{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T12:40:31Z","timestamp":1732711231241,"version":"3.28.2"},"reference-count":91,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"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":[[2024,7,22]]},"DOI":"10.1109\/iccp61108.2024.10644854","type":"proceedings-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T18:44:08Z","timestamp":1724870648000},"page":"1-12","source":"Crossref","is-referenced-by-count":0,"title":["Stereo-Knowledge Distillation from dpMV to Dual Pixels for Light Field Video Reconstruction"],"prefix":"10.1109","author":[{"given":"Aryan","family":"Garg","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Madras"}]},{"given":"Raghav","family":"Mallampali","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Madras"}]},{"given":"Akshat","family":"Joshi","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Madras"}]},{"given":"Shrisudhan","family":"Govindarajan","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Madras"}]},{"given":"Kaushik","family":"Mitra","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Madras"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093558"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00772"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00432"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCP48838.2020.9105278"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00223"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201329"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-11752-2_3","article-title":"High-resolution stereo datasets with subpixel-accurate ground truth","volume-title":"German Conference on Pattern Recognition","author":"Scharstein","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.438","article-title":"A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation","volume-title":"IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Mayer","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"issue":"6","key":"ref14","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","article-title":"Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks","volume":"44","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00987","article-title":"Depth anything: Unleashing the power of large-scale unlabeled data","volume-title":"CVPR","author":"Yang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1145\/3596711.3596759","volume-title":"Light Field Rendering","author":"Levoy","year":"2023"},{"key":"ref19","article-title":"Edge-aware bidirectional diffusion for dense depth estimation from light fields","volume-title":"British Machine Vision Conference","author":"Khan","year":"2021"},{"key":"ref20","article-title":"View-consistent 4D lightfield depth estimation","volume-title":"British Machine Vision Conference","author":"Numair","year":"2020"},{"volume-title":"Light field photography with a hand-held plenoptic camera","year":"2005","author":"Ng","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3355056.3364593"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392485"},{"key":"ref25","first-page":"162","volume-title":"Synthesizing light field video from monocular video","author":"Govindarajan","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417785"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.246"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icpr48806.2021.9411964"},{"key":"ref29","article-title":"Synthesizing a 4d spatio-angular consistent light field from a single image","author":"Ivan","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3366371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00249"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980251"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356528"},{"issue":"1","key":"ref34","doi-asserted-by":"crossref","DOI":"10.3390\/technologies9010002","article-title":"A survey on contrastive self-supervised learning","volume":"9","author":"Jaiswal","year":"2021","journal-title":"Technologies"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-023-09884-2"},{"key":"ref36","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref37","first-page":"402","article-title":"Raft: Recurrent all-pairs field transforms for optical flow","volume-title":"Computer Vision - ECCV 2020: 16th European Conference","author":"Teed"},{"key":"ref38","article-title":"Distilling the knowledge in a neural network","volume":"abs\/1503.02531","author":"Hinton","year":"2015","journal-title":"CoRR"},{"key":"ref39","article-title":"Do deep nets really need to be deep?","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Ba","year":"2014"},{"issue":"6","key":"ref40","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.754"},{"key":"ref45","article-title":"Fitnets: Hints for thin deep nets","volume-title":"3rd International Conference on Learning Representations, ICLR 2015","author":"Romero","year":"2015"},{"volume-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","year":"2017","author":"Zagoruyko","key":"ref46"},{"key":"ref47","article-title":"Contrastive representation distillation","volume-title":"International Conference on Learning Representations","author":"Tian","year":"2020"},{"journal-title":"Training data-efficient image transformers and distillation through attention","year":"2021","author":"Touvron","key":"ref48"},{"key":"ref49","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"International Conference on Learning Representations","author":"Wu","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"journal-title":"Evolving attention with residual convolutions","year":"2021","author":"Wang","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref54","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Xiao","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00342"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299004"},{"key":"ref58","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58452-8_24","article-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Mildenhall","year":"2020"},{"journal-title":"Neural sparse voxel fields","year":"2021","author":"Liu","key":"ref59"},{"journal-title":"Nerf++: Analyzing and improving neural radiance fields","year":"2020","author":"Zhang","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_42"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.178"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_21"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322980"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00247"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417827"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00063"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01603"},{"key":"ref70","first-page":"11037","article-title":"What knowledge gets distilled in knowledge distillation?","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Ojha","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01264"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185576"},{"key":"ref79","first-page":"14663","article-title":"Bridging the gap between vision transformers and convolutional neural networks on small datasets","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Lu","year":"2022"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"journal-title":"Linformer: Self-attention with linear complexity","year":"2020","author":"Wang","key":"ref81"},{"key":"ref82","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","volume":"abs\/2103.03404","author":"Dong","year":"2021","journal-title":"ArXiv"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref84","article-title":"Spatial transformer networks","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Jaderberg","year":"2015"},{"key":"ref85","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32"},{"journal-title":"Decoupled weight decay regularization","year":"2019","author":"Loshchilov","key":"ref86"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"issue":"6","key":"ref88","first-page":"6:1","article-title":"Deeplens: Shallow depth of field from a single image","volume":"37","author":"Lijun","year":"2018","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH Asia)"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073614"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00823"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"event":{"name":"2024 IEEE International Conference on Computational Photography (ICCP)","start":{"date-parts":[[2024,7,22]]},"location":"Lausanne, Switzerland","end":{"date-parts":[[2024,7,24]]}},"container-title":["2024 IEEE International Conference on Computational Photography (ICCP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10644133\/10644222\/10644854.pdf?arnumber=10644854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T11:31:28Z","timestamp":1732707088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10644854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,22]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iccp61108.2024.10644854","relation":{},"subject":[],"published":{"date-parts":[[2024,7,22]]}}}