{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:16:08Z","timestamp":1726038968106},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030275341"},{"type":"electronic","value":"9783030275358"}],"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\/978-3-030-27535-8_41","type":"book-chapter","created":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T20:26:01Z","timestamp":1564691161000},"page":"461-471","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Select and Focus: Action Recognition with Spatial-Temporal Attention"],"prefix":"10.1007","author":[{"given":"Wensong","family":"Chan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuguang","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,2]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"41_CR2","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. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Zhu, W., et al.: Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: AAAI Conference on Artificial Intelligence, p. 6 (2016)","DOI":"10.1609\/aaai.v30i1.10451"},{"key":"41_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-319-10602-1_38","volume-title":"Computer Vision \u2013 ECCV 2014","author":"X Peng","year":"2014","unstructured":"Peng, X., Zou, C., Qiao, Y., Peng, Q.: Action recognition with stacked fisher vectors. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 581\u2013595. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_38"},{"key":"41_CR5","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35, 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR6","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2018","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40, 1510\u20131517 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR7","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":"41_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron, G., Laptev, I., Schmid, C.: P-CNN: pose-based CNN features for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3218\u20133226 (2015)","DOI":"10.1109\/ICCV.2015.368"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"41_CR11","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. In: ICLR Workshop (2016)"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Luong, M.-T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"41_CR13","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"41_CR14","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: AAAI Conference on Artificial Intelligence, pp. 4263\u20134270 (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos \u201cin the wild\u201d. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1996\u20132003 (2009)","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"41_CR17","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":"41_CR18","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 2556\u20132563 (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"41_CR19","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., Snoek, C.G.M.: Videolstm convolves, attends and flows for action recognition. Comput. Vis. Image Underst. 166, 41\u201350 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: ActionVLAD: learning spatio-temporal aggregation for action classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p. 3 (2017)","DOI":"10.1109\/CVPR.2017.337"},{"key":"41_CR21","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 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"41_CR22","unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. In: Advances in Neural Information Processing Systems, pp. 34\u201345 (2017)"},{"key":"41_CR23","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)"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7299101"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-27535-8_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T01:23:18Z","timestamp":1664068998000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-27535-8_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030275341","9783030275358"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27535-8_41","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":"2 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","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 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}