{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:49:37Z","timestamp":1742914177806,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787487"},{"type":"electronic","value":"9789819787494"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-8749-4_10","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:57:22Z","timestamp":1730303842000},"page":"139-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-modal Variable-Channel Spatial-Temporal Semantic Action Recognition Network"],"prefix":"10.1007","author":[{"given":"Yao","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"JiaHong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YaQin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"LiuMing","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/s10489-020-01823-z","volume":"51","author":"O Elharrouss","year":"2021","unstructured":"Elharrouss, O., Almaadeed, N., Al-Maadeed, S., Bouridane, A., Beghdadi, A.: A combined multiple action recognition and summarization for surveillance video sequences. Appl. Intell. 51, 690\u2013712 (2021)","journal-title":"Appl. Intell."},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Liu, K., Zhu, M., Fu, H., Ma, H., Chua, T.S.: Enhancing anomaly detection in surveillance videos with transfer learning from action recognition. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4664\u20134668 (2020)","DOI":"10.1145\/3394171.3416298"},{"issue":"11","key":"10_CR3","doi-asserted-by":"publisher","first-page":"22301","DOI":"10.1109\/TITS.2021.3135251","volume":"23","author":"F Xu","year":"2021","unstructured":"Xu, F., Xu, F., Xie, J., Pun, C.M., Lu, H., Gao, H.: Action recognition framework in traffic scene for autonomous driving system. IEEE Trans. Intell. Transp. Syst. 23(11), 22301\u201322311 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Liu, X., Pintea, S.L., Nejadasl, F.K., Booij, O., Van\u00a0Gemert, J.C.: No frame left behind: full video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14892\u201314901 (2021)","DOI":"10.1109\/CVPR46437.2021.01465"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3163\u20133172 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4486\u20134496 (2021)","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Chi, H.G., Ha, M.H., Chi, S., Lee, S.W., Huang, Q., Ramani, K.: InfoGCN: representation learning for human skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20186\u201320196 (2022)","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"10_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-030-58545-7_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Das","year":"2020","unstructured":"Das, S., Sharma, S., Dai, R., Br\u00e9mond, F., Thonnat, M.: VPN: learning video-pose embedding for activities of daily living. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part IX. LNCS, vol. 12354, pp. 72\u201390. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_5"},{"key":"10_CR10","unstructured":"Su, L., Hu, C., Li, G., Cao, D.: MSAF: multimodal split attention fusion. arXiv preprint arXiv:2012.07175 (2020)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: Ntu rgb+ d: a large scale dataset for 3D human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"issue":"10","key":"10_CR12","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: Ntu rgb+ d 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J.: Human action recognition from various data modalities: a review. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Naseer, M., Khan, S., Khan, F.S., Ryoo, M.S.: Self-supervised video transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2874\u20132884 (2022)","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Qiu, H., Hou, B., Ren, B., Zhang, X.: Spatio-temporal tuples transformer for skeleton-based action recognition. arXiv preprint arXiv:2201.02849 (2022)","DOI":"10.1016\/j.neucom.2022.10.084"},{"issue":"11","key":"10_CR16","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"10_CR17","unstructured":"Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019 (2015)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"10_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"12","key":"10_CR20","doi-asserted-by":"publisher","first-page":"4246","DOI":"10.3390\/s21124246","volume":"21","author":"MB Shaikh","year":"2021","unstructured":"Shaikh, M.B., Chai, D.: RGB-D data-based action recognition: a review. Sensors 21(12), 4246 (2021)","journal-title":"Sensors"},{"issue":"10s","key":"10_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2022","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. ACM Comput. Surv. (CSUR) 54(10s), 1\u201341 (2022)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"1","key":"10_CR22","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61\u201380 (2008)","journal-title":"IEEE Trans. Neural Netw."},{"key":"10_CR23","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"10_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107356","volume":"104","author":"J Li","year":"2020","unstructured":"Li, J., Xie, X., Pan, Q., Cao, Y., Zhao, Z., Shi, G.: SGM-net: skeleton-guided multimodal network for action recognition. Pattern Recogn. 104, 107356 (2020)","journal-title":"Pattern Recogn."},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Jing, Y., Wang, F.: TP-VIT: a two-pathway vision transformer for video action recognition. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2185\u20132189. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747276"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Ahn, D., Kim, S., Hong, H., Ko, B.C.: Star-transformer: a spatio-temporal cross attention transformer for human action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3330\u20133339 (2023)","DOI":"10.1109\/WACV56688.2023.00333"},{"issue":"2","key":"10_CR29","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","volume":"45","author":"YF Song","year":"2022","unstructured":"Song, Y.F., Zhang, Z., Shan, C., Wang, L.: Constructing stronger and faster baselines for skeleton-based action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1474\u20131488 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Liu, S.L., et al.: Multi-dimensional refinement graph convolutional network with robust decouple loss for fine-grained skeleton-based action recognition. arXiv preprint arXiv:2306.15321 (2023)","DOI":"10.1109\/TNNLS.2024.3384770"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a031 (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2969\u20132978 (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W.: Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13359\u201313368 (2021)","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Communications in Computer and Information Science","Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8749-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:12:31Z","timestamp":1730304751000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8749-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819787487","9789819787494"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8749-4_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPCSEE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of Pioneering Computer Scientists, Engineers and Educators","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpcsee2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.icpcsee.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}