{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T20:24:24Z","timestamp":1771705464011,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,12,22]],"date-time":"2021-12-22T00:00:00Z","timestamp":1640131200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"GFJG-1 Optimization Research of ***","award":["NO.76150-41020054"],"award-info":[{"award-number":["NO.76150-41020054"]}]},{"name":"Major research and development plan of China State Railway Group Co., Ltd","award":["NO.K2020G024"],"award-info":[{"award-number":["NO.K2020G024"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,12,22]]},"DOI":"10.1145\/3511176.3511204","type":"proceedings-article","created":{"date-parts":[[2022,3,12]],"date-time":"2022-03-12T23:18:23Z","timestamp":1647127103000},"page":"184-190","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["GCRNet: Global Context Relation Network for Weakly-Supervised Temporal Action Localization"],"prefix":"10.1145","author":[{"given":"Yiguan","family":"Liao","sequence":"first","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-Sen University, China"}]},{"given":"Changzhen","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-Sen University, China"}]},{"given":"Zhiyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-Sen University, China"}]},{"given":"Luping","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-Sen University, China"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-Sen University, China"}]}],"member":"320","published-online":{"date-parts":[[2022,3,12]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"11327","volume-title":"``Background suppression network for weakly-supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence","author":"Lee P.","year":"2020","unstructured":"P. Lee , Y. Uh , and H. Byun , ``Background suppression network for weakly-supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence , 2020 , pp. 11320\u2013 11327 . doi: https:\/\/doi.org\/10.1609\/aaai.v34i07.6793 10.1609\/aaai.v34i07.6793 P. Lee, Y. Uh, and H. Byun, ``Background suppression network for weakly-supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence, 2020, pp. 11320\u201311327. doi: https:\/\/doi.org\/10.1609\/aaai.v34i07.6793"},{"key":"e_1_3_2_1_2_1","author":"Qu S.","year":"2021","unstructured":"S. Qu , G. Chen , Z. Li , L. Zhang , F. Lu , and A. Knoll , ``Acm-net: Action context modeling network for weakly-supervised temporal action localization[J],'' IEEE Transactions on Image Processing , 2021 . S. Qu, G. Chen, Z. Li, L. Zhang, F. Lu, and A. Knoll, ``Acm-net: Action context modeling network for weakly-supervised temporal action localization[J],'' IEEE Transactions on Image Processing, 2021.","journal-title":"``Acm-net: Action context modeling network for weakly-supervised temporal action localization[J],'' IEEE Transactions on Image Processing"},{"key":"e_1_3_2_1_3_1","first-page":"54","volume-title":"``Two-stream consensus network for weakly-supervised temporal action localization[C],'' in European Conference on Computer Vision","author":"Zhai Y.","year":"2020","unstructured":"Y. Zhai , L. Wang , W. Tang , Q. Zhang , and G. Hua , ``Two-stream consensus network for weakly-supervised temporal action localization[C],'' in European Conference on Computer Vision , 2020 , pp. 37\u2013 54 . doi: https:\/\/doi.org\/10.1007\/978-3-030-58539-6_3. 10.1007\/978-3-030-58539-6_3 Y. Zhai, L. Wang, W. Tang, Q. Zhang, and G. Hua, ``Two-stream consensus network for weakly-supervised temporal action localization[C],'' in European Conference on Computer Vision, 2020, pp. 37\u201354. doi: https:\/\/doi.org\/10.1007\/978-3-030-58539-6_3."},{"key":"e_1_3_2_1_4_1","volume-title":"`A hybrid attention mechanism for weakly-supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence","author":"Islam A.","year":"2021","unstructured":"A. Islam , C. Long , and R.\u223c J. Radke , ` `A hybrid attention mechanism for weakly-supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence . 2021 . A. Islam, C. Long, and R.\u223cJ. Radke, ``A hybrid attention mechanism for weakly-supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence. 2021."},{"key":"e_1_3_2_1_5_1","first-page":"1130","volume-title":"``Rethinking the faster r-cnn architecture for temporal action localization[C],'' in Conference on Computer Vision and Pattern Recognition","author":"Chao Y. W.","year":"2018","unstructured":"Y. W. Chao , S. Vijayanarasimhan , B. Seybold , D.