{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T11:37:23Z","timestamp":1760441843915,"version":"3.28.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"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":[[2024,6,2]]},"DOI":"10.1109\/iv55156.2024.10588598","type":"proceedings-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T17:19:28Z","timestamp":1721063968000},"page":"2353-2360","source":"Crossref","is-referenced-by-count":1,"title":["Guiding Attention in End-to-End Driving Models"],"prefix":"10.1109","author":[{"given":"Diego","family":"Porres","sequence":"first","affiliation":[{"name":"Universitat Autònoma de Barcelona (UAB),Computer Vision Center (CVC),Spain"}]},{"given":"Yi","family":"Xiao","sequence":"additional","affiliation":[{"name":"Universitat Autònoma de Barcelona (UAB),Computer Vision Center (CVC),Spain"}]},{"given":"Gabriel","family":"Villalonga","sequence":"additional","affiliation":[{"name":"Universitat Autònoma de Barcelona (UAB),Computer Vision Center (CVC),Spain"}]},{"given":"Alexandre","family":"Levy","sequence":"additional","affiliation":[{"name":"Universitat Autònoma de Barcelona (UAB),Computer Vision Center (CVC),Spain"}]},{"given":"Antonio M.","family":"L\u00f3pez","sequence":"additional","affiliation":[{"name":"Universitat Autònoma de Barcelona (UAB),Computer Vision Center (CVC),Spain"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0042-6989(94)00276-R"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"article-title":"Attention is all you need","volume-title":"Neural Information Processing Systems (NeurIPS)","author":"Vaswani","key":"ref7"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"Bahdanau","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref10"},{"key":"ref11","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.64"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341506"},{"key":"ref19","article-title":"Attention in psychology, neuroscience, and machine learning","volume-title":"Frontiers in Computational Neuroscience","volume":"14","author":"Lindsay","year":"2020"},{"article-title":"CARLA: An open urban driving simulator","volume-title":"Conference on Robot Learning (CoRL)","author":"Dosovitskiy","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21236\/ADA528601"},{"article-title":"Advances in neural information processing systems","volume-title":"Neural Information Processing Systems (NIPS)","author":"Stepputtis","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3262423"},{"article-title":"Imitation learning for end to end vehicle longitudinal control with forward camera","volume-title":"Neural Information Processing Systems (NIPS) Imitation Learning WS","author":"George","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.056"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"article-title":"Model-based imitation learning for urban driving","volume-title":"Neural Information Processing Systems (NeurIPS)","author":"Hu","key":"ref27"},{"article-title":"Learning to play guess who? and inventing a grounded language as a consequence","year":"2016","author":"Jorge","key":"ref28"},{"key":"ref29","article-title":"Deep imitation learning for playing real time strategy games","author":"Barratt","year":"2019","journal-title":"Cs229 Stanf. Edu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06367-y"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-247-2.50055-3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-35995-8_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"volume-title":"International Conference on Robotics and Automation (ICRA)","key":"ref34","article-title":"Bewley, alex and rigley, jessica and liu, yuxuan and hawke, jeffrey and shen, richard and lam, vinh-dieu and kendall, alex"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161449"},{"article-title":"End-to-end autonomous driving: Challenges and frontiers","year":"2023","author":"Chen","key":"ref39"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representation (ICLR)","author":"Dosovitskiy","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref42","article-title":"Recurrent models of visual attention","volume":"27","author":"Mnih","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564709"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3287359"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1167\/jov.21.9.2819"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093524"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-023-04550-8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw53098.2021.00325"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-019-00057-1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"article-title":"Human visual attention prediction boosts learning & performance of autonomous driving agents","year":"2019","author":"Makrigiorgos","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/s23020621"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01128"},{"key":"ref58","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Layer normalization","year":"2016","author":"Ba","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566636"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"}],"event":{"name":"2024 IEEE Intelligent Vehicle Symposium (IV)","start":{"date-parts":[[2024,6,2]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,6,5]]}},"container-title":["2024 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10587320\/10588370\/10588598.pdf?arnumber=10588598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:45:57Z","timestamp":1721281557000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10588598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,2]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iv55156.2024.10588598","relation":{},"subject":[],"published":{"date-parts":[[2024,6,2]]}}}