{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:17:07Z","timestamp":1750220227820,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 110-2634-F-002-028-,MOST 110-2221-E-002-128-MY3-"],"award-info":[{"award-number":["MOST 110-2634-F-002-028-,MOST 110-2221-E-002-128-MY3-"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,26]]},"DOI":"10.1145\/3459637.3482022","type":"proceedings-article","created":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T18:34:11Z","timestamp":1635618851000},"page":"4436-4444","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["VidLife: A Dataset for Life Event Extraction from Videos"],"prefix":"10.1145","author":[{"given":"Tai-Te","family":"Chu","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An-Zi","family":"Yen","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Hong","family":"Ang","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hen-Hsen","family":"Huang","sequence":"additional","affiliation":[{"name":"Academia Sinica & MOST Joint Research Center for AI Technology and All Vista Healthcare, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Hsi","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"volume-title":"IAPR Workshop on Multimodal Pattern Recognition of Social Signals in Human-Computer Interaction. Springer, 27--37","year":"2018","author":"Abebe Girmaw","key":"e_1_3_2_1_1_1"},{"volume-title":"TRECVID 2020: comprehensive campaign for evaluating video retrieval tasks across multiple application domains. In Proceedings of TRECVID 2020. NIST, USA.","year":"2020","author":"Awad George","key":"e_1_3_2_1_2_1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/1717171"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3391927"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.336"},{"volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 720--736","year":"2018","author":"Damen Dima","key":"e_1_3_2_1_6_1"},{"volume-title":"Antonino Furnari, Evangelos Kazakos, Jian Ma, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, et al.","year":"2020","author":"Damen Dima","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","volume-title":"Working Notes of CLEF 2017 - Conference and Labs of the Evaluation Forum, Dublin, Ireland, September 11--14, 2017 (CEUR Workshop Proceedings","volume":"10","author":"Dang-Nguyen Duc-Tien","year":"2017"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","author":"Devlin Jacob","year":"2019"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOMW.2017.7917583"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354936"},{"volume-title":"Proceedings of the Third International Conference on Language Resources and Evaluation (LREC'02)","year":"2002","author":"Fillmore Charles J.","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00524"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390700"},{"volume-title":"Do You Live a Healthy Life? Analyzing Lifestyle by Visual Life Logging. arXiv preprint arXiv:2011.12102","year":"2020","author":"Gao Qing","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914680"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Cathal Gurrin Hideo Joho Frank Hopfgartner Liting Zhou Rashmi Gupta Rami Albatal Dang Nguyen and Duc Tien. 2017. Overview of ntcir-13 lifelog-2 task. NTCIR.  Cathal Gurrin Hideo Joho Frank Hopfgartner Liting Zhou Rashmi Gupta Rami Albatal Dang Nguyen and Duc Tien. 2017. Overview of ntcir-13 lifelog-2 task. NTCIR.","DOI":"10.1145\/2911451.2914680"},{"key":"e_1_3_2_1_18_1","unstructured":"Cathal Gurrin Hideo Joho Frank Hopfgartner Liting Zhou Van-Tu Ninh Tu-Khiem Le Rami Albatal Duc-Tien Dang-Nguyen and Grace Healy. 2019. Overview of the NTCIR-14 Lifelog-3 task.  Cathal Gurrin Hideo Joho Frank Hopfgartner Liting Zhou Van-Tu Ninh Tu-Khiem Le Rami Albatal Duc-Tien Dang-Nguyen and Grace Healy. 2019. Overview of the NTCIR-14 Lifelog-3 task."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000033"},{"volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","year":"2016","author":"He Kaiming","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","unstructured":"Graham Healy Tu-Khiem Le Hideo Joho Frank Hopfgartner and Cathal Gurrin. 2020. Overview of NTCIR-15 MART. In NTCIR-15.  Graham Healy Tu-Khiem Le Hideo Joho Frank Hopfgartner and Cathal Gurrin. 2020. Overview of NTCIR-15 MART. In NTCIR-15."},{"volume-title":"MovieNet: A Holistic Dataset for Movie Understanding. In The European Conference on Computer Vision (ECCV).","year":"2020","author":"Huang Qingqiu","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"volume-title":"ICCV Workshop on Scene Graph Representation and Learning.","year":"2019","author":"Hussein Noureldien","key":"e_1_3_2_1_24_1"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_26_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev etal 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017).  Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"volume-title":"Mining youtube-a dataset for learning fine-grained action concepts from webly supervised video data. arXiv preprint arXiv:1906.01012","year":"2019","author":"Kuehne Hilde","key":"e_1_3_2_1_27_1"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2355016"},{"volume-title":"2020 a. TVQA+: Spatio-Temporal Grounding for Video Question Answering. (July","year":"2020","author":"Lei Jie","key":"e_1_3_2_1_29_1"},{"volume-title":"2020 b. Tvr: A large-scale dataset for video-subtitle moment retrieval. arXiv preprint arXiv:2001.09099","year":"2020","author":"Lei Jie","key":"e_1_3_2_1_30_1"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1214"},{"volume-title":"Proceedings of the European Conference on Computer Vision (ECCV).","author":"Li Yin","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.4108\/icst.pervasivehealth.2013.252128"},{"volume-title":"Behaviour understanding through the analysis of image sequences collected by wearable cameras. ELCVIA: electronic letters on computer vision and image analysis","year":"2020","author":"Mart'inez Estefan'ia Talavera","key":"e_1_3_2_1_34_1"},{"volume-title":"RareAct: A video dataset of unusual interactions. arXiv preprint arXiv:2008.01018","year":"2020","author":"Miech Antoine","key":"e_1_3_2_1_35_1"},{"volume-title":"Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6817--6826","year":"2017","author":"Nakamura K.","key":"e_1_3_2_1_36_1"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.338"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2355089"},{"key":"e_1_3_2_1_40_1","article-title":"Towards A Smartphone Based Lifelogging System for Reminiscence","volume":"14","author":"Rahman Md Abed","year":"2018","journal-title":"Journal of Engineering and Technology"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings, Part I (Lecture Notes in Computer Science","volume":"526","author":"Sigurdsson Gunnar A.","year":"2016"},{"volume-title":"Asian Conference on Computer Vision. Springer, 445--458","year":"2014","author":"Song Sibo","key":"e_1_3_2_1_42_1"},{"volume-title":"Amir Roshan Zamir, and Mubarak Shah","year":"2012","author":"Soomro Khurram","key":"e_1_3_2_1_43_1"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1080\/09658211.2014.886703"},{"volume-title":"Action Understanding with Multiple Classes of Actors. arXiv preprint arXiv:1704.08723","year":"2017","author":"Xu Chenliang","key":"e_1_3_2_1_45_1"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2586075"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331209"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186909"},{"volume-title":"2019 b. Multimodal joint learning for personal knowledge base construction from Twitter-based lifelogs. Information Processing & Management","year":"2019","author":"Yen An-Zi","key":"e_1_3_2_1_49_1"},{"volume-title":"Stair actions: A video dataset of everyday home actions. arXiv preprint arXiv:1804.04326","year":"2018","author":"Yoshikawa Yuya","key":"e_1_3_2_1_50_1"}],"event":{"name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event Queensland Australia","acronym":"CIKM '21"},"container-title":["Proceedings of the 30th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482022","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3482022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:11Z","timestamp":1750188611000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":50,"alternative-id":["10.1145\/3459637.3482022","10.1145\/3459637"],"URL":"https:\/\/doi.org\/10.1145\/3459637.3482022","relation":{},"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}