{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:17:56Z","timestamp":1781619476932,"version":"3.54.5"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515010116"],"award-info":[{"award-number":["2022A1515010116"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Laboratory","award":["2021NL0AB01"],"award-info":[{"award-number":["2021NL0AB01"]}]},{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["9610675"],"award-info":[{"award-number":["9610675"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tits.2024.3467175","type":"journal-article","created":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T17:50:29Z","timestamp":1728323429000},"page":"19469-19481","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal-XAD: Explainable Autonomous Driving Based on Multimodal Environment Descriptions"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3848-7670","authenticated-orcid":false,"given":"Yuchao","family":"Feng","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8752-950X","authenticated-orcid":false,"given":"Zhen","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2868-1920","authenticated-orcid":false,"given":"Wei","family":"Hua","sequence":"additional","affiliation":[{"name":"Zhejiang Laboratory, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7704-0559","authenticated-orcid":false,"given":"Yuxiang","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2994027"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2993926"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967299"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3423392"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3155749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3376534"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3033878"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3225340"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3184990"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3361093"},{"key":"ref12","article-title":"Explaining how a deep neural network trained with end-to-end learning steers a car","author":"Bojarski","year":"2017","journal-title":"arXiv:1704.07911"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"key":"ref14","first-page":"459","article-title":"PlanT: Explainable planning transformers via object-level representations","volume-title":"Proc. Conf. Robotic Learn. (CoRL)","author":"Renz"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561334"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3167702"},{"key":"ref21","article-title":"C-SENN: Contrastive self-explaining neural network","author":"Sawada","year":"2022","journal-title":"arXiv:2206.09575"},{"key":"ref22","first-page":"5338","article-title":"Concept bottleneck models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3229682"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108421"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3273547"},{"key":"ref27","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013","journal-title":"arXiv:1312.6034"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3449912"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3374342"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_29"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575779"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575715"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28141"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814050"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294462"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3208377"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref41","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref43","article-title":"FISHING net: Future inference of semantic heatmaps in grids","author":"Hendy","year":"2020","journal-title":"arXiv:2006.09917"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref45","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27880"},{"key":"ref49","first-page":"10421","article-title":"BEVFusion: A simple and robust LiDAR-camera fusion framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02103"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3458594"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3448251"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref58","article-title":"Cognitive accident prediction in driving scenes: A multimodality benchmark","author":"Fang","year":"2022","journal-title":"arXiv:2212.09381"},{"key":"ref59","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref62","article-title":"DriveLM: Driving with graph visual question answering","author":"Sima","year":"2023","journal-title":"arXiv:2312.14150"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2926463"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref69","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294422"},{"key":"ref71","article-title":"DriveDreamer: Towards Real-world-driven world models for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv:2309.09777"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3398357"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00803"},{"key":"ref74","article-title":"PSI: A pedestrian behavior dataset for socially intelligent autonomous car","author":"Chen","year":"2021","journal-title":"arXiv:2112.02604"},{"key":"ref75","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref76","article-title":"Backbones-review: Feature extraction networks for deep learning and deep reinforcement learning approaches","author":"Elharrouss","year":"2022","journal-title":"arXiv:2206.08016"},{"key":"ref77","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706. 05587"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10769775\/10706985.pdf?arnumber=10706985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:55:23Z","timestamp":1733885723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10706985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":77,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3467175","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}