{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:43:31Z","timestamp":1743108211100,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031202322"},{"type":"electronic","value":"9783031202339"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-20233-9_26","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:02:48Z","timestamp":1667433768000},"page":"257-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multidimension Joint Networks for Action Recognition"],"prefix":"10.1007","author":[{"given":"Wanhao","family":"Jia","sequence":"first","affiliation":[]},{"given":"Yi","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Tian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Wang Z, She Q, Smolic A. Action-net: multipath excitation for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13214\u201313223 (2021)","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Wang L, Tong Z, Ji B, et al.: TDN: temporal difference networks for efficient action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"26_CR3","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":"26_CR4","unstructured":"Chen, Y., Kalantidis, Y., Li, J., Yan, S., Feng, J.: A 2-nets: double attention networks. In: Advances in Neural Information Processing Systems, pp. 352\u2013361 (2018)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Hara,K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"26_CR7","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":"26_CR8","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, J., 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":"26_CR9","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: STM: spatiotemporal and motion encoding for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2000\u20132009 (2019)","DOI":"10.1109\/ICCV.2019.00209"},{"key":"26_CR11","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"26_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-030-01249-6_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Lee","year":"2018","unstructured":"Lee, M., Lee, S., Son, S., Park, G., Kwak, N.: Motion feature network: fixed motion filter for action recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 392\u2013408. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_24"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: TEA: temporal excitation and aggregation for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 909\u2013918 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: TEINet: towards an efficient architecture for video recognition. In: AAAI, pp. 11669\u201311676 (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12026\u201312035 (2019)","DOI":"10.1109\/CVPR.2019.01230"},{"key":"26_CR19","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Stroud, J., Ross, D., Sun, C., Deng, J., Sukthankar, R.: D3D: distilled 3d networks for video action recognition. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 625\u2013634 (2020)","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Escalera, S., Lanz, O.: Gate-shift networks for video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1102\u20131111 (2020)","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"26_CR22","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":"26_CR23","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":"26_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van Gool, L.: 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":"26_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., Zhou, B.: Temporal pyramid network for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 591\u2013600 (2020)","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"26_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1007\/978-3-030-01216-8_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Zolfaghari","year":"2018","unstructured":"Zolfaghari, M., Singh, K., Brox, T.: ECO: efficient convolutional network for online video understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 713\u2013730. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_43"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Jin, Y., Lu, J., Ruan, Q.: Coupled discriminative feature learning for heterogeneous face recognition. IEEE Trans. Inf. Forensics Secur. 10(3), 640\u2013652","DOI":"10.1109\/TIFS.2015.2390414"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Jin, Y., Chen, J., Kan, S., Cen, Y., Cao, Q.: PGAN: part-based nondirect coupling embedded GAN for person. IEEE MultiMedia 27(3), 23\u201333","DOI":"10.1109\/MMUL.2020.2999445"}],"container-title":["Lecture Notes in Computer Science","Biometric Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20233-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:28:36Z","timestamp":1667435316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20233-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031202322","9783031202339"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20233-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCBR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Biometric Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccbr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ccbr99.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"115","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":"70","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":"61% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}