{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:22:46Z","timestamp":1780500166118,"version":"3.54.1"},"reference-count":108,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["IITP-2022-2020-0-01819"],"award-info":[{"award-number":["IITP-2022-2020-0-01819"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ICT Creative Consilience program"},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2021R1C1C1006897"],"award-info":[{"award-number":["NRF-2021R1C1C1006897"]}],"id":[{"id":"10.13039\/501100003725","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":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3218727","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:38:33Z","timestamp":1667525913000},"page":"7174-7194","source":"Crossref","is-referenced-by-count":27,"title":["CATs++: Boosting Cost Aggregation With Convolutions and Transformers"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1199-9596","authenticated-orcid":false,"given":"Seokju","family":"Cho","sequence":"first","affiliation":[{"name":"Korea University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0685-3779","authenticated-orcid":false,"given":"Sunghwan","family":"Hong","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2927-6273","authenticated-orcid":false,"given":"Seungryong","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","first-page":"19545","article-title":"Space-time correspondence as a contrastive random walk","author":"jabri","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref56","article-title":"Self-supervised learning for video correspondence flow","author":"lai","year":"2019"},{"key":"ref59","article-title":"Dual-resolution correspondence networks","author":"li","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01295"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00566"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref45","first-page":"1","article-title":"Cats: Cost aggregation transformers for visual correspondence","author":"cho","year":"2021","journal-title":"Proc 35th Conf Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00334"},{"key":"ref47","first-page":"2414","article-title":"Universal correspondence network","author":"choy","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref42","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref41","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.17"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.206"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00976"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01262"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073683"},{"key":"ref9","article-title":"GAN-supervised dense visual alignment","author":"peebles","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref3","article-title":"Hypercorrelation squeeze for few-shot segmentation","author":"min","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/0600000009"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_43"},{"key":"ref101","article-title":"Few-shot segmentation with optimal transport matching and message flow","author":"liu","year":"2021"},{"key":"ref40","article-title":"Convolutional hough matching networks for robust and efficient visual correspondence","author":"min","year":"2021"},{"key":"ref35","article-title":"Recurrent transformer networks for semantic correspondence","volume":"31","author":"kim","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_22"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_22"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.73"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00238"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_38"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00629"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"ref26","first-page":"14278","article-title":"Gocor: Bringing globally optimized correspondence volumes into your neural network","author":"truong","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00115"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_21"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00349"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00296"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014573219977"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00936"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2724510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.378"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.156"},{"key":"ref98","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.12"},{"key":"ref16","article-title":"Spair-71K: A large-scale benchmark for semantic correspondence","author":"min","year":"2019"},{"key":"ref19","article-title":"Neighbourhood consensus networks","volume":"31","author":"rocco","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00723"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.203"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00210"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref94","article-title":"MLP-Mixer: An all-MLP architecture for vision","author":"tolstikhin","year":"2021","journal-title":"NIPS"},{"key":"ref91","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"NIPS-W"},{"key":"ref90","article-title":"Albumentations: Fast and flexible image augmentations","author":"buslaev","year":"2018"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref88","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref82","first-page":"9895","article-title":"Sparse is enough in scaling transformers","author":"jaszczur","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref81","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","author":"rao","year":"2021"},{"key":"ref84","article-title":"Nyströmformer: A Nystöm-based algorithm for approximating self-attention","author":"xiong","year":"2021","journal-title":"Proc AAAI Conf Artif Intell AAAI Conf Artif Intell"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref80","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"yang","year":"2021"},{"key":"ref79","article-title":"Fastformer: Additive attention can be all you need","author":"wu","year":"2021"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref78","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00897"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref75","article-title":"Token pooling in vision transformers","author":"marin","year":"2021"},{"key":"ref104","article-title":"R2D2: Repeatable and reliable detector and descriptor","author":"revaud","year":"2019"},{"key":"ref74","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2016"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_36"},{"key":"ref77","article-title":"Linformer: Self-attention with linear complexity","author":"wang","year":"2020"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1021\/ci00027a006"},{"key":"ref76","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2020"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00828"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.460"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.253"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"ref70","article-title":"Disk: Learning local features with policy gradient","author":"tyszkiewicz","year":"2020"},{"key":"ref73","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref72","article-title":"Deep learning using rectified linear units (RELU)","author":"agarap","year":"2018"},{"key":"ref68","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020"},{"key":"ref67","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref69","article-title":"TransTrack: Multiple-object tracking with transformer","author":"sun","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1177352.1177355"},{"key":"ref66","article-title":"Training data-efficient image transformers and distillation through attention","author":"touvron","year":"2020"},{"key":"ref65","first-page":"79","article-title":"Few-shot semantic segmentation with prototype learning","author":"dong","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00530"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01189"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09933865.pdf?arnumber=9933865","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:37:01Z","timestamp":1685381821000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9933865\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":108,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3218727","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":[[2023,6,1]]}}}