{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:40:28Z","timestamp":1730270428383,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9982106","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T14:38:15Z","timestamp":1672065495000},"page":"13128-13135","source":"Crossref","is-referenced-by-count":0,"title":["IndoLayout: Leveraging Attention for Extended Indoor Layout Estimation from an RGB Image"],"prefix":"10.1109","author":[{"given":"Shantanu","family":"Singh","sequence":"first","affiliation":[{"name":"Robotics Research Center,IIIT,Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaidev","family":"Shriram","sequence":"additional","affiliation":[{"name":"Robotics Research Center,IIIT,Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaantanu","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"Robotics Research Center,IIIT,Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brojeshwar","family":"Bhowmick","sequence":"additional","affiliation":[{"name":"TCS Research,Kolkata,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K. Madhava","family":"Krishna","sequence":"additional","affiliation":[{"name":"Robotics Research Center,IIIT,Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459411"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref12","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636550"},{"key":"ref15","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00252"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2010.5548091"},{"key":"ref36","article-title":"Attentiongan: Unpaired image-to-image translation using attention-guided generative adversarial networks","author":"tang","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref11","article-title":"Polygonal building segmentation by frame field learning","author":"girard","year":"2021","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561058"},{"key":"ref10","article-title":"Learning to map for active semantic goal navigation","author":"georgakis","year":"2022","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref32","article-title":"Learning to look around objects for top-view representations of outdoor scenes","author":"schulter","year":"2018","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989203"},{"key":"ref1","article-title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","volume":"abs 2006 13171","author":"batra","year":"2020","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013848"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref38","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561034"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2008.4795550"},{"key":"ref23","first-page":"1689","article-title":"Monolayout: Amodal scene layout from a single image","author":"mani","year":"2020","journal-title":"Winter Conference on Applications of Computer Vision WACV)"},{"key":"ref45","article-title":"Image parsing with stochastic scene grammar","volume":"24","author":"zhao","year":"2011","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref26","article-title":"Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d","author":"philion","year":"2020","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2014.07.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00348"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891028"},{"key":"ref44","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2019","journal-title":"International Conference on Ma-chine Learning (ICML)"},{"key":"ref21","first-page":"3413","article-title":"Rent3d: Floor-plan priors for monocular layout estimation","author":"liu","year":"2015","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01528"},{"key":"ref28","article-title":"Habitat-matterport 3d dataset (HM3d): 1000 large-scale 3d environments for embodied AI","volume":"35","author":"ramakrishnan","year":"2021","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref8","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref7","article-title":"On the relationship between self-attention and convolutional layers","author":"cordonnier","year":"2019","journal-title":"International Con-ference on Learning Representations (ICLR)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"ref5","article-title":"Learning to explore using active neural slam","author":"chaplot","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561790"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09982106.pdf?arnumber=9982106","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T17:52:34Z","timestamp":1701280354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9982106\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9982106","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}