{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:29:57Z","timestamp":1743071397028,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030341190"},{"type":"electronic","value":"9783030341206"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-34120-6_7","type":"book-chapter","created":{"date-parts":[[2019,11,27]],"date-time":"2019-11-27T17:03:47Z","timestamp":1574874227000},"page":"81-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Spatial-Temporal Bottom-Up Top-Down Attention Model for Action Recognition"],"prefix":"10.1007","author":[{"given":"Jinpeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andy J.","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,28]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp. 4724\u20134733. IEEE (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Van Gool, L.: Deep temporal linear encoding networks. In: CVPR, vol. 1 (2017)","DOI":"10.1109\/CVPR.2017.168"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Du, Y., Yuan, C., Li, B., Zhao, L., Li, Y., Hu, W.: Interaction-aware spatio-temporal pyramid attention networks for action classification. arXiv preprint arXiv:1808.01106 (2018)","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: Advances in Neural Information Processing Systems, pp. 3468\u20133476 (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.: Actionvlad: learning spatio-temporal aggregation for action classification. In: CVPR, vol. 2, p. 3 (2017)","DOI":"10.1109\/CVPR.2017.337"},{"key":"7_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":"7_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507 7 (2017)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"7_CR9","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"7_CR10","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"7_CR11","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/978-3-642-33374-3_41","volume-title":"High Performance Computing in Science and Engineering 2012","author":"H Kuehne","year":"2013","unstructured":"Kuehne, H., Jhuang, H., Stiefelhagen, R., Serre, T.: HMDB51: a large video database for human motion recognition. In: Nagel, W., Kr\u00f6ner, D., Resch, M. (eds.) High Performance Computing in Science and Engineering 2012, pp. 571\u2013582. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-33374-3_41"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Long, X., Gan, C., de Melo, G., Wu, J., Liu, X., Wen, S.: Attention clusters: purely attention based local feature integration for video classification. In: CVPR, pp. 7834\u20137843 (2018)","DOI":"10.1109\/CVPR.2018.00817"},{"key":"7_CR13","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: NIPS, pp. 2204\u20132212 (2014)"},{"key":"7_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., et al.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"7_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":"7_CR18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: AAAI, vol. 4, p. 12 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"7_CR20","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: NIPS, pp. 1799\u20131807 (2014)"},{"key":"7_CR21","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks"},{"key":"7_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"7_CR23","unstructured":"Wang, F., et al.: Residual attention network for image classification. arXiv preprint arXiv:1704.06904 (2017)"},{"key":"7_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., 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":"7_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Y., Long, M., Wang, J., Philip, S.Y.: Spatiotemporal pyramid network for video action recognition. In: CVPR, vol. 6, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.226"},{"key":"7_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"7_CR28","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: CVPR, pp. 6026\u20136035 (2018)","DOI":"10.1109\/CVPR.2018.00631"},{"key":"7_CR29","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057 (2015)"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Sun, X., Zha, Z.J., Zeng, W.: MiCT: mixed 3D\/2D convolutional tube for human action recognition. In: CVPR, pp. 449\u2013458 (2018)","DOI":"10.1109\/CVPR.2018.00054"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-34120-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:16:47Z","timestamp":1693527407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-34120-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030341190","9783030341206"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-34120-6_7","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":"28 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.csig.org.cn\/detail\/2669","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}