{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:28:30Z","timestamp":1783438110887,"version":"3.54.6"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ARC DP"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2020.3001940","type":"journal-article","created":{"date-parts":[[2020,6,12]],"date-time":"2020-06-12T20:57:59Z","timestamp":1591995479000},"page":"7035-7049","source":"Crossref","is-referenced-by-count":145,"title":["Structured Knowledge Distillation for Dense Prediction"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2746-8186","authenticated-orcid":false,"given":"Yifan","family":"Liu","sequence":"first","affiliation":[{"name":"University of Adelaide, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changyong","family":"Shu","sequence":"additional","affiliation":[{"name":"Nanjing Institute of Advanced Artificial Intelligence, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Adelaide, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2893630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref6","article-title":"ENet: A deep neural network architecture for real-time semantic segmentation","author":"Paszke","year":"2016","journal-title":"arXiv: Comput. Res. Repository"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794182"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"ref12","first-page":"1","article-title":"Improving fast segmentation with teacher-student learning","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Xie"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995966"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"ref16","article-title":"LightNet: Light-weight networks for semantic image segmentation","author":"Liu","year":"2018"},{"key":"ref17","article-title":"OCNet: Object context network for scene parsing","author":"Yuan","year":"2018","journal-title":"arXiv: Comput. Res. Repository"},{"key":"ref18","article-title":"Distilling the knowledge in a neural network","volume":"1050","author":"Hinton","year":"2015","journal-title":"stat"},{"key":"ref19","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv: Comput. Res. Repository"},{"key":"ref20","volume-title":"Markov Random Field Modeling in Image Analysis","author":"Li","year":"2009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref25","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.348"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref28","article-title":"Speeding up semantic segmentation for autonomous driving","volume-title":"Proc. Workshop Advances Neural Inf. Process. Syst.","author":"Treml"},{"key":"ref29","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1 mb model size","author":"Iandola","year":"2016","journal-title":"arXiv: Comput. Res. Repository"},{"key":"ref30","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv: Comput. Res. Repository"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408828"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_41"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2896963"},{"key":"ref39","first-page":"5683","article-title":"Enforcing geometric constraints of virtual normal for depth prediction","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Wei"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594243"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref42","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref44","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ba"},{"key":"ref45","article-title":"Do deep convolutional nets really need to be deep (or even convolutional)?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Urban"},{"key":"ref46","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93037-4_8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref51","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref52","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras"},{"key":"ref53","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv: Comput. Res. Repository"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.045"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.137"},{"key":"ref57","article-title":"Semantic segmentation using adversarial networks","author":"Luc","year":"2016","journal-title":"Proc. Workshop Advancesin Neural Inf. Process. Syst."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00163"},{"key":"ref59","first-page":"5767","article-title":"Improved training of wasserstein GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gulrajani"},{"key":"ref60","article-title":"Self-attention generative adversarial networks","volume":"1050","author":"Zhang","year":"2018","journal-title":"stat"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref66","first-page":"1175","article-title":"The one hundred layers Tiramisu: Fully convolutional DenseNets for semantic segmentation","volume-title":"Proc. Workshop IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Drozdzal"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1412.7062"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00116"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794220"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref74","article-title":"DSSD: Deconvolutional single shot detector","author":"Fu","year":"2017","journal-title":"arXiv: Comput. Res. Repository"},{"key":"ref75","article-title":"YOLOV3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv: Comput. Res. Repository"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09115859.pdf?arnumber=9115859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:37:57Z","timestamp":1704839877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9115859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":74,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3001940","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":[[2023,6,1]]}}}