{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T20:24:23Z","timestamp":1771705463513,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351044","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"738-746","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":57,"title":["Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization"],"prefix":"10.1145","author":[{"given":"Chengwei","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Yunlu","family":"Xu","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute, Shanghai, China"}]},{"given":"Zhanzhan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute & Zhejiang University, Shanghai, China"}]},{"given":"Yi","family":"Niu","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute, Shanghai, China"}]},{"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute, Hangzhou, China"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Futai","family":"Zou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Fabian Caba Heilbron, and Bernard Ghanem","author":"Alwassel Humam","year":"2018"},{"key":"e_1_3_2_1_2_1","volume-title":"SST: Single-Stream Temporal Action Proposals. In CVPR. 6373--6382.","author":"Buch Shyamal","year":"2017"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Joao Carreira and Andrew Zisserman. 2017. Quo Vadis Action Recognition? A New Model and the Kinetics Dataset. In CVPR . 4724--4733.  Joao Carreira and Andrew Zisserman. 2017. Quo Vadis Action Recognition? A New Model and the Kinetics Dataset. In CVPR . 4724--4733.","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Yu Wei Chao Sudheendra Vijayanarasimhan Bryan Seybold David A Ross Jia Deng and Rahul Sukthankar. 2018. Rethinking the Faster R-CNN Architecture for Temporal Action Localization. In CVPR . 2933--2942.  Yu Wei Chao Sudheendra Vijayanarasimhan Bryan Seybold David A Ross Jia Deng and Rahul Sukthankar. 2018. Rethinking the Faster R-CNN Architecture for Temporal Action Localization. In CVPR . 2933--2942.","DOI":"10.1109\/CVPR.2018.00124"},{"key":"e_1_3_2_1_5_1","unstructured":"Xiyang Dai Bharat Singh Guyue Zhang Larry S. Davis and Yan Qiu Chen. 2017. Temporal Context Network for Activity Localization in Videos. In ICCV . 5727--5736.  Xiyang Dai Bharat Singh Guyue Zhang Larry S. Davis and Yan Qiu Chen. 2017. Temporal Context Network for Activity Localization in Videos. In ICCV . 5727--5736."},{"key":"e_1_3_2_1_6_1","volume-title":"Cascaded Boundary Regression for Temporal Action Detection . CoRR","author":"Gao Jiyang","year":"2017"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Fabian Caba Heilbron Victor Escorcia Bernard Ghanem and Juan Carlos Niebles. 2015. ActivityNet: A large-scale video benchmark for human activity understanding. In CVPR . 961--970.  Fabian Caba Heilbron Victor Escorcia Bernard Ghanem and Juan Carlos Niebles. 2015. ActivityNet: A large-scale video benchmark for human activity understanding. In CVPR . 961--970.","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Zilong Huang Xinggang Wang Jiasi Wang Wenyu Liu and Jingdong Wang. 2018. Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing. In CVPR . 7014--7023.  Zilong Huang Xinggang Wang Jiasi Wang Wenyu Liu and Jingdong Wang. 2018. Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing. In CVPR . 7014--7023.","DOI":"10.1109\/CVPR.2018.00733"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_10_1","unstructured":"Y.-G. Jiang J. Liu A. Roshan Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. 2014. THUMOS Challenge: Action Recognition with a Large Number of Classes . http:\/\/crcv.ucf.edu\/THUMOS14\/.  Y.-G. Jiang J. Liu A. Roshan Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. 2014. THUMOS Challenge: Action Recognition with a Large Number of Classes . http:\/\/crcv.ucf.edu\/THUMOS14\/."},{"key":"e_1_3_2_1_11_1","volume-title":"Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, Mustafa Suleyman, and Andrew Zisserman.","author":"Kay Will","year":"2017"},{"key":"e_1_3_2_1_12_1","volume-title":"Lampert","author":"Kolesnikov Alexander","year":"2016"},{"key":"e_1_3_2_1_13_1","unstructured":"Tianwei Lin Xu Zhao and Zheng Shou. 2017. Single Shot Temporal Action Detection. In ACM MM. 988--996.  Tianwei Lin Xu Zhao and Zheng Shou. 2017. Single Shot Temporal Action Detection. In ACM MM. 988--996."},{"key":"e_1_3_2_1_14_1","volume-title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation. In ECCV . 3--19.","author":"Lin Tianwei","year":"2018"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Phuc Nguyen Ting Liu Gautam Prasad and Bohyung Han. 2018. Weakly Supervised Action Localization by Sparse Temporal Pooling Network. In CVPR . 6752--6761.  Phuc Nguyen Ting Liu Gautam Prasad and Bohyung Han. 2018. Weakly Supervised Action Localization by Sparse Temporal Pooling Network. In CVPR . 6752--6761.","DOI":"10.1109\/CVPR.2018.00706"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Dan Oneata Jakob J Verbeek and Cordelia Schmid. 2014. Efficient Action Localization with Approximately Normalized Fisher Vectors. In CVPR . 