{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T12:31:40Z","timestamp":1768393900007,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,21]]},"DOI":"10.1109\/mmsp64401.2025.11324169","type":"proceedings-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:55:15Z","timestamp":1768337715000},"page":"24-29","source":"Crossref","is-referenced-by-count":0,"title":["SpatialGeo: Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion"],"prefix":"10.1109","author":[{"given":"Jiajie","family":"Guo","sequence":"first","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}]},{"given":"Qingpeng","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}]},{"given":"Xiaolong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}]},{"given":"Changyong","family":"He","sequence":"additional","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}]},{"given":"Weida","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University,School of Computer Science and Technology,Shanghai,China"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","article-title":"A survey of large language models","volume":"1","author":"Zhao","year":"2023"},{"key":"ref2","first-page":"20482","article-title":"3d-llm: Injecting the 3d world into large language models","volume":"36","author":"Hong","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3428487"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557703"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535389"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref8","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Introducing gpt-4.1 in the api","year":"2025"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref11","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref13","article-title":"When llms step into the 3d world: A survey and meta-analysis of 3d tasks via multi-modal large language models","author":"Ma","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref16","article-title":"Spatialpin: Enhancing spatial reasoning capabilities of vision-language models through prompting and interacting 3d priors","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Ma"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128671"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"ref20","article-title":"Spatialscore: Towards unified evaluation for multimodal spatial understanding","author":"Wu","year":"2025"},{"key":"ref21","first-page":"1","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP61759.2024.10743309"},{"key":"ref23","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref26","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","volume-title":"International conference on machine learning","author":"Yu"},{"key":"ref27","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"}],"event":{"name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","location":"Beijing, China","start":{"date-parts":[[2025,9,21]]},"end":{"date-parts":[[2025,9,23]]}},"container-title":["2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11324077\/11324018\/11324169.pdf?arnumber=11324169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T07:49:10Z","timestamp":1768376950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11324169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/mmsp64401.2025.11324169","relation":{},"subject":[],"published":{"date-parts":[[2025,9,21]]}}}