{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:41:44Z","timestamp":1782333704343,"version":"3.54.5"},"reference-count":95,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62272128"],"award-info":[{"award-number":["62272128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013156","name":"Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology","doi-asserted-by":"publisher","award":["2025r029"],"award-info":[{"award-number":["2025r029"]}],"id":[{"id":"10.13039\/501100013156","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01719","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18498-18509","source":"Crossref","is-referenced-by-count":2,"title":["MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment"],"prefix":"10.1109","author":[{"given":"Yachun","family":"Mi","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weicheng","family":"Meng","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaofeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Hui","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaohui","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2019.2957670"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3088505"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02597-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref5","first-page":"5612","article-title":"No-reference video quality assessment using natural spatiotemporal scene statistics","volume":"29","author":"Veera","year":"2020","journal-title":"IEEE TIP"},{"key":"ref6","article-title":"An image is worth 16 times 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112055"},{"key":"ref8","article-title":"Hungry hungry hippos: Towards language modeling with state space models","author":"Fu","journal-title":"ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3130754"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3467124"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680624"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3077642"},{"key":"ref14","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu","year":"2021","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2251643"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503160"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3301213"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01798"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351311"},{"key":"ref31","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2023.1137006"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413845"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2017.2685941"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref40","first-page":"75","article-title":"Mamband: Selective state space modeling for multi-dimensional data","volume-title":"ECCV","author":"Li","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR49039.2020.00015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547849"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240643"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28170"},{"key":"ref46","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref49","article-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2023","journal-title":"ICLR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448422"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680930"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2012.2227726"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2015.2502725"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00225"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2562513"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_1"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"issue":"3","key":"ref60","first-page":"1352","article-title":"Blind prediction of natural video quality","volume":"23","author":"Michele","year":"2014","journal-title":"IEEE TIP"},{"key":"ref61","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2018.2869673"},{"key":"ref63","article-title":"Simplified state space layers for sequence modeling","author":"Smith","journal-title":"ICLR"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref65","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"ICML","author":"Tan","year":"2019"},{"key":"ref66","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","volume-title":"ICML","author":"Tan","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00618"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01323"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00267"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3319332"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249741"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00070"},{"key":"ref78","article-title":"Towards robust text-prompted semantic criterion for in-the-wild video quality assessment","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611737"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680916"},{"key":"ref82","first-page":"54015","article-title":"Q-align: teaching 1 mms for visual scoring via discrete text-defined levels","author":"Wu","year":"2024","journal-title":"ICML"},{"key":"ref83","first-page":"491","article-title":"Noreference video quality assessment via feature learning","volume-title":"ICIP","author":"Xu","year":"2014"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475486"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2355716"},{"key":"ref86","first-page":"1098","article-title":"Unsupervised feature learning framework for no-reference image quality assessment","volume-title":"CVPR","author":"Ye","year":"2012"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01380"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803395"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00423"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00174"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00137"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3207148"},{"key":"ref94","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00556"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444133.pdf?arnumber=11444133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:50Z","timestamp":1777611590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01719","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}