\u223c A. Ross , J. Deng , and R. Sukthankar , ``Rethinking the faster r-cnn architecture for temporal action localization[C],'' in Conference on Computer Vision and Pattern Recognition , 2018 , pp. 1130 - 1139 . doi: https:\/\/doi.org\/10.1109\/cvpr.2018.00124. 10.1109\/cvpr.2018.00124 Y. W. Chao, S. Vijayanarasimhan, B. Seybold, D.\u223cA. Ross, J. Deng, and R. Sukthankar, ``Rethinking the faster r-cnn architecture for temporal action localization[C],'' in Conference on Computer Vision and Pattern Recognition, 2018, pp. 1130-1139. doi: https:\/\/doi.org\/10.1109\/cvpr.2018.00124."},{"key":"e_1_3_2_1_6_1","first-page":"19","volume-title":"``Bsn: Boundary sensitive network for temporal action proposal generation[C],'' in European Conference on Computer Vision","author":"Lin T.","year":"2018","unstructured":"T. Lin , X. Zhao , H. Su , C. Wang , and M. Yang , ``Bsn: Boundary sensitive network for temporal action proposal generation[C],'' in European Conference on Computer Vision , 2018 , pp. 3\u2013 19 . doi: https:\/\/doi.org\/10.1007\/978-3-030-01225-0_1. 10.1007\/978-3-030-01225-0_1 T. Lin, X. Zhao, H. Su, C. Wang, and M. Yang, ``Bsn: Boundary sensitive network for temporal action proposal generation[C],'' in European Conference on Computer Vision, 2018, pp. 3\u201319. doi: https:\/\/doi.org\/10.1007\/978-3-030-01225-0_1."},{"key":"e_1_3_2_1_7_1","first-page":"3898","volume-title":"``Bmn: Boundary-matching network for temporal action proposal generation[C],'' in International Conference on Computer Vision","author":"Lin T.","year":"2020","unstructured":"T. Lin , X. Liu , X. Li , E. Ding , and S. Wen , ``Bmn: Boundary-matching network for temporal action proposal generation[C],'' in International Conference on Computer Vision , 2020 , pp. 3889\u2013 3898 . doi: https:\/\/doi.org\/10.1109\/iccv.2019.00399. 10.1109\/iccv.2019.00399 T. Lin, X. Liu, X. Li, E. Ding, and S. Wen, ``Bmn: Boundary-matching network for temporal action proposal generation[C],'' in International Conference on Computer Vision, 2020, pp. 3889\u20133898. doi: https:\/\/doi.org\/10.1109\/iccv.2019.00399."},{"key":"e_1_3_2_1_8_1","volume-title":"``Learning salient boundary feature for anchor-free temporal action localization[C],'' in Conference on Computer Vision and Pattern Recognition","author":"Lin C.","year":"2021","unstructured":"C. Lin , C. Xu , D. Luo , Y. Wang , Y. Tai , C. Wang , J. Li , F. Huang , and Y. Fu , ``Learning salient boundary feature for anchor-free temporal action localization[C],'' in Conference on Computer Vision and Pattern Recognition , 2021 . C. Lin, C. Xu, D. Luo, Y. Wang, Y. Tai, C. Wang, J. Li, F. Huang, and Y. Fu, ``Learning salient boundary feature for anchor-free temporal action localization[C],'' in Conference on Computer Vision and Pattern Recognition, 2021."},{"key":"e_1_3_2_1_9_1","first-page":"4334","volume-title":"``Untrimmednets for weakly supervised action recognition and detection[C],'' in Conference on Computer Vision and Pattern Recognition","author":"Wang L.","year":"2017","unstructured":"L. Wang , Y. Xiong , D. Lin , and L. V. Gool , ``Untrimmednets for weakly supervised action recognition and detection[C],'' in Conference on Computer Vision and Pattern Recognition , 2017 , pp. 4325\u2013 4334 . doi: https:\/\/doi.org\/10.1109\/cvpr.2017.678. 10.1109\/cvpr.2017.678 L. Wang, Y. Xiong, D. Lin, and L. V. Gool, ``Untrimmednets for weakly supervised action recognition and detection[C],'' in Conference on Computer Vision and Pattern Recognition, 2017, pp. 4325\u20134334. doi: https:\/\/doi.org\/10.1109\/cvpr.2017.678."},{"key":"e_1_3_2_1_10_1","first-page":"6761","volume-title":"``Weakly supervised action localization by sparse temporal pooling network[C],'' in Conference on Computer Vision and Pattern Recognition","author":"Nguyen P.","year":"2018","unstructured":"P. Nguyen , B. Han , T. Liu , and G. Prasad , ``Weakly supervised action localization by sparse temporal pooling network[C],'' in Conference on Computer Vision and Pattern Recognition , 2018 , pp. 6752\u2013 6761 . doi: https:\/\/doi.org\/10.1109\/cvpr.2018.00706. 10.1109\/cvpr.2018.00706 P. Nguyen, B. Han, T. Liu, and G. Prasad, ``Weakly supervised action localization by sparse temporal pooling network[C],'' in Conference on Computer Vision and Pattern Recognition, 2018, pp. 6752\u20136761. doi: https:\/\/doi.org\/10.1109\/cvpr.2018.00706."