{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T06:21:32Z","timestamp":1789626092512,"version":"build-2803163510"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"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":[],"published-print":{"date-parts":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897187","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:27:24Z","timestamp":1667510844000},"page":"3873-3877","source":"Crossref","is-referenced-by-count":53,"title":["Depthformer: Multiscale Vision Transformer for Monocular Depth Estimation with Global Local Information Fusion"],"prefix":"10.1109","author":[{"given":"Ashutosh","family":"Agarwal","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Delhi"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chetan","family":"Arora","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Delhi"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Depthmap Prediction From A Single Image Using A Multi-scale Deep network","volume-title":"NIPS 2014","author":"Eigen"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref3","article-title":"From Big To small: Multi-scale Local Planar Guidance For Monocular Depth Estimation","author":"Lee"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/98"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.238"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_14"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","article-title":"SegFormer: Simple and Efficient Design For Semantic Segmentation With Transformers","volume-title":"NIPS 2021","author":"Xie"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00061","article-title":"Pyramid Vision Transformer: A Versatile Back-bone For Dense Prediction Without Convolutions","volume-title":"ICCV 2021","author":"Wang"},{"key":"ref13","article-title":"An Image Is Worth 16x16 Words: Transformers For Image Recognition At Scale","volume-title":"ICLR 2021","author":"Dosovitskiy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","article-title":"Twins: Revisiting The Design Of Spatial Attention In Vision Transformers","volume-title":"NIPS 2021","author":"Chu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref25","article-title":"Decoupled Weight Decay Regularization","volume-title":"ICML 2019","author":"Loshchilov"},{"key":"ref26","article-title":"Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates","author":"Smith","journal-title":"CoRR."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","location":"Bordeaux, France","start":{"date-parts":[[2022,10,16]]},"end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897187.pdf?arnumber=9897187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:17:47Z","timestamp":1705958267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897187","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}