{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:13:15Z","timestamp":1780762395708,"version":"3.54.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802239","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"4957-4964","source":"Crossref","is-referenced-by-count":18,"title":["SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images"],"prefix":"10.1109","author":[{"given":"Pardis","family":"Taghavi","sequence":"first","affiliation":[{"name":"Texas A&M University,Department of Mechanical Engineering,College Station,TX,USA,77840"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reza","family":"Langari","sequence":"additional","affiliation":[{"name":"Texas A&M University,Department of Mechanical Engineering,College Station,TX,USA,77840"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaurav","family":"Pandey","sequence":"additional","affiliation":[{"name":"Texas A&M University,Department of Engineering Technology & Industrial Distribution,College Station,TX,USA,77840"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref2","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"International conference on machine learning","author":"Arjovsky"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102967"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106669"},{"key":"ref11","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume":"27","author":"Eigen","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00487"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref20","article-title":"Multi-task learning as multi-objective opti-mization","volume":"31","author":"Sener","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500504"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref24","first-page":"794","article-title":"Grad-norm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.69"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01098"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref29","article-title":"Taskprompter: Spatial-channel multi-task prompting for dense scene understanding","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ye"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","article-title":"Improved training of wasserstein gans","volume":"30","author":"Gulrajani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072883"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01578"},{"key":"ref35","article-title":"Openmixup: Open mixup toolbox and benchmark for visual representation learning","author":"Li","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00073"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00051"},{"key":"ref38","first-page":"1908","article-title":"Unsupervised monocular depth learning in dynamic scenes","volume-title":"Conference on Robot Learning","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_14"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00482"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"ref42","article-title":"Zero-shot metric depth with a field-of-view conditioned diffusion model","author":"Saxena","year":"2023"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462433"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01551"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00236"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01557"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_30"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802239.pdf?arnumber=10802239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:06Z","timestamp":1735196406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802239","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}