{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:49:41Z","timestamp":1772498981775,"version":"3.50.1"},"reference-count":65,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/dicta.2017.8227494","type":"proceedings-article","created":{"date-parts":[[2017,12,21]],"date-time":"2017-12-21T20:19:08Z","timestamp":1513887548000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["TenniSet: A Dataset for Dense Fine-Grained Event Recognition, Localisation and Description"],"prefix":"10.1109","author":[{"given":"Hayden","family":"Faulkner","sequence":"first","affiliation":[]},{"given":"Anthony","family":"Dick","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0851-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.902885"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-319-44781-0_1","article-title":"Video description using bidirectional recurrent neural networks","author":"peris","year":"2016","journal-title":"Artificial Neural Networks and Machine Learning - ICANN 2016"},{"key":"ref31","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1007\/978-3-319-11752-2_15","article-title":"Coherent multi-sentence video description with variable level of detail","author":"rohrbach","year":"2014","journal-title":"Pattern Recognition"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1162\/tacl_a_00207","article-title":"Grounding action descriptions in videos","volume":"1","author":"regneri","year":"2013","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.332"},{"key":"ref60","author":"xu","year":"2015","journal-title":"A multi-scale multiple instance video description network"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref63","author":"yeung","year":"2015","journal-title":"Every moment counts Dense detailed labeling of actions in complex videos"},{"key":"ref28","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref27","article-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","author":"montes","year":"2016","journal-title":"1st NIPS Workshop on Large Scale Computer Vision Systems"},{"key":"ref65","author":"zanfir","year":"2016","journal-title":"Spatio-Temporal attention models for grounded video captioning"},{"key":"ref29","article-title":"The LEAR submission at thumos 2014","author":"oneata","year":"2014","journal-title":"ECCV THUMOS Workshop"},{"key":"ref2","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref1","author":"abu-el-haija","year":"2016","journal-title":"Youtube-8m A large-scale video classification benchmark"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref21","author":"kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref23","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out Proceedings of the ACL-04 Workshop"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2000.840653"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref50","author":"torabi","year":"2015","journal-title":"Using descriptive video services to create a large data source for video annotation research"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref58","article-title":"Action recognition and detection by combining motion and appearance features","author":"wang","year":"2014","journal-title":"THUMOS14 Action Recognition Challenge"},{"key":"ref57","first-page":"124","article-title":"Evaluation of local spatio-temporal features for action recognition","author":"wang","year":"2009","journal-title":"BMVC 2009-British Machine Vision Conference"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref54","author":"venugopalan","year":"2014","journal-title":"Translating videos to natural language using deep recurrent neural networks"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref12","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"gorban","year":"2015","journal-title":"CVPR Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70711"},{"key":"ref14","author":"gu","year":"2017","journal-title":"AVA A video dataset of spatio-temporally localized atomic visual actions"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref16","first-page":"6","article-title":"A large video database for human motion recognition","volume":"4","author":"jhuang","year":"2011","journal-title":"Proc of IEEE International Conference on Computer Vision"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref18","author":"jiang","year":"2014","journal-title":"THUMOS Challenge Action Recognition with A Large Number of Classes"},{"key":"ref19","first-page":"5","article-title":"Fast saliency based pooling of fisher encoded dense trajectories","volume":"1","author":"karaman","year":"2014","journal-title":"ECCV THUMOS Workshop"},{"key":"ref4","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume":"1","author":"chen","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref6","author":"chollet","year":"2015"},{"key":"ref5","author":"chen","year":"2015","journal-title":"Microsoft COCO captions Data collection and evaluation server"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref7","article-title":"A system for the automatic annotation of tennis matches","author":"christmas","year":"2005","journal-title":"International Workshop on Content-Based Multimedia Indexing(CBMI)"},{"key":"ref49","author":"sukhwani","year":"2015","journal-title":"TennisVid2Text Fine-grained descriptions for domain specific videos"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1007\/978-3-319-46487-9_47","article-title":"DAPs: Deep action proposals for action understanding","author":"escorcia","year":"2016","journal-title":"Computer Vision - ECCV 2016"},{"key":"ref46","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref45","first-page":"568","article-title":"Two-Stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref48","author":"soomro","year":"2012","journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref42","author":"shetty","year":"2015","journal-title":"Video captioning with recurrent networks based on frame-and video-level features and visual content classification"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","author":"sigurdsson","year":"2016","journal-title":"Computer Vision - ECCV 2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"}],"event":{"name":"2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","location":"Sydney, NSW","start":{"date-parts":[[2017,11,29]]},"end":{"date-parts":[[2017,12,1]]}},"container-title":["2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8226656\/8227375\/08227494.pdf?arnumber=8227494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T00:27:57Z","timestamp":1693355277000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8227494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/dicta.2017.8227494","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}