{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:51:03Z","timestamp":1783439463777,"version":"3.54.6"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2242243"],"award-info":[{"award-number":["2242243"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EFFICACI"},{"DOI":"10.13039\/100009171","name":"Natural Resources Conservation Service","doi-asserted-by":"publisher","award":["NR233A750004G044"],"award-info":[{"award-number":["NR233A750004G044"]}],"id":[{"id":"10.13039\/100009171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3463648","type":"journal-article","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:21:43Z","timestamp":1727976103000},"page":"11491-11506","source":"Crossref","is-referenced-by-count":12,"title":["Optical Flow as Spatial-Temporal Attention Learners"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8046-3045","authenticated-orcid":false,"given":"Yawen","family":"Lu","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8145-3436","authenticated-orcid":false,"given":"Cheng","family":"Han","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7570-5756","authenticated-orcid":false,"given":"Qifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta AI, New York City, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7033-3690","authenticated-orcid":false,"given":"Heng","family":"Fan","sequence":"additional","affiliation":[{"name":"University of North Texas, Denton, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2493-1366","authenticated-orcid":false,"given":"Zhaodan","family":"Kong","sequence":"additional","affiliation":[{"name":"University of California, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6995-4775","authenticated-orcid":false,"given":"Dongfang","family":"Liu","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6705-3535","authenticated-orcid":false,"given":"Yingjie","family":"Chen","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01732"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_43"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00030"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00110"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref6","first-page":"15220","article-title":"Displacement-invariant matching cost learning for accurate optical flow estimation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_30"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","first-page":"12826","article-title":"Learning equivariant segmentation with instance-unique querying","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref10","article-title":"Visual recognition with deep nearest centroids","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00631"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5194\/isprsannals-II-3-W5-427-2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1993.378214"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000045324.43199.43"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0644-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_46"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01708"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"ref35","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.63"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_41"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0806-0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00373"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126381"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0404-0"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814146"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/123"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00826"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_37"},{"key":"ref47","first-page":"281","article-title":"SF-Net: Learning scene flow from RGB-D images with CNNs","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Qiao","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00062"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506286"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_44"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_14"},{"key":"ref53","article-title":"Uniform masking: Enabling mae pre-training for pyramid-based vision transformers with locality","author":"Li","year":"2022"},{"key":"ref54","first-page":"7793","article-title":"Softsort: A continuous relaxation for the argsort operator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Prillo"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00620"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00936"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01632"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01063"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01033"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20083"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00870"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.10"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790293"},{"key":"ref66","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref68","first-page":"7838","article-title":"Neural scene flow prior","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref69","article-title":"Virtual kitti 2","author":"Cabon","year":"2020"},{"key":"ref70","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_43"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2930258"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00742"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00271"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_32"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00827"},{"key":"ref79","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref80","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_42"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00938"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00201"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2884280"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2963380"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10746266\/10705000-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10705000.pdf?arnumber=10705000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:55:27Z","timestamp":1732665327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10705000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":89,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3463648","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":[[2024,12]]}}}