{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T02:23:10Z","timestamp":1794277390512,"version":"4.9.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200618","type":"print"},{"value":"9783031200625","type":"electronic"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20062-5_36","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T05:31:55Z","timestamp":1668058315000},"page":"627-644","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Spatiotemporal Self-attention Modeling with\u00a0Temporal Patch Shift for\u00a0Action Recognition"],"prefix":"10.1007","author":[{"given":"Wangmeng","family":"Xiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian-Sheng","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., Schmid, C.: ViViT: a video vision transformer. In: Computer Vision and Pattern Recognition (2021). arXiv","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"36_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding?. In: Computer Vision and Pattern Recognition (2021). arXiv"},{"key":"36_CR3","unstructured":"Bulat, A., Perez-Rua, J.M., Sudhakaran, S., Martinez, B., Tzimiropoulos, G.: Space-time mixing attention for video transformer. In: NeurIPS (2021)"},{"key":"36_CR4","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, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C.F., Fan, Q., Panda, R.: CrossVit: cross-attention multi-scale vision transformer for image classification. arXiv preprint arXiv:2103.14899 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"36_CR6","unstructured":"Christoph, R., Pinz, F.A.: Spatiotemporal residual networks for video action recognition. In: NIPS, pp. 3468\u20133476 (2016)"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation policies from data (2019). https:\/\/arxiv.org\/pdf\/1805.09501.pdf","DOI":"10.1109\/CVPR.2019.00020"},{"key":"36_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR 2021: The Ninth International Conference on Learning Representations (2021)"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"36_CR10","unstructured":"Fan, Q., Chen, C., Panda, R.: An image classifier can suffice for video understanding. CoRR abs\/2106.14104 (2021). https:\/\/arxiv.org\/abs\/2106.14104"},{"key":"36_CR11","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 33 (2019)"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"36_CR14","doi-asserted-by":"publisher","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.213","DOI":"10.1109\/CVPR.2016.213"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: International Conference on Computer Vision, pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"36_CR16","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. arXiv preprint arXiv:2103.00112 (2021)"},{"key":"36_CR17","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"36_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-030-58517-4_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Kwon","year":"2020","unstructured":"Kwon, H., Kim, M., Kwak, S., Cho, M.: MotionSqueeze: neural motion feature learning for video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 345\u2013362. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_21"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Collaborative spatiotemporal feature learning for video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00806"},{"key":"36_CR20","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 909\u2013918 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"36_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1007\/978-3-030-01231-1_32","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Li","year":"2018","unstructured":"Li, Y., Li, Y., Vasconcelos, N.: RESOUND: towards action recognition without representation bias. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 520\u2013535. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_32"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Computer Vision and Pattern Recognition (2021). arXiv","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"36_CR25","unstructured":"Liu, Z., et al.: Video swin transformer. arXiv preprint arXiv:2106.13230 (2021)"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z.,et al.: TEINet: towards an efficient architecture for video recognition. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"36_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Martinez, B., Modolo, D., Xiong, Y., Tighe, J.: Action recognition with spatial-temporal discriminative filter banks. In: International Conference on Computer Vision, pp. 5482\u20135491 (2019)","DOI":"10.1109\/ICCV.2019.00558"},{"key":"36_CR29","unstructured":"Patrick, M., et al.: Keeping your eye on the ball: trajectory attention in video transformers. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Ryoo, M.S.: Representation flow for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9945\u20139953 (2019)","DOI":"10.1109\/CVPR.2019.01018"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"issue":"3","key":"36_CR32","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/s11263-015-0851-8","volume":"119","author":"M Rohrbach","year":"2016","unstructured":"Rohrbach, M., Rohrbach, A., Regneri, M., Amin, S., Andriluka, M., Pinkal, M., Schiele, B.: Recognizing fine-grained and composite activities using hand-centric features and script data. IJCV 119(3), 346\u2013373 (2016)","journal-title":"IJCV"},{"key":"36_CR33","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014). https:\/\/papers.nips.cc\/paper\/5353-two-stream-convolutional-networks-for-action-recognition-in-videos"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR) (2015). https:\/\/arxiv.org\/abs\/1409.4842","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"36_CR35","unstructured":"Touvron, H., Cord, M., Matthijs, D., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: ICML 2021: 38th International Conference on Machine Learning (2021)"},{"key":"36_CR36","doi-asserted-by":"publisher","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: International Conference on Computer Vision, pp. 4489\u20134497 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.510","DOI":"10.1109\/ICCV.2015.510"},{"key":"36_CR37","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"36_CR38","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":"36_CR39","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"36_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., Smolic, A.: Action-Net: multipath excitation for action recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"36_CR41","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., Zhou, B.: Temporal pyramid network for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 591\u2013600 (2020)","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"36_CR42","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token ViT: training vision transformers from scratch on imagenet. arXiv preprint arXiv:2101.11986 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"36_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., Ngo, C.W.: Token shift transformer for video classification. In: Computer Vision and Pattern Recognition (2021). arXiv","DOI":"10.1145\/3474085.3475272"},{"key":"36_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Lin, D.: Recognize actions by disentangling components of dynamics. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6566\u20136575 (2018)","DOI":"10.1109\/CVPR.2018.00687"},{"key":"36_CR45","first-page":"7970","volume":"29","author":"YD Zheng","year":"2020","unstructured":"Zheng, Y.D., Liu, Z., Lu, T., Wang, L.: Dynamic sampling networks for efficient action recognition in videos. TIP 29, 7970\u20137983 (2020)","journal-title":"TIP"}],"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\/978-3-031-20062-5_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T01:35:45Z","timestamp":1794274545000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-20062-5_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200618","9783031200625"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20062-5_36","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-031-20062-5","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 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":"This content has been made available to all.","name":"free","label":"Free to read"}]}}