},{"key":"e_1_3_2_1_11_1","first-page":"154","author":"Shou Z.","year":"2018","unstructured":"Z. Shou , H. Gao , L. Zhang , and Kazuyuki and Shih-Fu Chang, ``Autoloc: Weakly-supervised temporal action localization[C],'' in European Conference on Computer Vision , 2018 , pp. 154 - 171 . doi: https:\/\/doi.org\/10.1007\/978-3-030-01270-0_10. 10.1007\/978-3-030-01270-0_10 Z. Shou, H. Gao, L. Zhang, and Kazuyuki and Shih-Fu Chang, ``Autoloc: Weakly-supervised temporal action localization[C],'' in European Conference on Computer Vision, 2018, pp. 154-171. doi: https:\/\/doi.org\/10.1007\/978-3-030-01270-0_10.","journal-title":"European Conference on Computer Vision"},{"key":"e_1_3_2_1_12_1","first-page":"745","volume-title":"``Weakly-supervised action localization with expectation-maximization multi-instance learning[C],'' in European Conference on Computer Vision","author":"Luo Z.","year":"2020","unstructured":"Z. Luo , D. Guillory , B. Shi , W. Ke , and H. Xu , ``Weakly-supervised action localization with expectation-maximization multi-instance learning[C],'' in European Conference on Computer Vision , 2020 , pp. 729\u2013 745 . doi: https:\/\/doi.org\/10.1007\/978-3-030-58526-6_43. 10.1007\/978-3-030-58526-6_43 Z. Luo, D. Guillory, B. Shi, W. Ke, and H. Xu, ``Weakly-supervised action localization with expectation-maximization multi-instance learning[C],'' in European Conference on Computer Vision, 2020, pp. 729\u2013745. doi: https:\/\/doi.org\/10.1007\/978-3-030-58526-6_43."},{"key":"e_1_3_2_1_13_1","first-page":"1019","volume-title":"``Weakly-supervised action localization by generative attention modeling[C],'' in Conference on Computer Vision and Pattern Recognition","author":"Shi B.","year":"2020","unstructured":"B. Shi , Q. Dai , Y. Mu , and J. Wang , ``Weakly-supervised action localization by generative attention modeling[C],'' in Conference on Computer Vision and Pattern Recognition , 2020 , pp. 1009\u2013 1019 . doi: https:\/\/doi.org\/10.1109\/cvpr42600.2020.00109. 10.1109\/cvpr42600.2020.00109 B. Shi, Q. Dai, Y. Mu, and J. Wang, ``Weakly-supervised action localization by generative attention modeling[C],'' in Conference on Computer Vision and Pattern Recognition, 2020, pp. 1009\u20131019. doi: https:\/\/doi.org\/10.1109\/cvpr42600.2020.00109."},{"key":"e_1_3_2_1_14_1","volume-title":"``Weakly-supervised temporal action localization by uncertainty modeling[C],'' in AAAI Conference on Artificial Intelligence","author":"Lee P.","year":"2021","unstructured":"P. Lee , J. Wang , Y. Lu , and H. Byun , ``Weakly-supervised temporal action localization by uncertainty modeling[C],'' in AAAI Conference on Artificial Intelligence , vol. abs\/ 2006 .07006, 2021 . P. Lee, J. Wang, Y. Lu, and H. Byun, ``Weakly-supervised temporal action localization by uncertainty modeling[C],'' in AAAI Conference on Artificial Intelligence, vol. abs\/2006.07006, 2021."},{"key":"e_1_3_2_1_15_1","volume-title":"``Acsnet: Action-context separation network for weakly supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence","author":"Liu Z.","year":"2021","unstructured":"Z. Liu , L. Wang , Q. Zhang , W. Tang , J. Yuan , N. Zheng , and G. Hua , ``Acsnet: Action-context separation network for weakly supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence , 2021 . Z. Liu, L. Wang, Q. Zhang, W. Tang, J. Yuan, N. Zheng, and G. Hua, ``Acsnet: Action-context separation network for weakly supervised temporal action localization[C],'' in AAAI Conference on Artificial Intelligence, 2021."},{"key":"e_1_3_2_1_16_1","first-page":"6308","volume-title":"Conference on Computer Vision and Pattern Recognition","author":"Carreira J.","year":"2017","unstructured":"J. Carreira and A. Zisserman , ``Quo vadis, action recognition? a new model and the kinetics dataset[C],'' in IEEE , Conference on Computer Vision and Pattern Recognition , 2017 , pp. 6299\u2013 6308 . doi: https:\/\/doi.org\/10.1109\/cvpr.2017.502. 10.1109\/cvpr.2017.502 J. Carreira and A. Zisserman, ``Quo vadis, action recognition? a new model and the kinetics dataset[C],'' in IEEE, Conference on Computer Vision and Pattern Recognition, 2017, pp. 6299\u20136308. doi: https:\/\/doi.org\/10.1109\/cvpr.2017.502."},{"key":"e_1_3_2_1_17_1","volume-title":"``Thumos challenge: Action recognition with a large number of classes","author":"Jiang Y.