{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T06:31:31Z","timestamp":1725085891334},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/icarm.2019.8834066","type":"proceedings-article","created":{"date-parts":[[2019,9,13]],"date-time":"2019-09-13T00:27:41Z","timestamp":1568334461000},"source":"Crossref","is-referenced-by-count":4,"title":["Attention-based Visual-Audio Fusion for Video Caption Generation"],"prefix":"10.1109","author":[{"given":"Ningning","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linhua","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"anderson","year":"2017","journal-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering[J]"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref12","article-title":"Translating Videos to Natural Language Using Deep Recurrent Neural Networks[J]","author":"venugopalan","year":"2014","journal-title":"Computer Science"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2818184"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"ref16","article-title":"Learning Spatiotemporal Features with 3D Convolutional Networks[C]","author":"tran","year":"2016","journal-title":"2015 IEEE International Conference on Computer Vision (ICCV)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2865000"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940770"},{"key":"ref4","article-title":"Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge[J]","author":"vinyals","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1994.03520200048034"},{"key":"ref3","author":"vinyals","year":"2014","journal-title":"Show and Tell A Neural Image Caption Generator"},{"key":"ref6","author":"shi","year":"2015","journal-title":"Convolutional LSTM network A machine learning approach for precipitation nowcasting"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref8","article-title":"Effective Approaches to Attention-based Neural Machine Translation[J]","author":"luong","year":"2015","journal-title":"Computer Science"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref2","article-title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation[J]","author":"cho","year":"2014","journal-title":"Computer Science"},{"key":"ref9","article-title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention[J]","author":"xu","year":"2015","journal-title":"Computer Science"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref20","author":"hao","year":"2017","journal-title":"Integrating both Visual and Audio Cues for Enhanced Video Caption[J]"},{"key":"ref22","author":"ullrich","year":"2017","journal-title":"Soft weight-sharing for neural network compression"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2819826"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref23","first-page":"199","article-title":"Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism[J]","author":"yao","year":"2015","journal-title":"ArXiv eprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2007.08.030"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-009-9059-4"}],"event":{"name":"2019 IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM)","location":"Toyonaka, Japan","start":{"date-parts":[[2019,7,3]]},"end":{"date-parts":[[2019,7,5]]}},"container-title":["2019 IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8826169\/8833630\/08834066.pdf?arnumber=8834066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:18:08Z","timestamp":1658261888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8834066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icarm.2019.8834066","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}