{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T03:47:32Z","timestamp":1761709652381,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030316532"},{"type":"electronic","value":"9783030316549"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-31654-9_3","type":"book-chapter","created":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T00:05:31Z","timestamp":1572480331000},"page":"26-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-scale Spatial-Temporal Attention for Action Recognition"],"prefix":"10.1007","author":[{"given":"Qing","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Hongping","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Lingfeng","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,10,31]]},"reference":[{"key":"3_CR1","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. Comput. Sci. (2015)"},{"key":"3_CR2","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.patrec.2018.07.034","volume":"112","author":"TZ Yu","year":"2018","unstructured":"Yu, T.Z., Guo, C.X., Wang, L.F., Gu, H.X., Xiang, S.M., Pan, C.H.: Joint spatial-temporal attention for action recognition. Pattern Recogn. Lett. 112, 226\u2013233 (2018)","journal-title":"Pattern Recogn. Lett."},{"issue":"5247","key":"3_CR3","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1126\/science.271.5247.348","volume":"271","author":"PW Dempsey","year":"1996","unstructured":"Dempsey, P.W., Allison, M.E.D., Akkaraju, S., et al.: C3d of complement as a molecular adjuvant: bridging innate and acquired immunity. Science 271(5247), 348\u2013350 (1996)","journal-title":"Science"},{"key":"3_CR4","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos (2014)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Balaguer, J.F., Gobbetti, E.: i3D: a high-speed 3D Web browser. In: Proceedings ACM Symposium on VRML, pp. 69\u201376 (1995)","DOI":"10.1145\/217306.217316"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"3_CR7","unstructured":"Wang, L., Xiong, Y., Wang, Z., et al.: Towards good practices for very deep two-stream ConvNets. Comput. Sci. (2015)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Computer Vision Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"3_CR9","unstructured":"Kosiorek, A.R., Bewley, A., Posner, I.: Hierarchical attentive recurrent tracking (2017)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Wang, F., Jiang, M., Qian, C., et al.: Residual attention network for image classification (2017)","DOI":"10.1109\/CVPR.2017.683"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Albanie, S., et al.: Squeeze-and-excitation networks (2017)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3_CR12","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems (2014)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Yi, Y., Jiang, W., et al.: Attention to scale: scale-aware semantic image segmentation. In: IEEE Conference on Computer Vision Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.396"},{"issue":"1","key":"3_CR14","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/BF00126140","volume":"18","author":"L Florack","year":"1996","unstructured":"Florack, L., Romeny, B.T.H., Viergever, M., et al.: The Gaussian scale-space paradigm and the multiscale local jet. Int. J. Comput. Vision 18(1), 61\u201375 (1996)","journal-title":"Int. J. Comput. Vision"},{"issue":"4","key":"3_CR15","first-page":"640","volume":"39","author":"J Long","year":"2014","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640\u2013651 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Lin, G.S., Shen, C.H., Hengel, A., Reid, I.: Efficient piecewise training of deep structured models for semantic segmentation. In: CVPR, pp. 3194\u20133203 (2016)","DOI":"10.1109\/CVPR.2016.348"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR18","unstructured":"Clement, F., Couprie, C., Najman, L., et al.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. (2013)"},{"key":"3_CR19","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"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Feifei, L.: Large-scale video classification with convolutional neural networks. In: CVPR, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Shi, B.: Human action recognition using factorized spatio-temporal convolutional networks. In: ICCV, pp. 57\u201365 (2015)","DOI":"10.1109\/ICCV.2015.522"},{"key":"3_CR23","unstructured":"Rohit, G., Deva, R.: Attentional pooling for action recognition. In: NIPS, pp. 33\u201344 (2017)"},{"key":"3_CR24","unstructured":"Cao, C., Zhang, Y., Zhang, C., Lu, H.: Body joint guided 3D deep convolutional descriptors for action recognition, CoRR. abs\/1704.07160 (2017)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Yu, T., Gu, H., Wang, L., Xiang, S., Pan, C.: Cascaded temporal spatial features for video action recognition. In: ICIP, pp. 1552\u20131556 (2017)","DOI":"10.1109\/ICIP.2017.8296542"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"3_CR27","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild, CoRR. abs\/1212.0402 (2012)"},{"key":"3_CR28","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: ICCV, pp. 2556\u20132563 (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhu, M., Derpanis, K.: From actemes to action: a strongly-supervised representation for detailed action understanding. In: ICCV, pp. 2248\u20132255 (2013)","DOI":"10.1109\/ICCV.2013.280"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Garbade, M., Gall, J.: Pose for action-action for pose. In: FG, pp. 438\u2013445 (2017)","DOI":"10.1109\/FG.2017.61"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31654-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:04:27Z","timestamp":1730333067000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-31654-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030316532","9783030316549"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31654-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"31 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv2019.com\/en\/index.html","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":"412","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":"165","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":"40% - 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":"4","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":"4","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)"}}]}}