{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:13:48Z","timestamp":1774419228287,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890721","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["ES-NeRF: Enhancing Segmentation in NeRF with CLIP"],"prefix":"10.1109","author":[{"given":"Chong","family":"Zhao","sequence":"first","affiliation":[{"name":"Engineering Quality Education Center of Undergraduate School, Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bi","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"ref7","article-title":"Decomposing nerf for editing via feature field distillation","author":"Kobayashi","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445897"},{"key":"ref11","article-title":"Segment anything in 3d with nerfs","author":"Cen","year":"2023","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Learning transferable visual models from natural language supervision","volume-title":"CoRR","author":"Radford","year":"2021"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW63382.2024.00367","article-title":"Sam-clip: Merging vision foundation models towards semantic and spatial understanding","author":"Wang","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.00973","article-title":"Locate then segment: A strong pipeline for referring image segmentation","volume-title":"CoRR","author":"Jing","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106153"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref20","article-title":"Attention is all you need","volume-title":"CoRR","author":"Vaswani","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01261-8_20","article-title":"Bisenet: Bilateral segmentation network for real-time semantic segmentation","volume-title":"CoRR","author":"Yu","year":"2018"},{"key":"ref23","article-title":"Bisenet V2: bilateral network with guided aggregation for real-time semantic segmentation","volume-title":"CoRR","author":"Yu","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322980"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1145\/2964284.2967274","article-title":"Unitbox: An advanced object detection network","volume-title":"Proceedings of the 24th ACM international conference on Multimedia","author":"Yu"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1145\/3596711.3596774","article-title":"Grabcut: Interactive foreground extraction using iterated graph cuts","volume-title":"Seminal Graphics Papers: Pushing the Boundaries, Volume 2","author":"Rother","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00180"},{"key":"ref31","article-title":"Decomposing nerf for editing via feature field distillation","author":"Kobayashi","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01980"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890721.pdf?arnumber=10890721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:41Z","timestamp":1774416101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890721","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}