{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:10:26Z","timestamp":1742933426759,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030922696"},{"type":"electronic","value":"9783030922702"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-92270-2_49","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T11:06:00Z","timestamp":1638788760000},"page":"573-584","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Lightweight Multidimensional Self-attention Network for\u00a0Fine-Grained Action Recognition"],"prefix":"10.1007","author":[{"given":"Hao","family":"Liu","sequence":"first","affiliation":[]},{"given":"Shenglan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Lianyu","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Heyu","family":"Fu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,7]]},"reference":[{"key":"49_CR1","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: Finegym: a hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"49_CR2","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":"49_CR3","unstructured":"Wang, Y., Wang, S., Tang, J., O\u2019Hare, N., Chang, Y., Li, B.: Hierarchical attention network for action recognition in videos. arXiv preprint arXiv:1607.06416 (2016)"},{"key":"49_CR4","doi-asserted-by":"crossref","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)","DOI":"10.1145\/3343031.3350876"},{"key":"49_CR5","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv preprint arXiv:1511.04119 (2015)"},{"key":"49_CR6","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. arXiv preprint arXiv:1406.2199 (2014)"},{"key":"49_CR7","doi-asserted-by":"crossref","unstructured":"Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6016\u20136025 (2018)","DOI":"10.1109\/CVPR.2018.00630"},{"key":"49_CR8","unstructured":"Huang, G., Bors, A.G.: Video classification with finecoarse networks. arXiv preprint arXiv:2103.15584 (2021)"},{"key":"49_CR9","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"49_CR10","unstructured":"Perez-Rua, J.-M., Martinez, B., Zhu, X., Toisoul, A., Escorcia, V., Xiang, T.: Knowing what, where and when to look: efficient video action modeling with attention. arXiv preprint arXiv:2004.01278 (2020)"},{"key":"49_CR11","doi-asserted-by":"publisher","first-page":"9532","DOI":"10.1109\/TIP.2020.3028207","volume":"29","author":"L Shi","year":"2020","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans. Image Process. 29, 9532\u20139545 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"49_CR13","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.neucom.2020.06.108","volume":"413","author":"S Liu","year":"2020","unstructured":"Liu, S., et al.: FSD-10: a fine-grained classification dataset for figure skating. Neurocomputing 413, 360\u2013367 (2020)","journal-title":"Neurocomputing"},{"key":"49_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., Vasconcelos, N.: Resound: towards action recognition without representation bias. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 513\u2013528 (2018)","DOI":"10.1007\/978-3-030-01231-1_32"},{"issue":"7","key":"49_CR15","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1007\/s00138-018-0956-5","volume":"29","author":"H Zhang","year":"2018","unstructured":"Zhang, H., Xin, M., Wang, S., Yang, Y., Zhang, L., Wang, H.: End-to-end temporal attention extraction and human action recognition. Mach. Vis. Appl. 29(7), 1127\u20131142 (2018). https:\/\/doi.org\/10.1007\/s00138-018-0956-5","journal-title":"Mach. Vis. Appl."},{"key":"49_CR16","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? arXiv preprint arXiv:2102.05095 (2021)"},{"key":"49_CR17","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"49_CR18","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"49_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: 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":"49_CR20","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":"49_CR21","doi-asserted-by":"crossref","unstructured":"Hu, L., Feng, L., Liu, S.: Hfnet: a novel model for human focused sports action recognition. In: Proceedings of the 3rd International Workshop on Multimedia Content Analysis in Sports, pp. 35\u201343 (2020)","DOI":"10.1145\/3422844.3423052"},{"key":"49_CR22","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, J.: 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":"49_CR23","doi-asserted-by":"crossref","unstructured":"Yu, B., Yin, H., Zhu, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875 (2017)","DOI":"10.24963\/ijcai.2018\/505"},{"key":"49_CR24","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S. : Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"49_CR25","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, H., 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"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92270-2_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:29:41Z","timestamp":1710257381000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92270-2_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030922696","9783030922702"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92270-2_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}