{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T21:33:45Z","timestamp":1768944825370,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/cvmi66673.2025.11337662","type":"proceedings-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:52:59Z","timestamp":1768855979000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Spatial Reasoning in Vision-Language Models via Monocular Depth Estimation: A Comparative Study on SpatialBench"],"prefix":"10.1109","author":[{"given":"Karthik Prasad","family":"G","sequence":"first","affiliation":[{"name":"Amrita School of Physical Sciences Coimbatore, Amrita Vishwa Vidyapeetham,Department of Mathematics,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murali Krishna","family":"Panthangi","sequence":"additional","affiliation":[{"name":"Amrita School of Physical Sciences Coimbatore, Amrita Vishwa Vidyapeetham,Department of Mathematics,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4V(ision) System Card","volume-title":"OpenAI","year":"2023"},{"key":"ref2","author":"Liu","year":"2023","journal-title":"Visual instruction tuning"},{"key":"ref3","author":"Bai","year":"2023","journal-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128671"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","author":"Bhat","year":"2023","journal-title":"ZoeDepth: Zero-shot transfer by combining relative and metric depth"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref8","volume-title":"DepthPro: High-Resolution Monoc-ular Depth Estimation","author":"Machine","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.387"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00888"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref14","author":"Armeni","year":"2017","journal-title":"Joint 2d-3d-semantic data for indoor scene understanding"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref16","volume-title":"ModelScope Swift Framework","author":"Community","year":"2024"},{"key":"ref17","author":"Dettmers","year":"2023","journal-title":"QLORA: Efficient finetuning of quantized LLMs"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC48092.2020.ICCMC-000167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3139000"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1400141"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIC.2018.8782363"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100338"}],"event":{"name":"2025 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","location":"Rourkela, India","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,13]]}},"container-title":["2025 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11335417\/11337242\/11337662.pdf?arnumber=11337662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T08:17:04Z","timestamp":1768897024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11337662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cvmi66673.2025.11337662","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}