{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:25:04Z","timestamp":1772907904025,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62233013"],"award-info":[{"award-number":["62233013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073245"],"award-info":[{"award-number":["62073245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tcsvt.2023.3326373","type":"journal-article","created":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T18:08:58Z","timestamp":1697825338000},"page":"4143-4158","source":"Crossref","is-referenced-by-count":10,"title":["Learning Depth Representation From RGB-D Videos by Time-Aware Contrastive Pre-Training"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2166-4450","authenticated-orcid":false,"given":"Zongtao","family":"He","sequence":"first","affiliation":[{"name":"Robotics and Artificial Intelligence Laboratory (RAIL), Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1368-0300","authenticated-orcid":false,"given":"Liuyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Laboratory (RAIL), Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1176-3735","authenticated-orcid":false,"given":"Ronghao","family":"Dang","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Laboratory (RAIL), Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8225-5426","authenticated-orcid":false,"given":"Shu","family":"Li","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Laboratory (RAIL), Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3304-1584","authenticated-orcid":false,"given":"Qingqing","family":"Yan","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Laboratory (RAIL), Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7543-0855","authenticated-orcid":false,"given":"Chengju","family":"Liu","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Laboratory (RAIL), Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5644-1188","authenticated-orcid":false,"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[{"name":"Robotics and Artificial Intelligence Laboratory (RAIL), Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696650"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561560"},{"key":"ref6","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Szot"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref10","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref11","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref12","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lan"},{"issue":"8","key":"ref13","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"issue":"1","key":"ref14","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref18","first-page":"1","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tong"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051277"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref22","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref24","article-title":"DIODE: A dense indoor and outdoor DEpth dataset","author":"Vasiljevic","year":"2019","journal-title":"arXiv:1908.00463"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3124956"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/164"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547852"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref35","article-title":"MLANet: Multi-level attention network with sub-instruction for continuous vision-and-language navigation","author":"He","year":"2023","journal-title":"arXiv:2303.01396"},{"key":"ref36","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neur. Inf. Process. Sys.","volume":"33","author":"Brown"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249906"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233554"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"issue":"2","key":"ref45","first-page":"1","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"Weinberger","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","first-page":"1","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume":"29","author":"Sohn","year":"2016","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref47","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref48","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3141051"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207174"},{"key":"ref51","first-page":"1","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ramakrishnan"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.292"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv:1807.06757"},{"key":"ref58","article-title":"ObjectNav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020","journal-title":"arXiv:2006.13171"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref63","volume-title":"Logistic Regression: A Self-Learning Text","volume":"94","author":"Kleinbaum","year":"2002"},{"key":"ref64","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref66","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. NIPS Workshop Deep Learn.","author":"Chung"},{"key":"ref67","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25500"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2836318"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10550083\/10288539.pdf?arnumber=10288539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T17:42:03Z","timestamp":1725385323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10288539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":72,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3326373","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}