{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:42:37Z","timestamp":1771699357635,"version":"3.50.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tpami.2023.3332407","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:17:21Z","timestamp":1699903041000},"page":"2224-2238","source":"Crossref","is-referenced-by-count":22,"title":["A Study on the Generality of Neural Network Structures for Monocular Depth Estimation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0993-6916","authenticated-orcid":false,"given":"Jinwoo","family":"Bae","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7878-697X","authenticated-orcid":false,"given":"Kyumin","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9776-8101","authenticated-orcid":false,"given":"Sunghoon","family":"Im","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, DGIST, Daegu, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340802"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103701"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00344"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00379"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1458-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00397"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00227"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref18","article-title":"ImagenNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geirhos"},{"key":"ref19","article-title":"Shape or texture: Understanding discriminative features in CNNs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Islam"},{"key":"ref20","article-title":"Are convolutional neural networks or transformers more like human vision?","author":"Tuli","year":"2021","journal-title":"CogSci"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/jocn_a_01544"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/cogs.13009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2014(88)90014-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1959.sp006308"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90014-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-vision-082114-035447"},{"key":"ref27","article-title":"Exploring corruption robustness: Inductive biases in vision transformers and MLP-mixers","author":"Morrison","year":"2021"},{"key":"ref28","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume":"34","author":"Naseer","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2017.08.019"},{"key":"ref30","article-title":"Approximating CNNs with bag-of-local-features models works surprisingly well on imagenet","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brendel"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3015812.3015979"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref34","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00707"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00713"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20103"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.596"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00821"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref47","article-title":"RegionViT: Regional-to-local attention for vision transformers","author":"Chen","year":"2022","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref48","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref50","article-title":"More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity","author":"Liu","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25090"},{"key":"ref52","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith"},{"key":"ref53","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Raghu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/134"},{"key":"ref57","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref59","article-title":"Global-local path networks for monocular depth estimation with vertical cutdepth","author":"Kim","year":"2022"},{"key":"ref60","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref61","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00026"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00092"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref72","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01181"},{"key":"ref74","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref76","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Eigen"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"ref78","article-title":"Self-supervised monocular depth estimation with internal feature fusion","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhou"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"ref81","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref84","article-title":"Texture image analysis and texture classification methods-a review","author":"Armi","year":"2019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_14"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1125-z"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref88","first-page":"795","article-title":"Algorithms for learning kernels based on centered alignment","volume":"13","author":"Cortes","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref89","article-title":"Feature selection via dependence maximization","volume":"120","author":"Song","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018368"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10461350\/10316606.pdf?arnumber=10316606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T18:04:20Z","timestamp":1711130660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10316606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":90,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3332407","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":[[2024,4]]}}}