{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:37Z","timestamp":1778048317967,"version":"3.51.4"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00559","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5766-5775","source":"Crossref","is-referenced-by-count":0,"title":["BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining"],"prefix":"10.1109","author":[{"given":"Ajinkya","family":"Khoche","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerg\u0151 L\u00e1szl\u00f3","family":"Nagy","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maciej","family":"Wozniak","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Gustafsson","sequence":"additional","affiliation":[{"name":"Scania CV AB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patric","family":"Jensfelt","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3298369"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/15326349708807412"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128393"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref8","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1982"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.470"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3675320"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00727"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093358"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01262"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1275808.1276407"},{"key":"ref20","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1944"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01118"},{"key":"ref23","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_5"},{"key":"ref25","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref26","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1685"},{"key":"ref28","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref29","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","volume-title":"International conference on machine learning","author":"Saunshi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref31","article-title":"Gemma 3 technical report","author":"Kamath","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref34","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432168"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3487489"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20183"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref45","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02282"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16464"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492468.pdf?arnumber=11492468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:51Z","timestamp":1778047011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00559","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}