{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:17:26Z","timestamp":1740107846547,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,3,18]],"date-time":"2022-03-18T00:00:00Z","timestamp":1647561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,18]],"date-time":"2022-03-18T00:00:00Z","timestamp":1647561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672268"],"award-info":[{"award-number":["61672268"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s00530-022-00912-y","type":"journal-article","created":{"date-parts":[[2022,3,18]],"date-time":"2022-03-18T04:40:32Z","timestamp":1647578432000},"page":"1529-1541","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Spatial\u2013temporal correlations learning and action-background jointed attention for weakly-supervised temporal action localization"],"prefix":"10.1007","volume":"28","author":[{"given":"Huifen","family":"Xia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongzhao","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keyang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,18]]},"reference":[{"key":"912_CR1","unstructured":"Fabian, C.H., Victor, E., Bernard, G., Juan, C.N.: Activitynet: A large-scale video benchmark for human activity understanding. In Proceedings of the ieee conference on computer vision and pattern recognition, pp 961\u2013970 (2015)"},{"key":"912_CR2","unstructured":"Joao, C., Andrew, Z.: Quo vadis, action recognition? a new model and the kinetics dataset. In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6299\u20136308 (2017)"},{"key":"912_CR3","unstructured":"Yu-Wei, C., Sudheendra, V., Bryan, S., Ross, D.A., Jia, D., Rahul, S.: Rethinking the faster r-cnn architecture for temporal action localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1130\u20131139 (2018)"},{"key":"912_CR4","unstructured":"Christoph, F., Haoqi, F., Jitendra, M., Kaiming, H.: Slowfast networks for video recognition. In Proceedings of the IEEE\/CVF international conference on computer vision, pp 6202\u20136211 (2019)"},{"key":"912_CR5","doi-asserted-by":"publisher","first-page":"107686","DOI":"10.1016\/j.patcog.2020.107686","volume":"110","author":"Y Ge","year":"2021","unstructured":"Ge, Y., Qin, X., Yang, D., Jagersand, M.: Deep snippet selective network for weakly supervised temporal action localization. Pattern Recogn. 110, 107686 (2021)","journal-title":"Pattern Recogn."},{"issue":"1","key":"912_CR6","first-page":"48","volume":"58","author":"Z Hang","year":"2021","unstructured":"Hang, Z., Yongzhao, Z., Qirong, M.: Video anomaly detection based on space\u2013time fusion graph network learning. J. Comput. Res. Dev. 58(1), 48 (2021)","journal-title":"J. Comput. Res. Dev."},{"key":"912_CR7","first-page":"11053","volume":"34","author":"L Huang","year":"2020","unstructured":"Huang, L., Huang, Y., Ouyang, W., Wang, L.: Relational prototypical network for weakly supervised temporal action localization. Proc. AAAI Conf. Artif. Intell. 34, 11053\u201311060 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"912_CR8","unstructured":"Jiang, Y.-G.., Liu, J.: A Roshan Zamir, George Toderici, Ivan Laptev, Mubarak Shah, and Rahul Sukthankar. Action recognition with a large number of classes, Thumos challenge (2014)"},{"key":"912_CR9","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016"},{"key":"912_CR10","doi-asserted-by":"crossref","unstructured":"Pilhyeon, L., Youngjung, U., Hyeran, B.: Background suppression network for weakly-supervised temporal action localization. In AAAI, pages 11320\u201311327, 2020","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"912_CR11","unstructured":"Tianwei, L., Xu, Z., Zheng, S.: Single shot temporal action detection. In Proceedings of the 25th ACM international conference on Multimedia, pages 988\u2013996 (2017)"},{"key":"912_CR12","unstructured":"Daochang, L., Tingting, J. Yizhou, W.: Completeness modeling and context separation for weakly supervised temporal action localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1298\u20131307, 2019"},{"key":"912_CR13","unstructured":"Fuchen, L., Ting, Y., Zhaofan, Q., Xinmei, T., Jiebo, L. Tao, M.: Gaussian temporal awareness networks for action localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 344\u2013353 (2019)"},{"issue":"5","key":"912_CR14","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1109\/TMM.2005.854410","volume":"7","author":"Y-F Ma","year":"2005","unstructured":"Ma, Y.-F., Hua, X.-S., Lie, L., Zhang, H.-J.: A generic framework of user attention model and its application in video summarization. IEEE Trans. Multimedia 7(5), 907\u2013919 (2005)","journal-title":"IEEE Trans. Multimedia"},{"key":"912_CR15","unstructured":"Phuc, N., Ting, L., Gautam, P., Bohyung, H.: Weakly supervised action localization by sparse temporal pooling network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6752\u20136761 (2018)"},{"key":"912_CR16","unstructured":"Phuc, X.N., Deva, R., Fowlkes, C.C.: Weakly-supervised action localization with background modeling. In Proceedings of the IEEE International Conference on Computer Vision, pages 5502\u20135511 (2019)"},{"key":"912_CR17","unstructured":"Sujoy ,P., Sourya, R., Roy-Chowdhury, A.K.: W-talc: Weakly-supervised temporal activity localization and classification. In Proceedings of the European Conference on Computer Vision (ECCV), pp 563\u2013579 (2018)"},{"key":"912_CR18","unstructured":"Maheen, R., Hedvig, K., Lee, Y.J. Action graphs: Weakly-supervised action localization with graph convolution networks. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 615\u2013624 (2020)"},{"key":"912_CR19","unstructured":"Baifeng, S., Qi, D., Yadong, M., Jingdong, W.: Weakly-supervised action localization by generative attention modeling. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1009\u20131019 (2020)"},{"key":"912_CR20","unstructured":"Lei, S., Yifan, Z., Jian, C., Hanqing, L.: Skeleton-based action recognition with directed graph neural networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 7912\u20137921 (2019)"},{"key":"912_CR21","unstructured":"Zheng, S., Hang, G., Lei, Z., Kazuyuki, M., Shih-Fu, C.: Weakly-supervised temporal action localization in untrimmed videos. In Proceedings of the European Conference on Computer Vision (ECCV), pages 154\u2013171 (2018)"},{"key":"912_CR22","unstructured":"Zheng, S., Dongang, W., Shih-Fu, C.: Temporal action localization in untrimmed videos via multi-stage cnns. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1049\u20131058 (2016)"},{"key":"912_CR23","unstructured":"Waqas, S., Chen, C., Mubarak, S.: Real-world anomaly detection in surveillance videos. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6479\u20136488 (2018)"},{"key":"912_CR24","unstructured":"Du, T., Lubomir, B., Rob, F., Lorenzo, T., Manohar, P.: Learning spatiotemporal features with 3d convolutional networks. In Proceedings of the IEEE international conference on computer vision, pages 4489\u20134497 (2015)"},{"key":"912_CR25","unstructured":"Heng, W., Cordelia, S.: Action recognition with improved trajectories. In Proceedings of the IEEE international conference on computer vision, pages 3551\u20133558 (2013)"},{"key":"912_CR26","unstructured":"Limin, W., Yuanjun, X., Dahua, L., Luc, V.G.: Untrimmednets for weakly supervised action recognition and detection. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 4325\u20134334 (2017)"},{"key":"912_CR27","doi-asserted-by":"crossref","unstructured":"Limin, W., Yuanjun, X., Zhe, W., Yu, Q., Dahua, L., Xiaoou, T., Luc, V.G.: Temporal segment networks: Towards good practices for deep action recognition. In European conference on computer vision, pages 20\u201336. Springer, 2016","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"912_CR28","doi-asserted-by":"crossref","unstructured":"Andreas, W., Thomas, P., Christopher, Z., Horst, B., Daniel, C.: An improved algorithm for tv-l 1 optical flow. In Statistical and geometrical approaches to visual motion analysis, pages 23\u201345. Springer (2009)","DOI":"10.1007\/978-3-642-03061-1_2"},{"key":"912_CR29","unstructured":"Mengmeng, X., Chen, Z. David, S.R., Ali, T., Bernard, G.: G-tad: Sub-graph localization for temporal action detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 10156\u201310165, 2020"},{"issue":"12","key":"912_CR30","doi-asserted-by":"publisher","first-page":"5797","DOI":"10.1109\/TIP.2019.2922108","volume":"28","author":"R Zeng","year":"2019","unstructured":"Zeng, R., Gan, C., Chen, P., Huang, W., Qingyao, W., Tan, M.: Breaking winner-takes-all: Iterative-winners-out networks for weakly supervised temporal action localization. IEEE Trans. Image Process. 28(12), 5797\u20135808 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"912_CR31","unstructured":"Runhao, Z., Wenbing, H., Mingkui, T., Yu, R., Peilin, Z., Junzhou, H., Chuang, G.: Graph convolutional networks for temporal action localization. In Proceedings of the IEEE International Conference on Computer Vision, pages 7094\u20137103 (2019)"},{"key":"912_CR32","doi-asserted-by":"crossref","unstructured":"Yuanhao, Z., Le, W., Wei, T., Qilin, Z., Junsong, Y., Gang, H.: Two-stream consensus network for weakly-supervised temporal action localization. In European conference on computer vision, pages 37\u201354. Springer (2020)","DOI":"10.1007\/978-3-030-58539-6_3"},{"key":"912_CR33","doi-asserted-by":"crossref","unstructured":"Peisen, Z., Lingxi, X., Chen, J., Ya, Z., Yanfeng, W., Qi, T.: Bottom-up temporal action localization with mutual regularization. In European Conference on Computer Vision, pages 539\u2013555. Springer (2020)","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"912_CR34","unstructured":"Yue, Z., Yuanjun, X., Limin, W., Zhirong, W., Xiaoou, T., Dahua, L.: Temporal action detection with structured segment networks. In Proceedings of the IEEE International Conference on Computer Vision, pages 2914\u20132923 (2017)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00912-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-022-00912-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00912-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T21:28:01Z","timestamp":1659043681000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-022-00912-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,18]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["912"],"URL":"https:\/\/doi.org\/10.1007\/s00530-022-00912-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2022,3,18]]},"assertion":[{"value":"2 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}