-G.","year":"2014","unstructured":"Y.-G. Jiang , J. Liu , A. Roshan Zamir , I. Laptev , M. Piccardi , M. Shah , and R. Sukthankar , ``Thumos challenge: Action recognition with a large number of classes ,'' 2014 . [Online]. http:\/\/crcv.ucf.edu\/THUMOS14\/. Y.-G. Jiang, J. Liu, A. Roshan Zamir, I. Laptev, M. Piccardi, M. Shah, and R. Sukthankar, ``Thumos challenge: Action recognition with a large number of classes,'' 2014. [Online]. http:\/\/crcv.ucf.edu\/THUMOS14\/."},{"key":"e_1_3_2_1_18_1","first-page":"970","volume-title":"``Activitynet: A large-scale video benchmark for human activity understanding[C],'' in proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Heilbron F. C.","year":"2015","unstructured":"F. C. Heilbron , V. Escorcia , B. Ghanem , and J. C. Niebles , ``Activitynet: A large-scale video benchmark for human activity understanding[C],'' in proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2015 , pp. 961\u2013 970 . doi: https:\/\/doi.org\/10.1109\/cvpr.2015.7298698. 10.1109\/cvpr.2015.7298698 F. C. Heilbron, V. Escorcia, B. Ghanem, and J. C. Niebles, ``Activitynet: A large-scale video benchmark for human activity understanding[C],'' in proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 961\u2013970. doi: https:\/\/doi.org\/10.1109\/cvpr.2015.7298698."},{"key":"e_1_3_2_1_19_1","volume-title":"``G-tad: Sub-graph localization for temporal action detection[C],'' in Conference on Computer Vision and Pattern Recognition","author":"Xu M.","year":"2020","unstructured":"M. Xu , C. Zhao , D. S. Rojas , A. Thabet , and B. Ghanem , ``G-tad: Sub-graph localization for temporal action detection[C],'' in Conference on Computer Vision and Pattern Recognition , 2020 , 10156\u201310165. doi: https:\/\/doi.org\/10.1109\/cvpr42600.2020.01017. 10.1109\/cvpr42600.2020.01017 M. Xu, C. Zhao, D. S. Rojas, A. Thabet, and B. Ghanem, ``G-tad: Sub-graph localization for temporal action detection[C],'' in Conference on Computer Vision and Pattern Recognition, 2020, 10156\u201310165. doi: https:\/\/doi.org\/10.1109\/cvpr42600.2020.01017."},{"key":"e_1_3_2_1_20_1","volume-title":"``Bsn++: Complementary boundary regressor with scale-balanced relation modeling for temporal action proposal generation[C],'' in AAAI Conference on Artificial Intelligence","author":"Su H.","year":"2021","unstructured":"H. Su , W. Gan , W. Wu , Y. Qiao , and J. Yan , ``Bsn++: Complementary boundary regressor with scale-balanced relation modeling for temporal action proposal generation[C],'' in AAAI Conference on Artificial Intelligence , 2021 . H. Su, W. Gan, W. Wu, Y. Qiao, and J. Yan, ``Bsn++: Complementary boundary regressor with scale-balanced relation modeling for temporal action proposal generation[C],'' in AAAI Conference on Artificial Intelligence, 2021."},{"key":"e_1_3_2_1_21_1","volume-title":"``CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning[C],'' in Conference on Computer Vision and Pattern Recognition","author":"Zhang C.","year":"2021","unstructured":"C. Zhang , M. Cao , D. Yang , J. Chen , and Y. Zou , ``CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning[C],'' in Conference on Computer Vision and Pattern Recognition , 2021 . C. Zhang, M. Cao, D. Yang, J. Chen, and Y. Zou, ``CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning[C],'' in Conference on Computer Vision and Pattern Recognition, 2021."}],"event":{"name":"ICVIP 2021: 2021 The 5th International Conference on Video and Image Processing","location":"Hayward CA USA","acronym":"ICVIP 2021"},"container-title":["2021 The 5th International Conference on Video and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511176.3511204","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3511176.3511204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:59Z","timestamp":1750191119000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511176.3511204"}},"subtitle":["Identify the target actions in a long untrimmed video and find the corresponding action start point and end point."],"short-title":[],"issued":{"date-parts":[[2021,12,22]]},"references-count":21,"alternative-id":["10.1145\/3511176.3511204","10.1145\/3511176"],"URL":"https:\/\/doi.org\/10.1145\/3511176.3511204","relation":{},"subject":[],"published":{"date-parts":[[2021,12,22]]},"assertion":[{"value":"2022-03-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}