{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T13:17:47Z","timestamp":1769087867882,"version":"3.49.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339286","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Breaking the 2D Dependency: What Limits 3D-Only Open-Vocabulary Scene Understanding"],"prefix":"10.1109","author":[{"given":"Domenico","family":"D'Orsi","sequence":"first","affiliation":[{"name":"University of Pisa,Dept. of Computer Engineering,Italy"}]},{"given":"Fabio","family":"Carrara","sequence":"additional","affiliation":[{"name":"CNR-ISTI,Pisa,Italy"}]},{"given":"Fabrizio","family":"Falchi","sequence":"additional","affiliation":[{"name":"CNR-ISTI,Pisa,Italy"}]},{"given":"Nicola","family":"Tonellotto","sequence":"additional","affiliation":[{"name":"University of Pisa,Dept. of Computer Engineering,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00085"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.066"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref5","article-title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","author":"Takmaz","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_16"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"issue":"4","key":"ref9","doi-asserted-by":"crossref","DOI":"10.1145\/3592433","article-title":"3d gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Transactions on Graphics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref15","article-title":"Pointnext: Revisiting pointnet ++ with improved training and scaling strategies","author":"Qian","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref16","first-page":"28223","article-title":"Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining","volume-title":"International Conference on Machine Learning","author":"Qi","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3142077"},{"key":"ref19","first-page":"35799","article-title":"Objaverse-xl: A uni-verse of 10m+ 3d objects","volume":"36","author":"Deitke","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"27061","article-title":"Point-m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02085"},{"key":"ref22","volume-title":"Talking to dino: Bridging self-supervised vision backbones with language for open-vocabulary segmentation","author":"Barsellotti","year":"2024"},{"key":"ref23","first-page":"67960","article-title":"Dit-3d: Exploring plain diffusion transformers for 3d shape generation","volume":"36","author":"Mo","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00614"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339286.pdf?arnumber=11339286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:07:05Z","timestamp":1769029625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339286","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}