Gao S-H, Cheng M-M, Zhao K, Zhang X-Y, Yang M-H, Torr P (2021) Res2net: a new multi-scale backbone architecture. IEEE Trans Pattern Anal Mach Intell 43(2):652\u2013662","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17834_CR31","unstructured":"Soomro K, Zamir A, Shah M (2012) Ucf101: A dataset of 101 human actions classes from videos in the wild. CoRR 12"},{"key":"17834_CR32","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) Hmdb: a large video database for human motion recognition. In: 2011 International conference on computer vision, pp 2556\u20132563","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"17834_CR33","doi-asserted-by":"crossref","unstructured":"Gangrade S, Sharma PC, Sharma AK (2023) Colonoscopy polyp segmentation using deep residual u-net with bottleneck attention module. In: 2023 Fifth International conference on electrical, computer and communication technologies (ICECCT), pp 1\u20136","DOI":"10.1109\/ICECCT56650.2023.10179818"},{"key":"17834_CR34","doi-asserted-by":"crossref","unstructured":"Li N, Guo R, Liu X, Wu L, Wang H (2022) Dental detection and classification of yolov3-spp based on convolutional block attention module. In: 2022 IEEE 8th International conference on computer and communications (ICCC), pp 2151\u20132156","DOI":"10.1109\/ICCC56324.2022.10065900"},{"key":"17834_CR35","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q (2020) Eca-net: Efficient channel attention for deep convolutional neural networks. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 11531\u201311539","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"17834_CR36","doi-asserted-by":"crossref","unstructured":"Jiang B, Wang M, Gan W, Wu W, Yan J (2021) Stm: spatiotemporal and motion encoding for action recognition. In: 2019 IEEE\/CVF International conference on computer vision (ICCV), pp 2000\u20132009","DOI":"10.1109\/ICCV.2019.00209"},{"key":"17834_CR37","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 6450\u20136459","DOI":"10.1109\/CVPR.2018.00675"},{"key":"17834_CR38","doi-asserted-by":"crossref","unstructured":"Wang L, Tong Z, Ji B, Wu G (2021) Tdn: Temporal difference networks for efficient action recognition. In: 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 1895\u20131904","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"17834_CR39","doi-asserted-by":"crossref","unstructured":"Wang Z, She Q, Smolic A (2021) Action-net: Multipath excitation for action recognition. In: 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 13209\u201313218","DOI":"10.1109\/CVPR46437.2021.01301"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17834-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17834-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17834-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T06:29:55Z","timestamp":1716618595000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17834-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"references-count":39,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["17834"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17834-0","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,15]]},"assertion":[{"value":"4 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 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 that there is no conflict of interests regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}