{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T21:39:13Z","timestamp":1782423553954,"version":"3.54.5"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T00:00:00Z","timestamp":1654387200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T00:00:00Z","timestamp":1654387200000},"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":[[2022,6,5]]},"DOI":"10.1109\/iv51971.2022.9827084","type":"proceedings-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T19:33:28Z","timestamp":1658259208000},"page":"895-902","source":"Crossref","is-referenced-by-count":40,"title":["Is attention to bounding boxes all you need for pedestrian action prediction?"],"prefix":"10.1109","author":[{"given":"Lina","family":"Achaji","sequence":"first","affiliation":[{"name":"Stellantis Group, Technical center of Velizy,France,78140"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Moreau","sequence":"additional","affiliation":[{"name":"Stellantis Group, Technical center of Velizy,France,78140"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thibault","family":"Fouqueray","sequence":"additional","affiliation":[{"name":"Stellantis Group, Technical center of Velizy,France,78140"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francois","family":"Aioun","sequence":"additional","affiliation":[{"name":"Stellantis Group, Technical center of Velizy,France,78140"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francois","family":"Charpillet","sequence":"additional","affiliation":[{"name":"Université de Lorraine,CNRS, Inria, LORIA,Nancy,France,54000"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00441"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref30","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"In Proceedings of the 1st Annual Conference on Robot Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0098628316677643"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3758\/BRM.42.4.1096"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.trf.2009.02.003"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.463"},{"key":"ref10","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv preprint arXiv 1706 03762"},{"key":"ref11","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref12","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412190"},{"key":"ref15","article-title":"Attention, please: A spatio-temporal transformer for 3d human motion prediction","author":"aksan","year":"2020","journal-title":"arXiv preprint arXiv 2004 06774"},{"key":"ref16","article-title":"Pedestrian action anticipation using contextual feature fusion in stacked rnns","author":"rasouli","year":"2020","journal-title":"arXiv preprint arXiv 2005 06138"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/a13120331"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.33"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917228"},{"key":"ref28","article-title":"Joint attention in autonomous driving (jaad)","author":"kotseruba","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"149318","DOI":"10.1109\/ACCESS.2019.2944792","article-title":"Multi-task deep learning for pedestrian detection, action recognition and time to cross prediction","volume":"7","author":"ovidiu pop","year":"2019","journal-title":"IEEE Access"},{"key":"ref27","article-title":"Funnel-transformer: Filtering out sequential redundancy for efficient language processing","author":"dai","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3341105.3373877"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976305"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00130"},{"key":"ref8","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00572"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2015.12.008"},{"key":"ref9","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"ArXiv preprint arXiv 1703 03130"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2008.0319"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00246"},{"key":"ref22","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021","journal-title":"arXiv preprint arXiv 2102 05988"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref24","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv 2010 11419"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s21175694"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"}],"event":{"name":"2022 IEEE Intelligent Vehicles Symposium (IV)","location":"Aachen, Germany","start":{"date-parts":[[2022,6,4]]},"end":{"date-parts":[[2022,6,9]]}},"container-title":["2022 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9826996\/9826997\/09827084.pdf?arnumber=9827084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T20:04:53Z","timestamp":1659989093000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9827084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,5]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iv51971.2022.9827084","relation":{},"subject":[],"published":{"date-parts":[[2022,6,5]]}}}