{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T05:57:35Z","timestamp":1768975055457,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61375016"],"award-info":[{"award-number":["No.61375016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475336","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T06:09:05Z","timestamp":1634537345000},"page":"1847-1855","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Ego-Deliver: A Large-Scale Dataset For Egocentric Video Analysis"],"prefix":"10.1145","author":[{"given":"Haonan","family":"Qiu","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"He","sequence":"additional","affiliation":[{"name":"University of Florida, Florida, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuchun","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiyuan","family":"Shao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feiyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Victor Escorcia, and Bernard Ghanem.","author":"Alwassel Humam","year":"2018"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 8th International Conference on Language Resources and Evaluation","author":"Bunt H.C."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"e_1_3_2_1_5_1","volume-title":"Scaling Egocentric Vision: The EPIC- KITCHENS Dataset. In European Conference on Computer Vision (ECCV).","author":"Damen Dima","year":"2018"},{"key":"e_1_3_2_1_6_1","volume-title":"Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michae Wray.","author":"Damen Dima","year":"2020"},{"key":"e_1_3_2_1_7_1","volume-title":"Tech","author":"la Torre Fernando De","year":"2009"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477701"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV).","author":"Li Yin"},{"key":"e_1_3_2_1_16_1","volume-title":"Focal Loss for Dense Object Detection. In 2017 IEEE International Conference on Computer Vision (ICCV). 2999--3007","author":"Lin T.","year":"2017"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2355089"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354909"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"e_1_3_2_1_25_1","volume-title":"Training Region-based Object Detectors with Online Hard Example Mining. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Shrivastava Abhinav","year":"2016"},{"key":"e_1_3_2_1_26_1","volume-title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos. CoRR abs\/1804.09626","author":"Sigurdsson Gunnar A.","year":"2018"},{"key":"e_1_3_2_1_27_1","volume-title":"AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection. arXiv preprint arXiv:1910.08250","author":"Tang Yiping","year":"2019"},{"key":"e_1_3_2_1_28_1","volume-title":"A Pursuit of Temporal Accuracy in General Activity Detection. CoRR abs\/1703.02716","author":"Xiong Yuanjun","year":"2017"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Runhao Zeng Wenbing Huang Mingkui Tan Yu Rong Peilin Zhao Junzhou Huang and Chuang Gan. 2019. Graph Convolutional Networks for Temporal Action Localization. In ICCV.  Runhao Zeng Wenbing Huang Mingkui Tan Yu Rong Peilin Zhao Junzhou Huang and Chuang Gan. 2019. Graph Convolutional Networks for Temporal Action Localization. In ICCV.","DOI":"10.1109\/ICCV.2019.00719"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"e_1_3_2_1_34_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.  Yue Zhao Yuanjun Xiong Limin Wang Zhirong Wu Xiaoou Tang and Dahua Lin. 2017. Temporal Action Detection with Structured Segment Networks. In ICCV.","DOI":"10.1109\/ICCV.2017.317"},{"key":"e_1_3_2_1_35_1","volume-title":"Towards Automatic Learning of Procedures From Web Instructional Videos. In AAAI Conference on Artificial Intelligence.","author":"Zhou Luowei","year":"2018"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475336","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:18Z","timestamp":1750193358000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":35,"alternative-id":["10.1145\/3474085.3475336","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475336","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}