{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:45:45Z","timestamp":1756309545777,"version":"3.37.3"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010661","name":"EU Horizon 2020 program","doi-asserted-by":"publisher","award":["H2020-ICT-2019-2 871542"],"award-info":[{"award-number":["H2020-ICT-2019-2 871542"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342275","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"1313-1318","source":"Crossref","is-referenced-by-count":9,"title":["Neural Implicit Vision-Language Feature Fields"],"prefix":"10.1109","author":[{"given":"Kenneth","family":"Blomqvist","sequence":"first","affiliation":[{"name":"Swiss Federal Institute of Technology in Zürich,Autonomous Systems Lab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Milano","sequence":"additional","affiliation":[{"name":"Swiss Federal Institute of Technology in Zürich,Autonomous Systems Lab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen Jen","family":"Chung","sequence":"additional","affiliation":[{"name":"School of ITEE, The University of Queensland,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lionel","family":"Ott","sequence":"additional","affiliation":[{"name":"Swiss Federal Institute of Technology in Zürich,Autonomous Systems Lab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Siegwart","sequence":"additional","affiliation":[{"name":"Swiss Federal Institute of Technology in Zürich,Autonomous Systems Lab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00085"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2923960"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3231498"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160800"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref7","article-title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref9","article-title":"Language-driven Semantic Segmentation","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"GLIPv2: Unifying Localization and Vision-Language Understanding","volume-title":"NeurIPS","author":"Zhang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01451"},{"key":"ref12","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref13","article-title":"Perceptual Grouping in Vision-Language Models","author":"Ranasinghe","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Visual Language Maps for Robot Navigation","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","author":"Song","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Open-vocabulary Queryable Scene Representations for Real World Planning","author":"Chen","year":"2022","journal-title":"arxiv preprint"},{"key":"ref18","article-title":"Planning with Large Language Models via Corrective Re-prompting","author":"Raman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Leveraging Large Language Models for Robot 3D Scene Understanding","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","volume-title":"Conference on Robot Learning","author":"Ha","year":"2022"},{"key":"ref21","article-title":"Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following","volume-title":"Conference on Robot Learning","author":"Blukis","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref23","article-title":"Self-supervised 3D Semantic Representation Learning for Vision-and-Language Navigation","author":"Tan","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","author":"Shah","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Find a Way Forward: a Language-Guided Semantic Map Navigator","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","author":"Majumdar","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00677"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00596"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811877"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794371"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560923"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.050"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00743"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref38","article-title":"Baking in the Feature: Accelerating Volumetric Segmentation by Rendering Feature Maps","author":"Blomqvist","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00873"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00296"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00098"},{"key":"ref44","article-title":"Decomposing NeRF for Editing via Feature Field Distillation","volume-title":"NeurIPS","author":"Kobayashi","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00617"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01245"},{"key":"ref51","article-title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","author":"Wang","year":"2021","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342275.pdf?arnumber=10342275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:16:07Z","timestamp":1703031367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342275","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}