{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:43:32Z","timestamp":1730270612446,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981047","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"518-525","source":"Crossref","is-referenced-by-count":1,"title":["FocusTR: Focusing on Valuable Feature by Multiple Transformers for Fusing Feature Pyramid on Object Detection"],"prefix":"10.1109","author":[{"given":"Bangquan","family":"Xie","sequence":"first","affiliation":[{"name":"School of Civil Engineering and Transportation, South China University of Technology,Guangzhou,China,510641"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"The City College of New York,New York,NY,USA,10031"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongming","family":"Yang","sequence":"additional","affiliation":[{"name":"Clemson University International Center for Automotive Research (CU-ICAR),Department of Automotive Engineering,Greenville,SC,USA,29607"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ailin","family":"Wei","sequence":"additional","affiliation":[{"name":"Clemson University,Department of Bioengineering,Clemson,SC,USA,29631"}],"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,510641"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Clemson University International Center for Automotive Research (CU-ICAR),Department of Automotive Engineering,Greenville,SC,USA,29607"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"524","article-title":"On layer normalization in the transformer architecture","volume-title":"International Conference on Machine Learning","volume":"10","author":"Xiong","year":"2020"},{"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","volume-title":"arXiv:1709.01507 [cs]","author":"Hu","year":"2019"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref8","first-page":"13","author":"Yu","year":"2016","journal-title":"MULTI-SCALE CONTEXT AGGREGATION BY DILATED CONVOLUTIONS"},{"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","author":"Dai","year":"2016","journal-title":"Advances in neural information processing systems"},{"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":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Masked language modeling for proteins via linearly scalable long-context transformers","author":"Choromanski","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00473"},{"key":"ref22","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/IROS.2018.8594049","article-title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","volume-title":"arXiv:1712.02294 [cs]","author":"Ku","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00752"},{"key":"ref27","article-title":"Vpfnet: Voxel-pixel fusion network for multi-class 3d object detection","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00706"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189778"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00337"},{"key":"ref37","article-title":"Multimodal pretraining unmasked: Unifying the vision and language berts","author":"Bugliarello","year":"2020","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981047.pdf?arnumber=9981047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:42:23Z","timestamp":1706766143000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981047","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}