{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T01:15:34Z","timestamp":1792286134568,"version":"4.4.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3676710","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:07:33Z","timestamp":1774296453000},"page":"9129-9141","source":"Crossref","is-referenced-by-count":3,"title":["Out-of-Sight Embodied Agents: Multimodal Tracking, Sensor Fusion, and Trajectory Forecasting"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9645-3255","authenticated-orcid":false,"given":"Haichao","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5857-4179","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5098-2853","authenticated-orcid":false,"given":"Yun","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.376"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1198\/016214503000125"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SECON55815.2022.9918171"},{"key":"ref4","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-4005(01)01001-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3072135"},{"key":"ref7","article-title":"Latent variable sequential set transformers for joint multi-agent motion prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Girgis","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412190"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2006.882988"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN54338.2022.00024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3466904"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614119"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2550005"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413984"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3070543"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809712"},{"key":"ref20","article-title":"DALL.E: Creating images from text","author":"Ramesh","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636577"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21236\/ada164453"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489734"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990542"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00084"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_39"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3274777"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01798"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02392"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108552"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3590487"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3368931"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00929"},{"key":"ref35","article-title":"Dense video understanding with gated residual tokenization","author":"Zhang","year":"2025"},{"key":"ref36","article-title":"VQToken: Neural discrete token representation learning for extreme token reduction in video large language models","volume-title":"Proc. 49th Annu. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2025"},{"key":"ref37","article-title":"LinkedOut: Linking world knowledge representation out of video LLM for next-generation video recommendation","author":"Zhang","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611936"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01402"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274686"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1017\/S0373463316000485"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00862"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11450494.pdf?arnumber=11450494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:45:14Z","timestamp":1783453514000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11450494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":42,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3676710","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":[[2026,8]]}}}