{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:05:44Z","timestamp":1782313544734,"version":"3.54.5"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T00:00:00Z","timestamp":1663545600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T00:00:00Z","timestamp":1663545600000},"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":["SIViP"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11760-022-02357-2","type":"journal-article","created":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T10:02:56Z","timestamp":1663581776000},"page":"1485-1492","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Spatiotemporal consistency enhancement self-supervised representation learning for action recognition"],"prefix":"10.1007","volume":"17","author":[{"given":"Shuai","family":"Bi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shufang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,19]]},"reference":[{"key":"2357_CR1","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":"2357_CR2","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher. R.: Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2357_CR3","doi-asserted-by":"crossref","unstructured":"Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 840\u2013849 (2019)","DOI":"10.1109\/CVPR.2019.00093"},{"key":"2357_CR4","doi-asserted-by":"crossref","unstructured":"Li, X., Lin, T., Liu. X.: Deep concept-wise temporal convolutional networks for action localization. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4004\u20134012 (2020)","DOI":"10.1145\/3394171.3413860"},{"key":"2357_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik. J.: SlowFast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2357_CR6","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Proceedings of the European Conference on Computer Vision, pp. 69\u201384 (2016)","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"2357_CR7","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)"},{"key":"2357_CR8","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"2357_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Proceedings of the European Conference on Computer Vision, pp. 649\u2013666 (2016)","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"2357_CR10","doi-asserted-by":"crossref","unstructured":"Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y.: Self-supervised spatiotemporal learning via video clip order prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10334\u201310343 (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"2357_CR11","doi-asserted-by":"crossref","unstructured":"Yao, Y., Liu, C., Luo, D., Zhou, Y., Ye, Q.: Video playback rate perception for self-supervised spatio-temporal representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6548\u20136557 (2020)","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"2357_CR12","doi-asserted-by":"crossref","unstructured":"Jenni, S., Meishvili, G., Favaro, P.: Video representation learning by recognizing temporal transformations. In: Proceedings of the European Conference on Computer Vision, pp. 425\u2013442 (2020)","DOI":"10.1007\/978-3-030-58604-1_26"},{"key":"2357_CR13","doi-asserted-by":"crossref","unstructured":"Misra, I., Maaten, L.: Self-supervised learning of pretext-invariant representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6707\u20136717 (2020)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"2357_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2357_CR15","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning, pp. 1597\u20131607 (2020)"},{"key":"2357_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Hu, P., Liu, Z., Peng, D., Zhou, J., Peng, X.: Contrastive clustering. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8547\u20138555 (2021)","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"2357_CR17","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of the Advanced in Neural Information Processing System, vol. 27 (2014)"},{"key":"2357_CR18","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Gool, L.: Temporal segment networks: towards good practices for deep action recognition. In: Proceedings of the European Conference on Computer Vision, pp. 20\u201336 (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"2357_CR19","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":"2357_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2357_CR21","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"},{"key":"2357_CR22","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3636\u20133645 (2017)","DOI":"10.1109\/CVPR.2017.607"},{"key":"2357_CR23","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1735\u20131742 (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"2357_CR24","unstructured":"Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"2357_CR25","unstructured":"Hjelm, R., Fedorov, A., Samuel, L.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"2357_CR26","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Proceedings of the European Conference on Computer Vision, pp. 776\u2013794 (2020)","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"2357_CR27","doi-asserted-by":"crossref","unstructured":"Tao, L., Wang, X., Yamasaki, T.: Self-supervised video representation learning using inter\u2013intra contrastive framework. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2193\u20132201 (2020)","DOI":"10.1145\/3394171.3413694"},{"key":"2357_CR28","doi-asserted-by":"crossref","unstructured":"Lee, H., Huang, J., Singh, M., Yang, M.: Unsupervised representation learning by sorting sequences. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 667\u2013676 (2017)","DOI":"10.1109\/ICCV.2017.79"},{"key":"2357_CR29","doi-asserted-by":"crossref","unstructured":"Buchler, U., Brattoli, B., Ommer, B.: Improving spatiotemporal self-supervision by deep reinforcement learning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 770\u2013786 (2018)","DOI":"10.1007\/978-3-030-01267-0_47"},{"key":"2357_CR30","doi-asserted-by":"crossref","unstructured":"Kim, D., Cho, D., Kweon, I.: Self-supervised video representation learning with space-time cubic puzzles. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8545\u20138552 (2019)","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"2357_CR31","doi-asserted-by":"crossref","unstructured":"Luo, D., Liu, Y., Yang, D., Ma, C., Ye, Q.: Video cloze procedure for self-supervised spatio-temporal learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11701\u201311708 (2020)","DOI":"10.1609\/aaai.v34i07.6840"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02357-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-022-02357-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-022-02357-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T03:33:24Z","timestamp":1728012804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-022-02357-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,19]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["2357"],"URL":"https:\/\/doi.org\/10.1007\/s11760-022-02357-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,19]]},"assertion":[{"value":"13 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declared that they have no conflict of interest to this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All the experimental subjects in this study do not include any animals or people and do not violate ethics.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All the authors agreed to publish the article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}