{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T12:31:35Z","timestamp":1762432295429,"version":"3.40.3"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031198328"},{"type":"electronic","value":"9783031198335"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19833-5_10","type":"book-chapter","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:40:30Z","timestamp":1667522430000},"page":"160-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["K-centered Patch Sampling for\u00a0Efficient Video Recognition"],"prefix":"10.1007","author":[{"given":"Seong Hyeon","family":"Park","sequence":"first","affiliation":[]},{"given":"Jihoon","family":"Tack","sequence":"additional","affiliation":[]},{"given":"Byeongho","family":"Heo","sequence":"additional","affiliation":[]},{"given":"Jung-Woo","family":"Ha","sequence":"additional","affiliation":[]},{"given":"Jinwoo","family":"Shin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: VIVIT: a video vision transformer. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"10_CR2","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems (2020)"},{"key":"10_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning (2021)"},{"key":"10_CR4","unstructured":"Bulat, A., Perez-Rua, J.M., Sudhakaran, S., Martinez, B., Tzimiropoulos, G.: Space-time mixing attention for video transformer. In: Advances in Neural Information Processing Systems (2021)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"10_CR6","unstructured":"Chen, B., et al.: PSViT: better vision transformer via token pooling and attention sharing. arXiv preprint arXiv:2108.03428 (2021)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: Advances in Neural Information Processing Systems (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Annual Conference of the North American Chapter of the Association for Computational Linguistics (2019)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"10_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal residual networks for video action recognition. In: Advances in Neural Information Processing Systems (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"10_CR16","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/0304-3975(85)90224-5","volume":"38","author":"TF Gonzalez","year":"1985","unstructured":"Gonzalez, T.F.: Clustering to minimize the maximum intercluster distance. Theoret. Comput. Sci. 38, 293\u2013306 (1985)","journal-title":"Theoret. Comput. Sci."},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Rohrbach, M., Sevilla-Lara, L.: Smart frame selection for action recognition. In: AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Har-Peled, S.: Geometric approximation algorithms. No. 173, American Mathematical Soc. (2011)","DOI":"10.1090\/surv\/173"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"10_CR21","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: IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"10_CR22","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017)"},{"key":"10_CR23","unstructured":"Li, K., et al.: Uniformer: unified transformer for efficient spatiotemporal representation learning. arXiv preprint arXiv:2201.04676 (2022)"},{"key":"10_CR24","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: expediting vision transformers via token reorganizations. In: International Conference on Learning Representations (2022)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10_CR26","unstructured":"Liu, Z., et al.: Video swin transformer. arXiv preprint arXiv:2106.13230 (2021)"},{"key":"10_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"10_CR28","unstructured":"Marin, D., Chang, J.H.R., Ranjan, A., Prabhu, A., Rastegari, M., Tuzel, O.: Token pooling in vision transformers. arXiv preprint arXiv:2110.03860 (2021)"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: AdaViT: adaptive vision transformers for efficient image recognition. arXiv preprint arXiv:2111.15668 (2021)","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Meng, Y., et al.: AR-Net: adaptive frame resolution for efficient action recognition. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"10_CR31","unstructured":"Meng, Y., et al.: AdaFuse: adaptive temporal fusion network for efficient action recognition. In: International Conference on Learning Representations (2021)"},{"key":"10_CR32","unstructured":"Micikevicius, P., et al.: Mixed precision training. In: International Conference on Learning Representations (2018)"},{"key":"10_CR33","unstructured":"Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Intriguing properties of vision transformers. In: Advances in Neural Information Processing Systems (2021)"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. arXiv preprint arXiv:2102.00719 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"10_CR35","unstructured":"Patrick, M., et al.: Keeping your eye on the ball: trajectory attention in video transformers. In: Advances in Neural Information Processing Systems (2021)"},{"key":"10_CR36","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (2017)"},{"key":"10_CR37","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"10_CR38","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: Advances in Neural Information Processing Systems (2021)"},{"key":"10_CR39","unstructured":"Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green AI. arXiv preprint arXiv:1907.10597 (2019)"},{"key":"10_CR40","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems (2014)"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Sun, X., Panda, R., Chen, C.F., Oliva, A., Feris, R., Saenko, K.: Dynamic network quantization for efficient video inference. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00728"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"10_CR43","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning (2021)"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"10_CR45","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Removing the background by adding the background: Towards background robust self-supervised video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11804\u201311813 (2021)","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, X., Li, H., Wu, Z., Jiang, Y.G.: Efficient video transformers with spatial-temporal token selection. arXiv preprint arXiv:2111.11591 (2021)","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, C., Ma, C.Y., Socher, R., Davis, L.S.: AdaFrame: adaptive frame selection for fast video recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00137"},{"key":"10_CR49","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":"10_CR50","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: VideoGPT: video generation using VQ-VAE and transformers. arXiv preprint arXiv:2104.10157 (2021)"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.293"},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Zhi, Y., Tong, Z., Wang, L., Wu, G.: MGSampler: an explainable sampling strategy for video action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1513\u20131522 (2021)","DOI":"10.1109\/ICCV48922.2021.00154"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19833-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T15:32:15Z","timestamp":1673278335000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19833-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198328","9783031198335"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19833-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}