{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:48Z","timestamp":1779948108304,"version":"3.53.1"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00161","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1691-1701","source":"Crossref","is-referenced-by-count":0,"title":["GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes"],"prefix":"10.1109","author":[{"given":"Huajian","family":"Zeng","sequence":"first","affiliation":[{"name":"TU München"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhishek","family":"Saroha","sequence":"additional","affiliation":[{"name":"TU München"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Cremers","sequence":"additional","affiliation":[{"name":"TU München"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"TU München"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Interaction networks for learning about objects, relations and physics","author":"Battaglia","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8414"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811889"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","article-title":"Introduction to inverse kinematics with jacobian transpose, pseudoinverse and damped least squares methods","volume-title":"IEEE Journal of Robotics and Automation","author":"Samuel","year":"2004"},{"key":"ref6","article-title":"Sam 3: Segment anything with concepts","author":"Carion","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01709"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1327"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00830"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00454-002-2886-1"},{"key":"ref13","article-title":"Project aria: A new tool for egocentric multi-modal ai research","author":"Engel","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01284"},{"key":"ref15","first-page":"67","volume":"1","author":"James","year":"1977","journal-title":"The theory of affordances. Perceiving, acting, and knowing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2027"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460730"},{"key":"ref22","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref23","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980280"},{"key":"ref26","article-title":"Yolov11: An overview of the key architectural enhancements","author":"Khanam","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref29","article-title":"Worldmodelbench: Judging video generation models as world models","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_4"},{"key":"ref31","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"Lotter","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0070"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref34","article-title":"OpenAI","year":"2024","journal-title":"Sora: Creating video from text"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"ref36","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Neurips"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00271"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02226"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00104"},{"key":"ref40","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref41","first-page":"9277","article-title":"Deep hough voting for 3d object detection in point clouds","volume-title":"proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Charles"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152817"},{"key":"ref44","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"Convolutional 1stm network: A machine learning approach for precipitation nowcasting","author":"Shi","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref46","first-page":"785","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1"},{"key":"ref48","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref50","article-title":"Visual interaction networks: Learning a physics simulator from video","author":"Watters","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Scaling autoregressive video models","author":"Weissenborn","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00235"},{"key":"ref53","article-title":"Learning affordances from interactive exploration using an object-level map","author":"Wulkop","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"Critiques of world models","author":"Xing","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00627"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01145"},{"key":"ref58","article-title":"Learning object bounding boxes for 3d instance segmentation on point clouds","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_39"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref65","article-title":"Is sora a world simulator? a comprehensive survey on general world models and beyond","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533304.pdf?arnumber=11533304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:45Z","timestamp":1779944565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00161","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}