2545--2552.  Dan Oneata Jakob J Verbeek and Cordelia Schmid. 2014. Efficient Action Localization with Approximately Normalized Fisher Vectors. In CVPR . 2545--2552.","DOI":"10.1109\/CVPR.2014.326"},{"key":"e_1_3_2_1_17_1","volume-title":"Amit K Roy Chowdhury, and Amit K","author":"Paul Sujoy","year":"2018"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Alexander Richard and Juergen Gall. 2016. Temporal Action Detection Using a Statistical Language Model. In CVPR . 3131--3140.  Alexander Richard and Juergen Gall. 2016. Temporal Action Detection Using a Statistical Language Model. In CVPR . 3131--3140.","DOI":"10.1109\/CVPR.2016.341"},{"key":"e_1_3_2_1_19_1","volume-title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos. In CVPR. 5734--5743.","author":"Shou Zheng","year":"2017"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Zheng Shou Hang Gao Lei Zhang Kazuyuki Miyazawa and Shih-Fu Chang. 2018. AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos. In ECCV . 154--171.  Zheng Shou Hang Gao Lei Zhang Kazuyuki Miyazawa and Shih-Fu Chang. 2018. AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos. In ECCV . 154--171.","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Zheng Shou Dongang Wang and Shih Fu Chang. 2016. Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs. In CVPR . 1049--1058.  Zheng Shou Dongang Wang and Shih Fu Chang. 2016. Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs. In CVPR . 1049--1058.","DOI":"10.1109\/CVPR.2016.119"},{"key":"e_1_3_2_1_22_1","volume-title":"Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge . CoRR","author":"Singh Gurkirt","year":"1979"},{"key":"e_1_3_2_1_23_1","unstructured":"Krishna Kumar Singh and Jae Lee Yong. 2017. Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization. In ICCV. 3544--3553.  Krishna Kumar Singh and Jae Lee Yong. 2017. Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization. In ICCV. 3544--3553."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Limin Wang Yuanjun Xiong Dahua Lin and Luc Van Gool. 2017. UntrimmedNets for Weakly Supervised Action Recognition and Detection. In CVPR . 6402--6411.  Limin Wang Yuanjun Xiong Dahua Lin and Luc Van Gool. 2017. UntrimmedNets for Weakly Supervised Action Recognition and Detection. In CVPR . 6402--6411.","DOI":"10.1109\/CVPR.2017.678"},{"key":"e_1_3_2_1_25_1","volume-title":"Zhao Yao, and Shuicheng Yan.","author":"Wei Yunchao","year":"2017"},{"key":"e_1_3_2_1_26_1","volume-title":"A Pursuit of Temporal Accuracy in General Activity Detection . CoRR","author":"Xiong Yuanjun","year":"2017"},{"key":"e_1_3_2_1_27_1","unstructured":"Huijuan Xu Abir Das and Kate Saenko. 2017. R-C3D: Region Convolutional 3D Network for Temporal Activity Detection. In ICCV . 5783--5792.  Huijuan Xu Abir Das and Kate Saenko. 2017. R-C3D: Region Convolutional 3D Network for Temporal Activity Detection. In ICCV . 5783--5792."},{"key":"e_1_3_2_1_28_1","unstructured":"Yunlu Xu Chengwei Zhang Zhanzhan Cheng Jianwen Xie Yi Niu Shiliang Pu and Fei Wu. 2019. Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection. AAAI .  Yunlu Xu Chengwei Zhang Zhanzhan Cheng Jianwen Xie Yi Niu Shiliang Pu and Fei Wu. 2019. Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection. AAAI ."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Ke Yang Peng Qiao Dongsheng Li Shaohe Lv and Yong Dou. 2018. Exploring Temporal Preservation Networks for Precise Temporal Action Localization. In AAAI . 7477--7484.  Ke Yang Peng Qiao Dongsheng Li Shaohe Lv and Yong Dou. 2018. Exploring Temporal Preservation Networks for Precise Temporal Action Localization. In AAAI . 7477--7484.","DOI":"10.1609\/aaai.v32i1.12234"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Yue Zhao Yuanjun Xiong Limin Wang Zhirong Wu Xiaoou Tang and Dahua Lin. 2017. Temporal Action Detection with Structured Segment Networks. In ICCV. 2933--2942.  Yue Zhao Yuanjun Xiong Limin Wang Zhirong Wu Xiaoou Tang and Dahua Lin. 2017. Temporal Action Detection with Structured Segment Networks. In ICCV. 2933--2942.","DOI":"10.1109\/ICCV.2017.317"},{"key":"e_1_3_2_1_31_1","volume-title":"One-by-one Collection: A Weakly Supervised Temporal Action Detector. In ACM Multimedia Conference. 35--44","author":"Zhong Jia Xing","year":"2018"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Bolei Zhou Aditya Khosla Agata Lapedriza Aude Oliva and Antonio Torralba. 2016. Learning Deep Features for Discriminative Localization. In CVPR . 2921--2929.  Bolei Zhou Aditya Khosla Agata Lapedriza Aude Oliva and Antonio Torralba. 2016. Learning Deep Features for Discriminative Localization. In CVPR . 2921--2929.","DOI":"10.1109\/CVPR.2016.319"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351044","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:11Z","timestamp":1750201991000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":32,"alternative-id":["10.1145\/3343031.3351044","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351044","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}