{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T07:26:16Z","timestamp":1768289176770,"version":"3.49.0"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093291","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"1606-1615","source":"Crossref","is-referenced-by-count":24,"title":["Spatio-Temporal Ranked-Attention Networks for Video Captioning"],"prefix":"10.1109","author":[{"given":"Anoop","family":"Cherian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiori","family":"Hori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim K.","family":"Marks","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref72","article-title":"Automatic video description generation via lstm with joint two-stream encoding","author":"zhang","year":"2016","journal-title":"ICPR"},{"key":"ref71","article-title":"Spatiotemporal attention models for grounded video captioning","author":"zanfir","year":"2016","journal-title":"ACCV"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref74","article-title":"The sound of pixels","author":"zhao","year":"0"},{"key":"ref39","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v27i1.8679","article-title":"Generating natural-language video descriptions using text-mined knowledge","author":"krishnamoorthy","year":"2013","journal-title":"AAAI"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref30","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref37","article-title":"Video captioning with listwise supervision","author":"liu","year":"2017","journal-title":"AAAI"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref35","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/307"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1743384.1743433"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref63","article-title":"Video super-resolution based on spatial-temporal recurrent residual networks","author":"yang","year":"2017","journal-title":"CVIU"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123327"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459342"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref67","article-title":"Grounded language learning from video described with sentences","author":"yu","year":"2013","journal-title":"ACL"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296542"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref21","article-title":"On differentiating parameterized argmin and argmax problems with application to bi-level optimization","author":"gould","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123354"},{"key":"ref51","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2125"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref55","article-title":"Reconstruction network for vide ocaptioning","author":"wang","year":"2018","journal-title":"CVPR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"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","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015"},{"key":"ref11","article-title":"Less is more: Picking informative frames for video captioning","author":"chen","year":"2018","journal-title":"ECCV"},{"key":"ref40","article-title":"Two-stream collaborative learning with spatial-temporal attention for video classification","author":"peng","year":"2018","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.172"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018"},{"key":"ref16","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.212"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref4","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"NIPS"},{"key":"ref3","article-title":"Bottom-up and top-down attention for image captioning and VQA","author":"anderson","year":"2018","journal-title":"CVPR"},{"key":"ref6","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"NIPS"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref49","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","author":"thomason","year":"2014","journal-title":"ICCL"},{"key":"ref9","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"HLT-ACL"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref48","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"NIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130432"},{"key":"ref42","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref43","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093291.pdf?arnumber=9093291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T19:46:14Z","timestamp":1666554374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093291","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}