{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:15:16Z","timestamp":1740147316871,"version":"3.37.3"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T00:00:00Z","timestamp":1633910400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T00:00:00Z","timestamp":1633910400000},"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":["61771420","62001413"],"award-info":[{"award-number":["61771420","62001413"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F2020203064"],"award-info":[{"award-number":["F2020203064"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Doctoral Foundation of Yanshan University","award":["BL18033"],"award-info":[{"award-number":["BL18033"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s11760-021-02039-5","type":"journal-article","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T09:21:36Z","timestamp":1633944096000},"page":"947-954","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Two-stream graph convolutional neural network fusion for weakly supervised temporal action detection"],"prefix":"10.1007","volume":"16","author":[{"given":"Mengyao","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0300-6144","authenticated-orcid":false,"given":"Zhengping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shufang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,11]]},"reference":[{"key":"2039_CR1","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1007\/s11760-013-0493-7","volume":"9","author":"JL Chua","year":"2015","unstructured":"Chua, J.L., Chang, Y.C., Lim, W.K.: A simple vision-based fall detection technique for indoor video surveillance. SIViP 9, 623\u2013633 (2015)","journal-title":"SIViP"},{"key":"2039_CR2","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1346\u20131353 (2012)","DOI":"10.1109\/CVPR.2012.6247820"},{"key":"2039_CR3","doi-asserted-by":"crossref","unstructured":"Xiong, B., Kalantidis, Y., Ghadiyaram, D., et al.: Less is more: learning highlight detection from video duration. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1258\u20131267 (2019)","DOI":"10.1109\/CVPR.2019.00135"},{"issue":"1","key":"2039_CR4","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s11263-019-01211-2","volume":"128","author":"Y Zhao","year":"2020","unstructured":"Zhao, Y., Xiong, Y., Wang, L., et al.: Temporal action detection with structured segment networks. Int. J. Comput. Vis. 128(1), 74\u201395 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"2039_CR5","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., et al.: UntrimmedNets for weakly supervised action recognition and detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6402\u20136411 (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"2039_CR6","doi-asserted-by":"crossref","unstructured":"Lee, P., Uh, Y., Byun, H.: Background suppression network for weakly-supervised temporal action localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11320\u201311327 (2020)","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"2039_CR7","doi-asserted-by":"crossref","unstructured":"Islam, A., Radke, R.J.: Weakly supervised temporal action localization using deep metric learning. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 536\u2013545 (2020)","DOI":"10.1109\/WACV45572.2020.9093620"},{"key":"2039_CR8","doi-asserted-by":"crossref","unstructured":"Islam, A., Long, C., Radke, R.J.: A hybrid attention mechanism for weakly-supervised temporal action localization. arXiv preprint, arXiv: 2101.00545 (2021)","DOI":"10.1109\/WACV45572.2020.9093620"},{"key":"2039_CR9","doi-asserted-by":"crossref","unstructured":"Rashid, M., Kjellstrom, H., Lee, Y.J.: Action graphs: weakly-supervised action localization with graph convolution networks. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 604\u2013613 (2020)","DOI":"10.1109\/WACV45572.2020.9093404"},{"key":"2039_CR10","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., et al.: Weakly supervised action localization by sparse temporal pooling network. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6752\u20136761 (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"2039_CR11","doi-asserted-by":"crossref","unstructured":"Liu, D., Jiang, T., Wang, Y.: Completeness modeling and context separation for weakly supervised temporal action localization. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1298\u20131307 (2019)","DOI":"10.1109\/CVPR.2019.00139"},{"key":"2039_CR12","doi-asserted-by":"crossref","unstructured":"Nguyen, P.X., Ramanan, D., Fowlkes, C.C.: Weakly-supervised action localization with background modeling. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5501\u20135510 (2019)","DOI":"10.1109\/ICCV.2019.00560"},{"key":"2039_CR13","doi-asserted-by":"crossref","unstructured":"Shi, B., Dai, Q., Mu, Y., et al.: Weakly-supervised action localization by generative attention modeling. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1006\u20131016 (2020)","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"2039_CR14","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Wang, L., Tang, W., et al.: Two-stream consensus network for weakly-supervised temporal action localization. In: European Conference on Computer Vision, pp. 37\u201354 (2020)","DOI":"10.1007\/978-3-030-58539-6_3"},{"key":"2039_CR15","doi-asserted-by":"crossref","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: European Conference on Computer Vision, pp. 588\u2013607 (2018)","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"2039_CR16","doi-asserted-by":"crossref","unstructured":"Fernando, B., Yin Chet, C.T., Bilen, H.: Weakly supervised Gaussian networks for action detection. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 526\u2013535 (2020)","DOI":"10.1109\/WACV45572.2020.9093263"},{"key":"2039_CR17","doi-asserted-by":"crossref","unstructured":"Huang, L., Huang, Y., Ouyang, W., et al.: Relational prototypical network for weakly supervised temporal action localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11053\u201311060 (2020)","DOI":"10.1609\/aaai.v34i07.6760"},{"key":"2039_CR18","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A., Vadis, Q.: Action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"2039_CR19","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"2039_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., et al.: BSN: boundary sensitive network for temporal action proposal generation. In: European Conference on Computer Vision, Munich, Germany, pp. 3\u201321 (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"2039_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","volume":"155","author":"H Idrees","year":"2017","unstructured":"Idrees, H., Zamir, A.R., Jiang, Y., et al.: The THUMOS challenge on action recognition for videos \u201cin the wild.\u201d Comput. Vis. Image Underst. 155, 1\u201323 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"2039_CR22","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., et al.: Activitynet: a large-scale video benchmark for human activity understanding. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"2039_CR23","unstructured":"Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. arXiv preprint, arXiv: 1412.6980 (2014)"},{"key":"2039_CR24","doi-asserted-by":"crossref","unstructured":"Shou, Z., Gao, H., Zhang, L., et al.: AutoLoc: weakly-supervised temporal action localization in untrimmed videos. In: European Conference on Computer Vision, pp. 162\u2013179 (2018)","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"2039_CR25","unstructured":"Yuan, Y., Lyu, Y., Shen, X., et al.: Marginalized average attentional network for weakly supervised learning. arXiv preprint, arXiv: 1905.08586 (2019)"},{"key":"2039_CR26","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., et al.: Deep snippet selective network for weakly supervised temporal action localization. Pattern Recognit. 110, 107686 (2021)","journal-title":"Pattern Recognit."},{"key":"2039_CR27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2962815","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Li, C., Shi, H., et al.: AdapNet: adaptability decomposing encoder-decoder network for weakly supervised action recognition and localization. IEEE Trans. Neural Netw. Learn. Syst. (2020). https:\/\/doi.org\/10.1109\/TNNLS.2019.2962815","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2039_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, C., Cheng, Z., et al.: Segregated temporal assembly recurrent networks for weakly supervised multiple action detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 9070\u20139078 (2019)","DOI":"10.1609\/aaai.v33i01.33019070"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-02039-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-021-02039-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-02039-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T19:48:18Z","timestamp":1725911298000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-021-02039-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,11]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["2039"],"URL":"https:\/\/doi.org\/10.1007\/s11760-021-02039-5","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2021,10,11]]},"assertion":[{"value":"8 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}