{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:01:41Z","timestamp":1742972501141,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030687625"},{"type":"electronic","value":"9783030687632"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-68763-2_53","type":"book-chapter","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T16:28:24Z","timestamp":1613838504000},"page":"701-713","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Compressed Video Action Recognition Using Motion Vector Representation"],"prefix":"10.1007","author":[{"given":"Chenghui","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,21]]},"reference":[{"key":"53_CR1","doi-asserted-by":"crossref","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A., Gould, S.: Dynamic image networks for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3034\u20133042 (2016)","DOI":"10.1109\/CVPR.2016.331"},{"key":"53_CR2","unstructured":"Bross, B., Han, W.J., Ohm, J.R., Sullivan, G.J., Wang, Y.K., Wiegand, T.: High efficiency video coding (hevc) text specification draft 10 (for fdis & final call). Joint Collaborative Team on Video Coding (JCT-VC) of ITU-T SG16 WP3 and ISO\/IEC JTC1\/SC29\/WG11, JCTVCL1003. v34 (2013)"},{"key":"53_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":"53_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: 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":"53_CR5","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Van Gool, L.: Deep temporal linear encoding networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2329\u20132338 (2017)","DOI":"10.1109\/CVPR.2017.168"},{"key":"53_CR6","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110\u20131118 (2015)"},{"key":"53_CR7","doi-asserted-by":"crossref","unstructured":"Fernando, B., Gavves, E., Oramas, J.M., Ghodrati, A., Tuytelaars, T.: Modeling video evolution for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5378\u20135387 (2015)","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"53_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"53_CR9","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"},{"issue":"4","key":"53_CR10","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1145\/103085.103090","volume":"34","author":"D Le Gall","year":"1991","unstructured":"Le Gall, D.: Mpeg: a video compression standard for multimedia applications. Commun. ACM 34(4), 46\u201358 (1991)","journal-title":"Commun. ACM"},{"issue":"4","key":"53_CR11","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1109\/76.313138","volume":"4","author":"R Li","year":"1994","unstructured":"Li, R., Zeng, B., Liou, M.L.: A new three-step search algorithm for block motion estimation. IEEE Trans. Circ. Syst. Video Technol 4(4), 438\u2013442 (1994)","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"53_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-319-46487-9_50","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Liu","year":"2016","unstructured":"Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816\u2013833. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_50"},{"key":"53_CR13","doi-asserted-by":"crossref","unstructured":"Lu, T., Ai, S., Jiang, Y., Xiong, Y., Min, F.: Deep optical flow feature fusion based on 3D convolutional networks for video action recognition. In: 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld\/SCALCOM\/UIC\/ATC\/CBDCom\/IOP\/SCI), pp. 1077\u20131080. IEEE (2018)","DOI":"10.1109\/SmartWorld.2018.00187"},{"issue":"7","key":"53_CR14","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TMM.2017.2666540","volume":"19","author":"Y Shi","year":"2017","unstructured":"Shi, Y., Tian, Y., Wang, Y., Huang, T.: Sequential deep trajectory descriptor for action recognition with three-stream CNN. IEEE Trans. Multimedia 19(7), 1510\u20131520 (2017)","journal-title":"IEEE Trans. Multimedia"},{"key":"53_CR15","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":"53_CR16","unstructured":"Song, X., Lan, C., Zeng, W., Xing, J., Sun, X., Yang, J.: Temporal-spatial mapping for action recognition. IEEE Trans. Circ. Syst. Video Technol. 30, 748\u2013759 (2019)"},{"key":"53_CR17","unstructured":"Soomro, K., Zamir, A., Shah, M.: Ucf101-action recognition data set (2017)"},{"key":"53_CR18","doi-asserted-by":"crossref","unstructured":"Sullivan, G.J., Baker, R.L.: Efficient quadtree coding of images and video. In: Proceedings ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing (2002)","DOI":"10.1109\/ICASSP.1991.150949"},{"key":"53_CR19","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":"53_CR20","unstructured":"Tran, D., Ray, J., Shou, Z., Chang, S.F., Paluri, M.: Convnet architecture search for spatiotemporal feature learning. arXiv preprint arXiv:1708.05038 (2017)"},{"issue":"6","key":"53_CR21","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2017","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1510\u20131517 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"53_CR22","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., 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"},{"issue":"3","key":"53_CR23","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1109\/TMM.2017.2749159","volume":"20","author":"X Wang","year":"2017","unstructured":"Wang, X., Gao, L., Wang, P., Sun, X., Liu, X.: Two-stream 3-D convnet fusion for action recognition in videos with arbitrary size and length. IEEE Trans. Multimedia 20(3), 634\u2013644 (2017)","journal-title":"IEEE Trans. Multimedia"},{"key":"53_CR24","unstructured":"Wiegand, T., Sullivan, G.J., Bjontegaard, G., Luthra, A.: Overview of the h. 264\/avc video coding standard. IEEE Trans. Circ. Syst. Video Technol. 13(7), 560\u2013576 (2003)"},{"key":"53_CR25","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A.J., Kr\u00e4henb\u00fchl, P.: Compressed video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6026\u20136035 (2018)","DOI":"10.1109\/CVPR.2018.00631"},{"issue":"5","key":"53_CR26","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TIP.2018.2791180","volume":"27","author":"B Zhang","year":"2018","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with deeply transferred motion vector CNNs. IEEE Trans. Image Process. 27(5), 2326\u20132339 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"53_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/978-3-030-20893-6_23","volume-title":"Computer Vision \u2013 ACCV 2018","author":"Y Zhu","year":"2019","unstructured":"Zhu, Y., Lan, Z., Newsam, S., Hauptmann, A.: Hidden two-stream convolutional networks for action recognition. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 363\u2013378. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_23"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-68763-2_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T17:40:33Z","timestamp":1613842833000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-68763-2_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030687625","9783030687632"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-68763-2_53","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":"21 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ICPR2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpr2020.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}