{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:14:06Z","timestamp":1743027246576,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463075"},{"type":"electronic","value":"9783031463082"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46308-2_23","type":"book-chapter","created":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:01:24Z","timestamp":1698602484000},"page":"277-288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Human Action Recognition Method Based on Spatio-temporal Relationship"],"prefix":"10.1007","author":[{"given":"Haigang","family":"Yu","sequence":"first","affiliation":[]},{"given":"Ning","family":"He","sequence":"additional","affiliation":[]},{"given":"Shengjie","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Wenjing","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,30]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., et al.: 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":"23_CR2","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., et al.: Tam: temporal adaptive module for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13708\u201313718 (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., et al.: 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":"23_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318\u2013335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19"},{"key":"23_CR5","unstructured":"Li, K., Li, X., Wang, Y., et al.: CT-net: channel tensorization network for video classification. arXiv preprint arXiv:2106.01603 (2021)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Lin, D.: Recognize actions by disentangling components of dynamics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00687"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Jiang, B., Wang, M.M., Gan, W., et al.: STM: spatiotemporal and motion encoding for action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2000\u20132009 (2019)","DOI":"10.1109\/ICCV.2019.00209"},{"key":"23_CR8","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. arXiv preprint arXiv:1406.2199 (2014)"},{"key":"23_CR9","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., Xiong, Y., Wang, Z., et al.: Temporal segment networks: Towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"23_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"23_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-030-58517-4_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Kwon","year":"2020","unstructured":"Kwon, H., Kim, M., Kwak, S., Cho, M.: Motionsqueeze: neural motion feature learning for video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 345\u2013362. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_21"},{"key":"23_CR13","unstructured":"Xu, K., Ba, J., Kiros, R., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"23_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-030-00928-1_48","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"AG Roy","year":"2018","unstructured":"Roy, A.G., Navab, N., Wachinger, C.: Concurrent spatial and channel \u2018squeeze & excitation\u2019 in fully convolutional networks. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 421\u2013429. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00928-1_48"},{"key":"23_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Gao, Z., Xie, J., Wang, Q., et al.: Global second-order pooling convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3024\u20133033 (2019)","DOI":"10.1109\/CVPR.2019.00314"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Liu. J.J., Hou, Q., Cheng, M.M., et al.: Improving convolutional networks with self-calibrated convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10096\u201310105 (2020)","DOI":"10.1109\/CVPR42600.2020.01011"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., Smolic, A.: Action-net: multipath excitation for action recognition. arXiv preprint arXiv:2103.07372 (2021)","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Materzynska, J., Xiao, T., Herzig, R., et al.: Something-else: compositional action recognition with spatial-temporal interaction networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131059 (2020)","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., et al.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Long, X., Gan, C., De Melo, G., et al.: Attention clusters: purely attention based local feature integration for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7834\u20137843 (2018)","DOI":"10.1109\/CVPR.2018.00817"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Meng, L., Zhao, B., Chang, B., et al.: Interpretable spatio-temporal attention for video action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00189"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Srivastava, A., Dutta, O., Gupta, J., et al.: A variational information bottleneck based method to compress sequential networks for human action recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2745\u20132754 (2021)","DOI":"10.1109\/WACV48630.2021.00279"},{"key":"23_CR25","unstructured":"Fan, Q., Chen, C.F.R., Kuehne, H., et al.: More is less: learning efficient video representations by big-little network and depthwise temporal aggregation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Luo, C., Yuille, A.L.: Grouped spatial-temporal aggregation for efficient action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5512\u20135521 (2019)","DOI":"10.1109\/ICCV.2019.00561"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, Y., Zhou, Z., et al.: Smallbignet: integrating core and contextual views for video classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1092\u20131101 (2020)","DOI":"10.1109\/CVPR42600.2020.00117"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46308-2_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:04:28Z","timestamp":1698602668000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46308-2_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463075","9783031463082"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46308-2_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"166","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}