{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T11:35:25Z","timestamp":1773142525125,"version":"3.50.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585389","type":"print"},{"value":"9783030585396","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58539-6_17","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:02:46Z","timestamp":1604689366000},"page":"275-291","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["Directional Temporal Modeling for Action Recognition"],"prefix":"10.1007","author":[{"given":"Xinyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Tighe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"17_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":"17_CR2","doi-asserted-by":"publisher","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733, July 2017. https:\/\/doi.org\/10.1109\/CVPR.2017.502","DOI":"10.1109\/CVPR.2017.502"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition. A new model and the kinetics dataset. CoRR, abs\/1705.07750 2, 3 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"17_CR4","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":"17_CR5","unstructured":"Fan, Q., Chen, C.F.R., Kuehne, H., Pistoia, M., Cox, D.: More is less: learning efficient video representations by temporal aggregation modules. In: Advances in Neural Information Processing Systems, vol. 33 (2019)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"17_CR7","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"},{"issue":"4","key":"17_CR8","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/TPAMI.2016.2558148","volume":"39","author":"B Fernando","year":"2016","unstructured":"Fernando, B., Gavves, E., Oramas, J., Ghodrati, A., Tuytelaars, T.: Rank pooling for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 773\u2013787 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR9","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":"17_CR10","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The something something video database for learning and evaluating visual common sense. In: ICCV, vol. 1, p. 3 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"17_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"17_CR15","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information processing Systems, pp. 1097\u20131105 (2012)"},{"key":"17_CR16","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":"3","key":"17_CR17","first-page":"73","volume":"1","author":"X Li","year":"2017","unstructured":"Li, X., et al.: Progress estimation and phase detection for sequential processes. Proc. ACM Interact. Mob. Wearable Ubiquit. Technol. 1(3), 73 (2017)","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquit. Technol."},{"key":"17_CR18","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.: Videolstm convolves, attends and flows for action recognition. Comput. Vis. Image Underst. 166, 41\u201350 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"17_CR20","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 4898\u20134906 (2016)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Martinez, B., Modolo, D., Xiong, Y., Tighe, J.: Action recognition with spatial-temporal discriminative filter banks. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00558"},{"key":"17_CR22","doi-asserted-by":"publisher","first-page":"137","DOI":"10.5201\/ipol.2013.26","volume":"2013","author":"JS P\u00e9rez","year":"2013","unstructured":"P\u00e9rez, J.S., Meinhardt-Llopis, E., Facciolo, G.: Tv-l1 optical flow estimation. Image Process. On Line 2013, 137\u2013150 (2013)","journal-title":"Image Process. On Line"},{"issue":"11","key":"17_CR23","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Shen, T., Zhou, T., Long, G., Jiang, J., Pan, S., Zhang, C.: DiSAN: directional self-attention network for RNN\/CNN-free language understanding. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11941"},{"key":"17_CR25","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":"17_CR26","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: A dataset of 101 human action classes from videos in the wild. Center for Research in Computer Vision (2012)"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"17_CR28","unstructured":"Sun, K., et al.: High-resolution representations for labeling pixels and regions. CoRR abs\/1904.04514 (2019)"},{"key":"17_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/978-3-642-15567-3_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"GW Taylor","year":"2010","unstructured":"Taylor, G.W., Fergus, R., LeCun, Y., Bregler, C.: Convolutional learning of spatio-temporal features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 140\u2013153. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15567-3_11"},{"key":"17_CR30","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":"17_CR31","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"17_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"17_CR33","unstructured":"Wang, F., et al.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2017)"},{"key":"17_CR34","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":"17_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 399\u2013417 (2018)","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"17_CR40","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, pp. 4694\u20134702 (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 803\u2013818 (2018)","DOI":"10.1007\/978-3-030-01246-5_49"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58539-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:11:08Z","timestamp":1730851868000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58539-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585389","9783030585396"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58539-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}