{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:35Z","timestamp":1778048315789,"version":"3.51.4"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00227","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2295-2305","source":"Crossref","is-referenced-by-count":0,"title":["CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning"],"prefix":"10.1109","author":[{"given":"Zeyuan","family":"Chen","sequence":"first","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyang","family":"Xu","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwen","family":"Xie","sequence":"additional","affiliation":[{"name":"Lambda, Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuowen","family":"Tu","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref4","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref5","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1492"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref11","article-title":"Grounded 3d-llm with referent tokens","author":"Chen","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref13","first-page":"8282","article-title":"Panoptic 3d scene reconstruction from a single rgb image","volume-title":"NeurIPS","volume":"34","author":"Dahnert"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_21"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref17","article-title":"Scene-llm: Extending language model for 3d visual understanding and reasoning","author":"Fu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/info12020092"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.066"},{"key":"ref20","first-page":"20482","article-title":"3d-llm: Injecting the 3d world into large language models","volume":"36","author":"Hong","year":"2023","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Chat-3d v2: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2023"},{"key":"ref22","first-page":"113991","article-title":"Chat-scene: Bridging 3d scene and large language models with object identifiers","volume-title":"NeurIPS","volume":"37","author":"Huang"},{"key":"ref23","first-page":"20413","article-title":"An embodied generalist agent in 3d world","volume-title":"ICML","author":"Huang"},{"key":"ref24","first-page":"15524","article-title":"Mult-iview transformer for 3d visual grounding","volume-title":"CVPR","author":"Huang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref31","article-title":"LLaVA-onevision: Easy visual task transfer","volume-title":"TMLR","author":"Li"},{"key":"ref32","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.91"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103624"},{"key":"ref36","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref37","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref39","article-title":"Sqa3d: Situated question answering in 3d scenes","volume-title":"ICLR","author":"Ma"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01298"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01470"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207665"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"ref44","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.3115\/1073083.1073135","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"ACL","author":"Papineni"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00593"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref48","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.178"},{"key":"ref51","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref52","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Georgiev","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01525"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/504729.504754"},{"key":"ref55","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref56","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.656"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01612"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00849"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref70","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00542"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00841"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00409"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00761"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492360.pdf?arnumber=11492360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:09Z","timestamp":1778046969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00227","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}