{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:01:46Z","timestamp":1777568506048,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.01671","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"18180-18189","source":"Crossref","is-referenced-by-count":14,"title":["UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstruction"],"prefix":"10.1109","author":[{"given":"Zhenwei","family":"Zhu","sequence":"first","affiliation":[{"name":"Macau University of Science and Technology"}]},{"given":"Liying","family":"Yang","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology"}]},{"given":"Chaohao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology"}]},{"given":"Yanyan","family":"Liang","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref2","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume-title":"ICML","volume":"2","author":"Bertasius"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548395"},{"key":"ref4","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9365-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00298"},{"key":"ref11","article-title":"Learning a multi-view stereo machine","volume":"30","author":"Kar","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3506733"},{"key":"ref14","article-title":"Decoupled spatial-temporal transformer for video inpainting","author":"Liu","year":"2021"},{"key":"ref15","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01523-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/S096249291700006X"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00410"},{"key":"ref20","article-title":"3d-retr: End-to-end single and multi-view 3d reconstruction with transformers","volume-title":"British Machine Vision Conference","author":"Shi"},{"key":"ref21","first-page":"87","article-title":"Improved adversarial systems for 3d object generation and reconstruction","volume-title":"Conference on Robot Learning","author":"Smith"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.308"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00314"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00352"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26319-4_13"},{"key":"ref27","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","author":"Touvron"},{"key":"ref28","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00567"},{"key":"ref30","article-title":"Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling","volume":"29","author":"Wu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00278"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01347-6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_31"},{"key":"ref36","article-title":"Legoformer: Transformers for block-by-block multi-view 3d reconstruction","author":"Yagubbayli","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01217-w"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00317"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108295"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01952"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109674"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Paris, France","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10378126.pdf?arnumber=10378126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:50:22Z","timestamp":1705542622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10378126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.01671","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}