乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:34:32Z","timestamp":1732041272793,"version":"3.28.0"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/iccv48922.2021.00179","type":"proceedings-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T22:08:02Z","timestamp":1646086082000},"page":"1749-1759","source":"Crossref","is-referenced-by-count":174,"title":["TransVG: End-to-End Visual Grounding with Transformers"],"prefix":"10.1109","author":[{"given":"Jiajun","family":"Deng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of GIPAS,Hefei,China"}]},{"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Rochester"}]},{"given":"Tianlang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Rochester"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of GIPAS,Hefei,China"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of GIPAS,Hefei,China"}]}],"member":"263","reference":[{"article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","year":"2019","author":"raffel","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"journal-title":"NeurIPS","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","year":"2019","author":"lu","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"ref36","first-page":"4055","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref60","first-page":"69","article-title":"Modeling context in referring expressions","author":"yu","year":"2016","journal-title":"ECCV"},{"key":"ref62","first-page":"528","article-title":"Learning joint spatial-temporal transformations for video inpainting","author":"zeng","year":"2020","journal-title":"ECCV"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.122"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"journal-title":"ICLRE","article-title":"Incorporating bert into neural machine translation","year":"2020","author":"zhu","key":"ref66"},{"journal-title":"ICLRE","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2021","author":"zhu","key":"ref67"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref22","first-page":"17","article-title":"Hand-transformer: Non-autoregressive structured modeling for 3d hand pose estimation","author":"huang","year":"2020","journal-title":"ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref24","first-page":"451","article-title":"Pirc net: Using proposal indexing, relationships and context for phrase grounding","author":"kovvuri","year":"2018","journal-title":"ACCV"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref26","first-page":"121","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"li","year":"2020","journal-title":"ECCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123439"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"article-title":"Tap: Text-aware pre-training for text-vqa and text-caption","year":"2020","author":"yang","key":"ref57"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref10","first-page":"104","article-title":"Uniter: Universal image-text representation learning","author":"chen","year":"2020","journal-title":"ECCV"},{"journal-title":"ICLRE","article-title":"Universal transformers","year":"2018","author":"dehghani","key":"ref11"},{"article-title":"Yolov3: An incremental improvement","year":"2018","author":"redmon","key":"ref40"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00430"},{"journal-title":"ICLRE","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"dosovitskiy","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","article-title":"High-speed tracking with kernelized correlation filters","volume":"37","author":"henriques","year":"2014","journal-title":"TPAMI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"journal-title":"TPAMI","article-title":"Learning to compose and reason with language tree structures for visual grounding","year":"2019","author":"hong","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00438"},{"article-title":"Pre-trained image processing transformer","year":"2020","author":"chen","key":"ref6"},{"key":"ref5","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref8","first-page":"1691","article-title":"Generative pre-training from pixels","author":"chen","year":"2020","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.95"},{"article-title":"Multi-modal 3d object detection in autonomous driving: a survey","year":"2021","author":"wang","key":"ref49"},{"article-title":"Real-time referring expression comprehension by single-stage grounding network","year":"2018","author":"chen","key":"ref9"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","article-title":"Learning two-branch neural networks for image-text matching tasks","volume":"41","author":"wang","year":"2018","journal-title":"TPAMI"},{"journal-title":"NeurIPS","article-title":"Attention is all you need","year":"2017","author":"vaswani","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1150"},{"journal-title":"Vl-bert Pre-training of generic visual-linguistic representations","year":"2020","author":"su","key":"ref43"}],"event":{"name":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2021,10,10]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2021,10,17]]}},"container-title":["2021 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9709627\/9709628\/09710016.pdf?arnumber=9710016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T20:04:01Z","timestamp":1657569841000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9710016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv48922.2021.00179","relation":{},"subject":[],"published":{"date-parts":[[2021,10]]}}}