{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T18:44:51Z","timestamp":1746816291595,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585761"},{"type":"electronic","value":"9783030585778"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58577-8_3","type":"book-chapter","created":{"date-parts":[[2020,9,23]],"date-time":"2020-09-23T14:04:27Z","timestamp":1600869867000},"page":"35-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition"],"prefix":"10.1007","author":[{"given":"Niamul","family":"Quader","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juwei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,24]]},"reference":[{"key":"3_CR1","unstructured":"Green 500 List for June 2016. https:\/\/www.top500.org\/green500\/lists\/2016\/06\/. Accessed 8 Nov 2019"},{"key":"3_CR2","unstructured":"Carreira, J., Noland, E., Hillier, C., Zisserman, A.: A short note on the kinetics-700 human action dataset. arXiv preprint arXiv:1907.06987 (2019)"},{"key":"3_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":"3_CR4","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":"3_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4768\u20134777 (2017)","DOI":"10.1109\/CVPR.2017.787"},{"key":"3_CR6","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":"3_CR7","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV, vol. 1, p. 3 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1321\u20131330. JMLR.org (2017)","DOI":"10.1109\/WACV.2018.00149"},{"key":"3_CR9","unstructured":"He, D., et al.: Stnet: local and global spatial-temporal modeling for action recognition. arXiv preprint arXiv:1811.01549 (2018)"},{"key":"3_CR10","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"3_CR11","unstructured":"Huang, G., Chen, D., Li, T., Wu, F., Van Der Maaten, L., Weinberger, K.Q.: Multi-scale dense convolutional networks for efficient prediction. arXiv preprint arXiv:1703.09844 (2017)"},{"issue":"4","key":"3_CR12","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1109\/TIP.2018.2877936","volume":"28","author":"W Huang","year":"2018","unstructured":"Huang, W., et al.: Toward efficient action recognition: principal backpropagation for training two-stream networks. IEEE Trans. Image Process. 28(4), 1773\u20131782 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: STM: spatiotemporal and motion encoding for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2000\u20132009 (2019)","DOI":"10.1109\/ICCV.2019.00209"},{"key":"3_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"},{"issue":"5","key":"3_CR15","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/BF00336961","volume":"50","author":"JJ Koenderink","year":"1984","unstructured":"Koenderink, J.J.: The structure of images. Biol. Cybern. 50(5), 363\u2013370 (1984)","journal-title":"Biol. Cybern."},{"issue":"3","key":"3_CR16","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/BF00364135","volume":"58","author":"JJ Koenderink","year":"1988","unstructured":"Koenderink, J.J.: Scale-time. Biol. Cybern. 58(3), 159\u2013162 (1988)","journal-title":"Biol. Cybern."},{"key":"3_CR17","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":"3_CR18","unstructured":"Lin, J., Rao, Y., Lu, J., Zhou, J.: Runtime neural pruning. In: Advances in Neural Information Processing Systems, pp. 2181\u20132191 (2017)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Luo, C., Yuille, A.L.: Grouped spatial-temporal aggregation for efficient action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5512\u20135521 (2019)","DOI":"10.1109\/ICCV.2019.00561"},{"key":"3_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":"3_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, pp. 5482\u20135491 (2019)","DOI":"10.1109\/ICCV.2019.00558"},{"issue":"2","key":"3_CR22","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.bandc.2004.08.035","volume":"57","author":"M Mermillod","year":"2005","unstructured":"Mermillod, M., Guyader, N., Chauvin, A.: The coarse-to-fine hypothesis revisited: evidence from neuro-computational modeling. Brain Cogn. 57(2), 151\u2013157 (2005)","journal-title":"Brain Cogn."},{"key":"3_CR23","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"3_CR24","doi-asserted-by":"publisher","first-page":"142","DOI":"10.3389\/fncom.2015.00142","volume":"9","author":"AJ Rodr\u00edguez-S\u00e1nchez","year":"2015","unstructured":"Rodr\u00edguez-S\u00e1nchez, A.J., Fallah, M., Leonardis, A.: Hierarchical object representations in the visual cortex and computer vision. Front. Comput. Neurosci. 9, 142 (2015)","journal-title":"Front. Comput. Neurosci."},{"key":"3_CR25","volume-title":"Multiresolution Image Processing and Analysis","author":"A Rosenfeld","year":"2013","unstructured":"Rosenfeld, A.: Multiresolution Image Processing and Analysis, vol. 12. Springer, Heidelberg (2013)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, Y., Hu, J., Cheng, J., Lu, H.: Gesture recognition using spatiotemporal deformable convolutional representation. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 1900\u20131904. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803152"},{"key":"3_CR27","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":"3_CR28","unstructured":"Stroud, J.C., Ross, D.A., Sun, C., Deng, J., Sukthankar, R.: D3D: distilled 3D networks for video action recognition. arXiv preprint arXiv:1812.08249 (2018)"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., Kung, H.T.: Branchynet: fast inference via early exiting from deep neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2464\u20132469 (2016)","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"3_CR30","unstructured":"The 20BN-jester dataset V1: The 20BN-jester Dataset V1. Accessed 8 Nov 2019"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"The 20BN-something-something Dataset V1: The 20BN-something-something Dataset V1. Accessed 8 Nov 2019","DOI":"10.4324\/9780429504747-1"},{"key":"3_CR32","unstructured":"The 20BN-something-something Dataset V2: The 20BN-something-something Dataset V2. Accessed 8 Nov 2019"},{"key":"3_CR33","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":"3_CR34","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"},{"issue":"2","key":"3_CR35","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vision 57(2), 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"3_CR36","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_CR37","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":"3_CR38","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":"3_CR39","unstructured":"Wang, X., Luo, Y., Crankshaw, D., Tumanov, A., Yu, F., Gonzalez, J.E.: IDK cascades: fast deep learning by learning not to overthink. arXiv preprint arXiv:1706.00885 (2017)"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, F., Dou, Z.Y., Darrell, T., Gonzalez, J.E.: Skipnet: learning dynamic routing in convolutional networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 409\u2013424 (2018)","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"3_CR41","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":"3_CR42","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"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xu, C., Hui, L., Lu, C., Tao, D.: Approximated bilinear modules for temporal modeling. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3494\u20133503 (2019)","DOI":"10.1109\/ICCV.2019.00359"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Singh, K., Brox, T.: Eco: efficient convolutional network for online video understanding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 695\u2013712 (2018)","DOI":"10.1007\/978-3-030-01216-8_43"}],"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\/978-3-030-58577-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:02:12Z","timestamp":1727049732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58577-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585761","9783030585778"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58577-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"24 September 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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}