{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T01:58:59Z","timestamp":1790474339445,"version":"4.1.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U24A20328"],"award-info":[{"award-number":["U24A20328"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Shenzhen Science and Technology Program","award":["KQTD20240729102207002"],"award-info":[{"award-number":["KQTD20240729102207002"]}]},{"name":"Guangdong S&T Program","award":["2025B0101130003"],"award-info":[{"award-number":["2025B0101130003"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2025A1515011732"],"award-info":[{"award-number":["2025A1515011732"]}]},{"name":"Beijing Natural Science Foundation","award":["4262074"],"award-info":[{"award-number":["4262074"]}]},{"name":"Science and Technology Innovation Program for Distinguished Young Scholars of Shandong Province","award":["2023KJ128"],"award-info":[{"award-number":["2023KJ128"]}]},{"name":"Major Key Project of Pengcheng Laboratory","award":["PCL2025A14-4"],"award-info":[{"award-number":["PCL2025A14-4"]}]},{"name":"Fundamental Research Funds for the Central Universities","award":["HIT.DZJJ.2025048"],"award-info":[{"award-number":["HIT.DZJJ.2025048"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3692302","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:46:23Z","timestamp":1778528783000},"page":"11593-11607","source":"Crossref","is-referenced-by-count":1,"title":["SpaceEra++: A Unified Framework Toward 3D Spatial Reasoning in Video"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5658-5509","authenticated-orcid":false,"given":"Weili","family":"Guan","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3896-170X","authenticated-orcid":false,"given":"Haoyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5764","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5907-3289","authenticated-orcid":false,"given":"Qianlong","family":"Xiang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00994"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688992"},{"key":"ref3","first-page":"4698","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Tian"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312302"},{"key":"ref5","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Driess"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1684"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i15.38244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128671"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref13","article-title":"GPT4scene: Understand 3D scenes from videos with vision-language models","author":"Qi","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/085713-3449"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-short.33"},{"key":"ref16","article-title":"Sphere: Unveiling spatial blind spots in vision-language models through hierarchical evaluation","author":"Zhang","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2198"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688990"},{"key":"ref19","first-page":"4005","article-title":"RoboPoint: A vision-language model for spatial affordance prediction in robotics","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Yuan"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01470"},{"key":"ref21","article-title":"SpatialCoT: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning","author":"Liu","year":"2025"},{"key":"ref22","first-page":"1","article-title":"ARKitScenes: A diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Baruch"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0433"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0658"},{"key":"ref27","first-page":"1","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ramakrishnan"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01886"},{"key":"ref33","article-title":"Point-bind & point-LLM: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following","author":"Guo","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0435"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2444"},{"key":"ref38","article-title":"Improved visual-spatial reasoning via R1-zero-like training","author":"Liao","year":"2025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4532"},{"key":"ref40","article-title":"Spacer: Reinforcing MLLMs in video spatial reasoning","author":"Ouyang","year":"2025"},{"key":"ref41","article-title":"OpenAI O1 system card","author":"Jaech","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.66774\/etc_5001_099"},{"key":"ref44","article-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024"},{"key":"ref45","article-title":"LMM-R1: Empowering 3B LMMs with strong reasoning abilities through two-stage rule-based RL","author":"Peng","year":"2025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/085713-0457"},{"key":"ref47","article-title":"Spartun3D: Situated spatial understanding of 3D world in large language models","author":"Zhang","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4473"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref55","first-page":"1","article-title":"SQA3D: Situated question answering in 3D scenes","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref56","article-title":"GPT-4o system card","author":"Hurst","year":"2024"},{"key":"ref57","article-title":"SpaceVista: All-scale visual spatial reasoning from MM to km","author":"Sun","year":"2025"},{"key":"ref58","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref59","article-title":"Qwen2. 5-Vl technical report","author":"Bai","year":"2025"},{"key":"ref60","article-title":"Qwen3-Vl technical report","author":"Bai","year":"2025"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11515169.pdf?arnumber=11515169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:14:45Z","timestamp":1790266485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11515169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":60,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3692302","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}