{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T19:46:34Z","timestamp":1793130394860,"version":"4.5.0"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["U2336213"],"award-info":[{"award-number":["U2336213"]}],"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":["62176251"],"award-info":[{"award-number":["62176251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0680202"],"award-info":[{"award-number":["XDB0680202"]}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484368"],"award-info":[{"award-number":["20230484368"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Suzhou Frontier Technology Research Project","award":["SYG202325"],"award-info":[{"award-number":["SYG202325"]}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3531772","type":"journal-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:43:48Z","timestamp":1737398628000},"page":"1895-1907","source":"Crossref","is-referenced-by-count":6,"title":["Collaboratively Self-Supervised Video Representation Learning for Action Recognition"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8899-3996","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2742-3613","authenticated-orcid":false,"given":"Zhifan","family":"Wan","sequence":"additional","affiliation":[{"name":"Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8788-5811","authenticated-orcid":false,"given":"Lanqing","family":"Hu","sequence":"additional","affiliation":[{"name":"Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuzhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Huawei Digital Technologies Company Ltd., Haidian, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8348-392X","authenticated-orcid":false,"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref6","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/104"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01867"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09333-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17215"},{"key":"ref14","first-page":"1","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. NeurIPS","author":"Feichtenhofer"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00982"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_27"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref20","first-page":"1","article-title":"Multi-modal self-supervision from generalized data transformations","volume-title":"Proc. ICLR","author":"Patrick"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01367"},{"key":"ref22","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv:1411.1784"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref29","first-page":"1","article-title":"Space-time mixing attention for video transformer","volume-title":"Proc. NeurIPS","author":"Bulat"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00377"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2019.00011"},{"key":"ref39","first-page":"1","article-title":"VPN++: Rethinking video-pose embeddings for understanding activities of daily living","volume-title":"Proc. IEEE TPAMI","author":"Das"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"ref41","article-title":"A survey on self-supervised learning: Algorithms, applications, and future trends","author":"Gui","year":"2023","journal-title":"arXiv:2301.05712"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00911"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00789"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref47","first-page":"1","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. NeurIPS","author":"Zhan"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref50","first-page":"1","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/AICAPS57044.2023.10074051"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref56","first-page":"1","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"Proc. ICLR","author":"Villegas"},{"key":"ref57","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021","journal-title":"arXiv:2104.10157"},{"key":"ref58","article-title":"CV-VAE: A compatible video VAE for latent generative video models","author":"Zhao","year":"2024","journal-title":"arXiv:2405.20279"},{"key":"ref59","first-page":"1","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. ICML","author":"Nichol"},{"key":"ref60","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref62","first-page":"1","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NeurIPS","author":"Saharia"},{"key":"ref63","first-page":"1","article-title":"Video diffusion models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref64","first-page":"1","article-title":"Mcvd-masked conditional video diffusion for prediction, generation, and interpolation","volume-title":"Proc. NeurIPS","author":"Voleti"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref67","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv:2209.14792"},{"key":"ref68","article-title":"VideoFusion: Decomposed diffusion models for high-quality video generation","author":"Luo","year":"2023","journal-title":"arXiv:2303.08320"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref70","first-page":"5769","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. NeurIPS","volume":"30","author":"Gulrajani"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00336"},{"key":"ref72","first-page":"1","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. NeurIPS","author":"Han"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00153"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref75","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref76","article-title":"FaceShifter: Towards high fidelity and occlusion aware face swapping","author":"Li","year":"2019","journal-title":"arXiv:1912.13457"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref81","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00629"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_9"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127136"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00784"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"ref90","first-page":"1","article-title":"TCGL: Temporal contrastive graph for self-supervised video representation learning","volume-title":"Proc. IEEE TIP","author":"Liu"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00813"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01026"},{"key":"ref93","article-title":"Inter-intra variant dual representations forSelf-supervised video recognition","author":"Zhang","year":"2021","journal-title":"arXiv:2107.01194"},{"key":"ref94","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2019","journal-title":"arXiv:1911.05722"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/10847948.pdf?arnumber=10847948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:36:22Z","timestamp":1740422182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10847948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3531772","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}