{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T19:18:45Z","timestamp":1787167125795,"version":"build-2736575974"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Ubiquitous Data Enabling Key Lab","award":["ZDSYS20220527171406015"],"award-info":[{"award-number":["ZDSYS20220527171406015"]}]},{"name":"Tsinghua Shenzhen International Graduate School-Shenzhen Pengrui Endowed Professor-Ship Scheme of Shenzhen Pengrui Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3698366","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:58:29Z","timestamp":1780603109000},"page":"6041-6054","source":"Crossref","is-referenced-by-count":1,"title":["Embodied Spatial Affordance: Spatial-Aware Affordance Learning for Embodied Navigation and Manipulation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4209-6695","authenticated-orcid":false,"given":"Xiaoshuai","family":"Hao","sequence":"first","affiliation":[{"name":"Xiaomi EV, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1657-256X","authenticated-orcid":false,"given":"Yingbo","family":"Tang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Xiaomi EV, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3641-1429","authenticated-orcid":false,"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Cardiff University, Cardiff, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"University of Sheffield, Sheffield, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0597-4512","authenticated-orcid":false,"given":"Wenbo","family":"Ding","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5241-0069","authenticated-orcid":false,"given":"Xiao-Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Ubiquitous Data Enabling Key Laboratory, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3393716"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3324595"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3298638"},{"key":"ref4","article-title":"Evaluating GPT-4o\u2019s embodied intelligence: A comprehensive empirical study","author":"Wu","year":"2025","journal-title":"TechRxiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3512380"},{"key":"ref6","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Driess"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00168"},{"key":"ref8","article-title":"RoboBrain 2.0 technical report","volume-title":"arXiv:2507.02029","author":"Cao","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"ref10","article-title":"Gemini robotics: Bringing AI into the physical world","author":"Abeyruwan","year":"2025","journal-title":"arXiv:2503.20020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758313"},{"key":"ref12","article-title":"MIMO-embodied: X-embodied foundation model technical report","volume-title":"arXiv:2511.16518","author":"Hao","year":"2025"},{"key":"ref13","article-title":"Is your VLM sky-ready? A comprehensive spatial intelligence benchmark for UAV navigation","author":"Zhang","year":"2025","journal-title":"arXiv:2511.13269"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.638"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3554559"},{"key":"ref17","article-title":"NavA\u00b3: Understanding any instruction, navigating anywhere, finding anything","author":"Zhang","year":"2025","journal-title":"arXiv:2508.04598"},{"key":"ref18","first-page":"3157","article-title":"Robotic control via embodied chain-of-thought reasoning","volume-title":"Proc. Conf. Robot Learn.","author":"Micha\u0142"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11245995"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3459800"},{"key":"ref21","first-page":"4005","article-title":"RoboPoint: A vision-language model for spatial affordance prediction in robotics","volume-title":"Proc. Conf. Robot Learn.","author":"Yuan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01470"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206484"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/124"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01642-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01988"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00657"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00182"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01351"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128671"},{"key":"ref38","article-title":"SpatialCoT: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning","author":"Liu","year":"2025","journal-title":"arXiv:2501.10074"},{"key":"ref39","first-page":"143297","article-title":"Reinforcing spatial reasoning in vision-language models with interwoven thinking and visual drawing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref40","article-title":"MetaSpatial: Reinforcing 3D spatial reasoning in VLMs for the metaverse","author":"Pan","year":"2025","journal-title":"arXiv:2503.18470"},{"key":"ref41","article-title":"Embodied-r1: Reinforced embodied reasoning for general robotic manipulation","author":"Yuan","year":"2025","journal-title":"arXiv:2508.13998"},{"key":"ref42","article-title":"ST4 VLA: Spatially guided training for vision-language-action models","author":"Ye","year":"2026","journal-title":"arXiv:2602.10109"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01253"},{"key":"ref44","volume-title":"GPT-4o","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref47","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017","journal-title":"arXiv:1712.05474"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref49","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref51","first-page":"28085","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Ravi"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref53","volume-title":"Qwen2.5-vl","author":"Team","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"ref55","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref56","volume-title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","year":"2024"},{"key":"ref57","volume-title":"Gemini 2.5 Flash","year":"2025"},{"key":"ref58","volume-title":"Gemini 2.5 Pro","author":"Gemini Team","year":"2025"},{"key":"ref59","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11551826.pdf?arnumber=11551826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:03:15Z","timestamp":1781154195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11551826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3698366","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}