{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T13:08:53Z","timestamp":1783948133893,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819699070","type":"print"},{"value":"9789819699087","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9908-7_23","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T16:26:14Z","timestamp":1753374374000},"page":"277-289","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MCSTN: A Novel Multi-feature Fusion-Based Action Recognition Model"],"prefix":"10.1007","author":[{"given":"Wei","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In:\u00a02017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Luo, C., Yuille, A.L.: Grouped spatial-temporal aggregation for efficient action recognition. In:\u00a02019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5511\u20135520 (2019)","DOI":"10.1109\/ICCV.2019.00561"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In:\u00a0European Conference on Computer Vision, pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In:\u00a02019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6201\u20136210 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In:\u00a02016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"23_CR6","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"23_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"23_CR8","unstructured":"Zhang, B., et al.: Co-training transformer with videos and images improves action recognition. arXiv preprint arXiv:2112.07175 (2021)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu, M., Schmid, C.: ViViT: a video vision transformer. In:\u00a02021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"23_CR10","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: The 38th International Conference on Machine Learning (ICML), vol. 2, no. 3, p. 4 (2021)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., Smolic, A.: ACTION-net: multipath excitation for action recognition. In:\u00a02021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13209\u201313218 (2021)","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In:\u00a02016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR13","unstructured":"Soomro, K., Zamir, A. R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201cSomething Something\u201d video database for learning and evaluating visual common sense. In:\u00a02017 IEEE International Conference on Computer Vision (ICCV), pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: TEINet: towards an efficient architecture for video recognition. In:\u00a0AAAI Conference on Artificial Intelligence, vol. 34, no. 7, pp. 11669\u201311676 (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T.: TAM: temporal adaptive module for video recognition. In:\u00a02021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 13688\u201313698 (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"23_CR17","unstructured":"Zhang, C., Zou, Y., Chen, G., Gan, L.: PAN: towards fast action recognition via learning persistence of appearance. arXiv preprint arXiv:2008.03462 (2020)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In:\u00a02021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"23_CR19","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1007\/s11263-022-01661-1","volume":"130","author":"Y Tian","year":"2022","unstructured":"Tian, Y., Yan, Y., Zhai, G., Guo, G., Gao, Z.: EAN: event adaptive network for enhanced action recognition. Int. J. Comput. Vision 130, 2453\u20132471 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"23_CR20","unstructured":"Li, K., Wang, Y., Gao, P., Song, G., Liu, Y., Li, H.: UniFormer: unified transformer for efficient spatiotemporal representation learning. arXiv preprint arXiv:2201.04676 (2022)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z.: Video swin transformer. In:\u00a02022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3192\u20133201 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Multiview transformers for video recognition. In:\u00a02022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3323\u20133333 (2022)","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Frozen CLIP models are efficient video learners. In:\u00a0European Conference on Computer Vision, pp. 388\u2013404 (2022)","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"23_CR24","unstructured":"Li, K., et al.: UniFormerV2: spatiotemporal learning by arming image ViTs with video UniFormer. arXiv preprint arXiv:2211.09552 (2023)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Mirza, M.J., Micorek, J., Possegger, H., Bischof, H.: The norm must go on: dynamic unsupervised domain adaptation by normalization. In:\u00a02022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14745\u201314755 (2022)","DOI":"10.1109\/CVPR52688.2022.01435"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Lin, W., Mirza, M.J., Kozinski, M., Possegger, H., Kuehne, H., Bischof, H.: Video test-time adaptation for action recognition. In:\u00a02023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22952\u201322961 (2023)","DOI":"10.1109\/CVPR52729.2023.02198"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9908-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T12:27:25Z","timestamp":1783945645000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9908-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819699070","9789819699087"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9908-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}