{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:52:50Z","timestamp":1758127970151,"version":"3.40.3"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031198052"},{"type":"electronic","value":"9783031198069"}],"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\/978-3-031-19806-9_39","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T23:11:54Z","timestamp":1666221114000},"page":"675-691","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["In Defense of Image Pre-Training for Spatiotemporal Recognition"],"prefix":"10.1007","author":[{"given":"Xianhang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jieru","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cihang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"39_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: ICCV, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"39_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding. In: ICML , vol. 2, no. 3, p. 4 (2021)"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: non-local networks meet squeeze-excitation networks and beyond. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Rohrbach, M., Yan, Z., Shuicheng, Y., Feng, J., Kalantidis, Y.: Graph-based global reasoning networks. In: CVPR, pp. 433\u2013442 (2019)","DOI":"10.1109\/CVPR.2019.00052"},{"key":"39_CR6","unstructured":"Christoph, R., Pinz, F.A.: Spatiotemporal residual networks for video action recognition. In: NeurIPS, pp. 3468\u20133476 (2016)"},{"key":"39_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: CVPRW, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"39_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: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"39_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$16 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: Expanding architectures for efficient video recognition. In: CVPR, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The something something video database for learning and evaluating visual common sense. In: ICCV, pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Girshick, R., Doll\u00e1r, P.: Rethinking imagenet pre-training. In: ICCV, pp. 4918\u20134927 (2019)","DOI":"10.1109\/ICCV.2019.00502"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"39_CR17","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":"39_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: Stm: Spatiotemporal and motion encoding for action recognition. In: ICCV, pp. 2000\u20132009 (2019)","DOI":"10.1109\/ICCV.2019.00209"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Kondratyuk, D., et al.: Movinets: mobile video networks for efficient video recognition. In: CVPR, pp. 16020\u201316030 (2021)","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"39_CR20","unstructured":"Li, K., Li, X., Wang, Y., Wang, J., Qiao, Y.: CT-net: channel tensorization network for video classification. In: ICLR (2021)"},{"key":"39_CR21","unstructured":"Li, K., et al.: Uniformer: unified transformer for efficient spatiotemporal representation learning. In: ICLR (2022)"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, Y., Zhou, Z., Qiao, Y.: Smallbignet: integrating core and contextual views for video classification. In: CVPR, pp. 1092\u20131101 (2020)","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: Tea: temporal excitation and aggregation for action recognition. In: CVPR, pp. 909\u2013918 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: temporal shift module for efficient video understanding. In: ICCV, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video swin transformer. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Teinet: towards an efficient architecture for video recognition. In: AAAI, vol. 34, no. 07, pp. 11669\u201311676 (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: ICCV, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"39_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"39_CR31","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurIPS (2014)"},{"key":"39_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Escalera, S., Lanz, O.: Gate-shift networks for video action recognition. In: CVPR, pp. 1102\u20131111 (2020)","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: ICCV, pp. 843\u2013852 (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"39_CR35","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"39_CR36","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML, pp. 10347\u201310357 (2021)"},{"key":"39_CR37","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"39_CR38","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: ICCV, pp. 5552\u20135561 (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"39_CR39","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: CVPR, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Wang, H., Tran, D., Torresani, L., Feiszli, M.: Video modeling with correlation networks. In: CVPR, pp. 352\u2013361 (2020)","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"39_CR41","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: Tdn: Temporal difference networks for efficient action recognition. In: CVPR, pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"39_CR42","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., Xiong, Y., Wang, Z., Qiao, Yu., Lin, D., Tang, X., Van Gool, L.: 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":"39_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"39_CR44","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":"39_CR45","unstructured":"Wightman, R., Touvron, H., J\u00e9gou, H.: Resnet strikes back: an improved training procedure in timm. arXiv (2021)"},{"key":"39_CR46","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Girshick, R., He, K., Feichtenhofer, C., Krahenbuhl, P.: A multigrid method for efficiently training video models. In: CVPR, pp. 153\u2013162 (2020)","DOI":"10.1109\/CVPR42600.2020.00023"},{"key":"39_CR47","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":"39_CR48","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., Zhou, B.: Temporal pyramid network for action recognition. In: CVPR, pp. 591\u2013600 (2020)","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"39_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-58555-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Yin","year":"2020","unstructured":"Yin, M., Yao, Z., Cao, Y., Li, X., Zhang, Z., Lin, S., Hu, H.: Disentangled non-local neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 191\u2013207. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_12"},{"key":"39_CR50","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: ICCV, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"39_CR51","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: ICLR (2018)"},{"key":"39_CR52","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 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19806-9_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T23:17:08Z","timestamp":1666394228000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19806-9_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198052","9783031198069"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19806-9_39","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":"20 October 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)"}}]}}