{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:50:36Z","timestamp":1743000636298,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533075"},{"type":"electronic","value":"9783031533082"}],"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\/978-3-031-53308-2_36","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"494-506","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MoCap-Video Data Retrieval with\u00a0Deep Cross-Modal Learning"],"prefix":"10.1007","author":[{"given":"Lu","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jingliang","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Na","family":"Lv","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Caetano, C., Sena, J., Br\u00e9mond, F., Dos\u00a0Santos, J.A., Schwartz, W.R.: SkeleMotion: a new representation of skeleton joint sequences based on motion information for 3D action recognition. In: 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.\u00a01\u20138. IEEE (2019)","DOI":"10.1109\/AVSS.2019.8909840"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Gu, W., Gu, X., Gu, J., Li, B., Xiong, Z., Wang, W.: Adversary guided asymmetric hashing for cross-modal retrieval. In: Proceedings of the 2019 on International Conference on Multimedia Retrieval, pp. 159\u2013167 (2019)","DOI":"10.1145\/3323873.3325045"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Li, Z., Li, W., Li, X., Peng, J.: Generic video-based motion capture data retrieval. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1950\u20131957. IEEE (2019)","DOI":"10.1109\/APSIPAASC47483.2019.9023336"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Kapadia, M., Chiang, I., Thomas, T., Badler, N.I., Kider, J.T., Jr.: Efficient motion retrieval in large motion databases. In: Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, pp. 19\u201328 (2013)","DOI":"10.1145\/2448196.2448199"},{"key":"36_CR7","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"36_CR8","unstructured":"Le, L., Patterson, A., White, M.: Supervised autoencoders: improving generalization performance with unsupervised regularizers. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, M., Lee, D., Lee, S.: Hierarchically decomposed graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:2208.10741 (2022)","DOI":"10.1109\/ICCV51070.2023.00958"},{"key":"36_CR10","unstructured":"Li, L., Zheng, W., Zhang, Z., Huang, Y., Wang, L.: Skeleton-based relational modeling for action recognition. arXiv preprint arXiv:1805.02556 (2018)"},{"key":"36_CR11","unstructured":"Li, W., Huang, Y., Kuo, C.C.J., Peng, J., et\u00a0al.: Video-based human motion capture data retrieval via normalized motion energy image subspace projections. In: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 243\u2013248. IEEE (2017)"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Li, X., Hu, D., Nie, F.: Deep binary reconstruction for cross-modal hashing. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1398\u20131406 (2017)","DOI":"10.1145\/3123266.3123355"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Xia, R., Liu, X., Huang, Q.: Learning shape-motion representations from geometric algebra spatio-temporal model for skeleton-based action recognition. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 1066\u20131071. IEEE (2019)","DOI":"10.1109\/ICME.2019.00187"},{"key":"36_CR14","unstructured":"Li, Z., Guo, C., Feng, Z., Hwang, J.N., Jin, Y., Zhang, Y.: Image-text retrieval with binary and continuous label supervision. arXiv preprint arXiv:2210.11319 (2022)"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"36_CR16","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"issue":"6","key":"36_CR17","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1109\/TVCG.2017.2702620","volume":"24","author":"N Lv","year":"2017","unstructured":"Lv, N., Jiang, Z., Huang, Y., Meng, X., Meenakshisundaram, G., Peng, J.: Generic content-based retrieval of marker-based motion capture data. IEEE Trans. Vis. Comput. Graph. 24(6), 1969\u20131982 (2017)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"36_CR18","unstructured":"M\u00fcller, M., R\u00f6der, T., Clausen, M., Eberhardt, B., Kr\u00fcger, B., Weber, A.: Mocap database HDM05. Institut f\u00fcr Informatik II, Universit\u00e4t Bonn 2(7) (2007)"},{"key":"36_CR19","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":"36_CR20","doi-asserted-by":"crossref","unstructured":"Numaguchi, N., Nakazawa, A., Shiratori, T., Hodgins, J.K.: A puppet interface for retrieval of motion capture data. In: Proceedings of the 2011 ACM SIGGRAPH\/Eurographics Symposium on Computer Animation, pp. 157\u2013166 (2011)","DOI":"10.1145\/2019406.2019427"},{"key":"36_CR21","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: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1010\u20131019. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"36_CR22","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"36_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.sigpro.2015.01.004","volume":"113","author":"J Xiao","year":"2015","unstructured":"Xiao, J., Tang, Z., Feng, Y., Xiao, Z.: Sketch-based human motion retrieval via selected 2D geometric posture descriptor. Sig. Process. 113, 1\u20138 (2015)","journal-title":"Sig. Process."},{"key":"36_CR24","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s00500-015-1889-9","volume":"21","author":"Q Xiao","year":"2017","unstructured":"Xiao, Q., Siqi, L.: Motion retrieval based on dynamic Bayesian network and canonical time warping. Soft. Comput. 21, 267\u2013280 (2017)","journal-title":"Soft. Comput."},{"key":"36_CR25","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":"36_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-030-01240-3_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"P Zhang","year":"2018","unstructured":"Zhang, P., Xue, J., Lan, C., Zeng, W., Gao, Z., Zheng, N.: Adding attentiveness to the neurons in recurrent neural networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 136\u2013152. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_9"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53308-2_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:13:23Z","timestamp":1710242003000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53308-2_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533075","9783031533082"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53308-2_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","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":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","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":"112","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":"38% - 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":"3.2","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":"3.2","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)"}}]}}