{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:32:32Z","timestamp":1753889552814,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448295","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3320-3324","source":"Crossref","is-referenced-by-count":1,"title":["Language-Driven Open-Vocabulary 3D Semantic Segmentation with Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"Yuting","family":"Wu","sequence":"first","affiliation":[{"name":"SouthWest University,College of Computer and Information Science,Chongqing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian-Feng","family":"Han","sequence":"additional","affiliation":[{"name":"SouthWest University,College of Computer and Information Science,Chongqing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqiang","family":"Xiao","sequence":"additional","affiliation":[{"name":"SouthWest University,College of Computer and Information Science,Chongqing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01572"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"article-title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","year":"2023","author":"Yang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref9","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Jia"},{"journal-title":"Florence: A new foundation model for computer vision","year":"2021","author":"Yuan","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00836"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"article-title":"Regionplc: Regional point-language contrastive learning for open-world 3d scene understanding","year":"2023","author":"Yang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref17"},{"article-title":"Fitnets: Hints for thin deep nets","year":"2015","author":"Romero","key":"ref18"},{"journal-title":"Open-scene: 3d scene understanding with open vocabularies","year":"2022","author":"Peng","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"article-title":"Language-driven semantic segmentation","volume-title":"International Conference on Learning Representations","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00107"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093545"},{"key":"ref24","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe"},{"key":"ref25","article-title":"Rectified linear units improve restricted boltzmann machines","author":"Nair","year":"2010","journal-title":"Icml"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448295.pdf?arnumber=10448295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:51:48Z","timestamp":1722660708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448295","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}