{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:56:09Z","timestamp":1783439769968,"version":"3.54.6"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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","award":["62376222"],"award-info":[{"award-number":["62376222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00492","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5177-5187","source":"Crossref","is-referenced-by-count":3,"title":["AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations"],"prefix":"10.1109","author":[{"given":"Junli","family":"Liu","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qizhi","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwen","family":"Tang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiting","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"TeleAI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref3","article-title":"Freegaussian: Guidance-free controllable 3d gaussian splats with flow derivatives","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3867"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00179"},{"key":"ref9","author":"Devlin","year":"2019","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref14","article-title":"Openfly: A versatile toolchain and large-scale benchmark for aerial vision-language navigation","author":"Gao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf6991"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01410"},{"key":"ref18","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","author":"Hildebrandt","year":"2020","journal-title":"Scene graph reasoning for visual question answering"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00888"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3423663"},{"key":"ref23","author":"Harold Li","year":"2019","journal-title":"Visualbert: A simple and performant baseline for vision and language"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref32","author":"Achiam","year":"2024","journal-title":"Gpt-4 technical report"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284847"},{"key":"ref34","article-title":"Livescene: Language embedding interactive radiance fields for physical scene rendering and control","author":"Qu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0393"},{"key":"ref36","first-page":"19584","article-title":"Implicit eventrgbd neural slam","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Qu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IUS54386.2022.9958621"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28323"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_26"},{"key":"ref43","author":"Tang","year":"2025","journal-title":"Exploring the potential of encoderfree architectures in 3d lmms"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref46","author":"Xiao","year":"2023","journal-title":"Florence-2: Advancing a unified representation for a variety of vision tasks"},{"key":"ref47","author":"Xu","year":"2023","journal-title":"mplug-2: A modularized multi-modal foundation model across text, image and video"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3339661\/mm1"},{"key":"ref52","article-title":"Glipv2: Unifying localization and vision-language understanding","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref54","author":"Zheng","year":"2024","journal-title":"Tracevla: Visual trace prompting enhances spatial-temporal awareness for generalist robotic policies"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443501.pdf?arnumber=11443501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:27Z","timestamp":1777612887000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00492","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}