{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:31:04Z","timestamp":1783823464452,"version":"3.55.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585167","type":"print"},{"value":"9783030585174","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.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\/978-3-030-58517-4_21","type":"book-chapter","created":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T19:03:11Z","timestamp":1602270191000},"page":"345-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":102,"title":["MotionSqueeze: Neural Motion Feature Learning for Video Understanding"],"prefix":"10.1007","author":[{"given":"Heeseung","family":"Kwon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manjin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suha","family":"Kwak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsu","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,10]]},"reference":[{"issue":"1","key":"21_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-010-0390-2","volume":"92","author":"S Baker","year":"2011","unstructured":"Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vision (IJCV) 92(1), 1\u201331 (2011)","journal-title":"Int. J. Comput. Vision (IJCV)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Kalantidis, Y., Li, J., Yan, S., Feng, J.: Multi-fiber networks for video recognition. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00630"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.: Spatiotemporal residual networks for video action recognition. In: Proceedings of Neural Information Processing Systems (NeurIPS) (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \"something something\" video database for learning and evaluating visual common sense. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Han, K., et al.: Scnet: learning semantic correspondence. In: Proceeding of IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.203"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Honari, S., Molchanov, P., Tyree, S., Vincent, P., Pal, C., Kautz, J.: Improving landmark localization with semi-supervised learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00167"},{"key":"21_CR14","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint arXiv:1704.04861"},{"key":"21_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv preprint arXiv:1502.03167"},{"key":"21_CR16","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 IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00209"},{"key":"21_CR17","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017). arXiv preprint arXiv:1705.06950"},{"key":"21_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 IEEE International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., Ponce, J., Ham, B.: SFNET: learning object-aware semantic correspondence. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00238"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Lee, M., Lee, S., Son, S., Park, G., Kwak, N.: Motion feature network: fixed motion filter for action recognition. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01249-6_24"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: temporal shift module for efficient video understanding. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Liu, X., Lee, J.Y., Jin, H.: Learning video representations from correspondence proposals. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00440"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Martinez, B., Modolo, D., Xiong, Y., Tighe, J.: Action recognition with spatial-temporal discriminative filter banks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00558"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: Hyperpixel flow: semantic correspondence with multi-layer neural features. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00349"},{"key":"21_CR25","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of International Conference on Machine Learning (ICML) (2010)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Ng, J.Y.H., Choi, J., Neumann, J., Davis, L.S.: Actionflownet: learning motion representation for action recognition. In: Proceedings of Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00179"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Ryoo, M.S.: Representation flow for action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01018"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.12"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Sevilla-Lara, L., Liao, Y., G\u00fcney, F., Jampani, V., Geiger, A., Black, M.J.: On the integration of optical flow and action recognition. In: Proceedings of German Conference on Pattern Recognition (GCPR) (2018)","DOI":"10.1007\/978-3-030-12939-2_20"},{"key":"21_CR31","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of Neural Information Processing Systems (NeurIPS) (2014)"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Stroud, J., Ross, D., Sun, C., Deng, J., Sukthankar, R.: D3D: distilled 3D networks for video action recognition. In: Proceedings of Winter Conference on Applications of Computer Vision (WACV) (2020)","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: CNNs for optical flow using pyramid, warping, and cost volume. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.: Optical flow guided feature: a fast and robust motion representation for video action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00151"},{"key":"21_CR35","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 IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"21_CR37","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 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Cheng-Lin, L.: Action recognition by dense trajectories. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Proceedings of European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 399\u2013417 (2018)","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"21_CR43","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 European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"21_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-540-74936-3_22","volume-title":"Pattern Recognition","author":"C Zach","year":"2007","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime tv-l 1 optical flow. In: Hamprecht, Fred A., Schn\u00f6rr, Christoph, J\u00e4hne, Bernd (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214\u2013223. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74936-3_22"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Lin, D.: Recognize actions by disentangling components of dynamics. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00687"},{"key":"21_CR46","unstructured":"Zhao, Y., Xiong, Y., Lin, D.: Trajectory convolution for action recognition. In: Proceedings of Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Singh, K., Brox, T.: Eco: efficient convolutional network for online video understanding. In: Proceedings of European Conference on Computer Vision (ECCV) (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\/978-3-030-58517-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:12:33Z","timestamp":1728432753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58517-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585167","9783030585174"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58517-4_21","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":"10 October 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. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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"}]}}