{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T09:07:50Z","timestamp":1725700070564},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561797","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"13997-14003","source":"Crossref","is-referenced-by-count":1,"title":["Referring Image Segmentation via Language-Driven Attention"],"prefix":"10.1109","author":[{"given":"Ding-Jie","family":"Chen","sequence":"first","affiliation":[{"name":"Academia Sinica,Institute of Information Science,Taiwan"}]},{"given":"He-Yen","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Academia Sinica,Institute of Information Science,Taiwan"}]},{"given":"Tyng-Luh","family":"Liu","sequence":"additional","affiliation":[{"name":"Academia Sinica,Institute of Information Science,Taiwan"}]}],"member":"263","reference":[{"key":"ref39","first-page":"263","article-title":"Referring expression object segmentation with caption-aware consistency","author":"chen","year":"2019","journal-title":"BMVC"},{"key":"ref38","article-title":"Utilizing large scale vision and text datasets for image segmentation from referring expressions","author":"hu","year":"2016","journal-title":"CoRR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref31","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ISCA Speech Synthesis Workshop"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref36","article-title":"Training rnns as fast as cnns","author":"lei","year":"2017","journal-title":"CoRR"},{"key":"ref35","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"shi","year":"2015","journal-title":"NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref27","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref22","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref21","first-page":"10502","article-title":"Cross-modal self-attention network for referring image segmentation","author":"ye","year":"2019","journal-title":"CVPR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00312"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref25","first-page":"1808","article-title":"Learning generative models with visual attention","author":"tang","year":"2014","journal-title":"NIPS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2942480"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref55","first-page":"109","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","author":"kr\u00e4henb\u00fchl","year":"2011","journal-title":"NIPS"},{"key":"ref54","first-page":"10031","article-title":"Multitask collaborative network for joint referring expression comprehension and segmentation","author":"luo","year":"2020","journal-title":"CVPR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481301"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196987"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461082"},{"key":"ref6","article-title":"Learning answer embeddings for visual question answering","author":"hu","year":"2018","journal-title":"CVPR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref7","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"NIPS"},{"key":"ref49","first-page":"740","article-title":"Microsoft COCO: common objects in´ context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00050"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref44","first-page":"833","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"ECCV"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561797.pdf?arnumber=9561797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:21:53Z","timestamp":1659482513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561797","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}