{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:40:48Z","timestamp":1779295248071,"version":"3.51.4"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"International Training Program for Outstanding Young Scientific Research Talents in 2019 of Guangdong Provincial Department of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3299190","type":"journal-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T18:31:08Z","timestamp":1690914668000},"page":"4407-4415","source":"Crossref","is-referenced-by-count":9,"title":["MuTrans: Multiple Transformers for Fusing Feature Pyramid on 2D and 3D Object Detection"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4500-8941","authenticated-orcid":false,"given":"Bangquan","family":"Xie","sequence":"first","affiliation":[{"name":"School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3454-6242","authenticated-orcid":false,"given":"Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"Apple, Inc., Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8626-3973","authenticated-orcid":false,"given":"Ailin","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, Clemson University, Clemson, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxiong","family":"Weng","sequence":"additional","affiliation":[{"name":"School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4987-6129","authenticated-orcid":false,"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automotive Engineering, Clemson University International Center for Automotive Research (CU-ICAR), Greenville, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"10524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00320"},{"key":"ref5","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2017","journal-title":"arXiv:1709.01507"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2023.3238524"},{"key":"ref8","first-page":"13","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. ICLR","author":"Yu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6957"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"ref14","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01337"},{"key":"ref18","article-title":"Joint 3D proposal generation and object detection from view aggregation","author":"Ku","year":"2017","journal-title":"arXiv:1712.02294"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00752"},{"key":"ref20","article-title":"VPFNet: Voxel-pixel fusion network for multi-class 3D object detection","author":"Wang","year":"2021","journal-title":"arXiv:2111.00966"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref22","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref23","article-title":"Masked language modeling for proteins via linearly scalable long-context transformers","author":"Choromanski","year":"2020","journal-title":"arXiv:2006.03555"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref25","article-title":"BoxeR: Box-attention for 2D and 3D transformers","author":"Nguyen","year":"2021","journal-title":"arXiv:2111.13087"},{"key":"ref26","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00706"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00534"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_5"},{"key":"ref38","article-title":"VPFNet: Improving 3D object detection with virtual point based LiDAR and stereo data fusion","author":"Zhu","year":"2021","journal-title":"arXiv:2111.14382"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00337"},{"key":"ref40","article-title":"Multimodal pretraining unmasked: A meta-analysis and a unified framework of vision-and-language BERTs","author":"Bugliarello","year":"2020","journal-title":"arXiv:2011.15124"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref44","article-title":"LargeKernel3D: Scaling up kernels in 3D sparse CNNs","author":"Chen","year":"2022","journal-title":"arXiv:2206.10555"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"ref46","article-title":"BEVFusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation","author":"Liu","year":"2022","journal-title":"arXiv:2205.13542"},{"key":"ref47","article-title":"DeepInteraction: 3D object detection via modality interaction","author":"Yang","year":"2022","journal-title":"arXiv:2208.11112"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10198476.pdf?arnumber=10198476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T16:33:03Z","timestamp":1709310783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10198476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3299190","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}