{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:27:22Z","timestamp":1778084842454,"version":"3.51.4"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956415","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1148-1155","source":"Crossref","is-referenced-by-count":8,"title":["MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator"],"prefix":"10.1109","author":[{"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"The University of Hong Kong,Pokfulam,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Qian","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Pokfulam,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Pokfulam,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edmund Y.","family":"Lam","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Pokfulam,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siew-Chong","family":"Tan","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Pokfulam,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngai","family":"Wong","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Pokfulam,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01224"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref31","article-title":"Voxel r-cnn: Towards high performance voxel-based 3d object detection","author":"deng","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref37","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569793"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3079821"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref22","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"qi","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref23","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"qi","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6933"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00202"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.528"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.477"},{"key":"ref40","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00096"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561245"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref15","article-title":"Lifting 2d object locations to 3d by discounting lidar outliers across objects and views","author":"mccraith","year":"2021"},{"key":"ref16","article-title":"3d for free: Crossmodal transfer learning using hd maps","author":"wilson","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3063611"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413805"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"ref3","first-page":"11 621","article-title":"nuscenes: A multi-modal dataset for autonomous driving","author":"caesar","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2926463"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_31"},{"key":"ref49","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00071"},{"key":"ref46","article-title":"Differentiable iou of oriented boxes","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00019"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref41","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956415.pdf?arnumber=9956415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:06:48Z","timestamp":1671480408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956415","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}