{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:35:22Z","timestamp":1767706522767,"version":"build-2065373602"},"reference-count":44,"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\/wacv45572.2020.9093515","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"3316-3325","source":"Crossref","is-referenced-by-count":20,"title":["Attention Flow: End-to-End Joint Attention Estimation"],"prefix":"10.1109","author":[{"given":"Omer","family":"Sumer","sequence":"first","affiliation":[]},{"given":"Peter","family":"Gerjets","sequence":"additional","affiliation":[]},{"given":"Ulrich","family":"Trautwein","sequence":"additional","affiliation":[]},{"given":"Enkelejda","family":"Kasneci","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/mbe.12011"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref33","article-title":"Automatic mapping of remote crowd gaze to stimuli in the classroom","author":"santini","year":"2017","journal-title":"Eye Tracking Enhanced Learning (ETEL2017)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.160"},{"key":"ref31","first-page":"199","article-title":"Where are they looking?","volume":"28","author":"recasens","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/jcal.12232"},{"key":"ref37","article-title":"Teachers’ perception in the classroom","author":"s\u00fcmer","year":"2018","journal-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-9568.2006.04822.x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/1745691615589104"},{"key":"ref34","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00676"},{"key":"ref40","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00785"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10648-019-09514-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.370"},{"key":"ref14","first-page":"545","article-title":"Graph-based visual saliency. In B. Schölkopf","author":"harel","year":"2007","journal-title":"Advances in Neural Information Processing Systems 19"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TPAMI.2011.146","article-title":"Image signature: Highlighting sparse salient regions","volume":"34","author":"hou","year":"2012","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.679"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.435"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv eprints abs\/1409 0473"},{"key":"ref27","first-page":"422","article-title":"3d social saliency from head-mounted cameras","author":"park","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171287"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_49"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299110"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref7","article-title":"Connecting gaze, scene, and attention: Generalized attention estimation via joint modeling of gaze and scene saliency","author":"chong","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702592"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-011-9624-y"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/0012-1649.29.5.832"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/mbe.12002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/1088357607311443"},{"key":"ref21","article-title":"Deepgaze II: reading fixations from deep features trained on object recognition","author":"k\u00fcmmerer","year":"2016","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/09540090310001655101"},{"key":"ref41","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning volume 37 of Proceedings of Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1163\/156855306778522497"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","author":"zitnick","year":"2014","journal-title":"Computer Vision – ECCV 2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.648"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1044\/2014_JSLHR-L-13-0058"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","start":{"date-parts":[[2020,3,1]]},"location":"Snowmass Village, CO, USA","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\/09093515.pdf?arnumber=9093515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:15:54Z","timestamp":1656602154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093515","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}