{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:59:54Z","timestamp":1775815194015,"version":"3.50.1"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341519","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"7651-7658","source":"Crossref","is-referenced-by-count":11,"title":["Superpixel Transformers for Efficient Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Alex Zihao","family":"Zhu","sequence":"first","affiliation":[{"name":"Waymo LLC"}]},{"given":"Jieru","family":"Mei","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}]},{"given":"Siyuan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Hang","family":"Yan","sequence":"additional","affiliation":[{"name":"Waymo LLC"}]},{"given":"Yukun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Research"}]},{"given":"Henrik","family":"Kretzschmar","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","author":"Chen","year":"2021","journal-title":"Transunet: Transformers make strong encoders for medical image segmentation"},{"key":"ref4","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","volume-title":"ICLR","author":"Chen","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2699184"},{"key":"ref6","author":"Chen","year":"2017","journal-title":"Rethinking atrous convolution for semantic image segmentation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref9","article-title":"Mask2former for video instance segmentation","volume-title":"CVPR","author":"Cheng","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref12","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"NeurIPS","author":"Cheng","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/34.1000236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref16","article-title":"Autoaugment: Learning augmentation policies from data","volume-title":"CVPR","author":"Cubuk","year":"2019"},{"key":"ref17","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459175"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_36"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","article-title":"Carreira-Perpin\u00e1n. Multiscale conditional random fields for image labeling","volume-title":"CVPR","author":"He","year":"2004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_22"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma","year":"2015"},{"key":"ref26","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","volume-title":"NeurIPS","author":"Kr\u00e4henb\u00fchl","year":"2011"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459248"},{"key":"ref28","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume-title":"ICML","author":"Lafferty","year":"2001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref35","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","year":"2019"},{"key":"ref36","article-title":"Stand-alone self-attention in vision models","volume-title":"NeurIPS","author":"Ramachandran","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref40","article-title":"Attention is all you need","volume-title":"NeurIPS","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref44","article-title":"Solov2: Dynamic and fast instance segmentation","volume-title":"NeurIPS","author":"Wang","year":"2020"},{"key":"ref45","author":"Weber","year":"2021","journal-title":"Deeplab2: A tensorflow library for deep labeling"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref47","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"NeurIPS","author":"Xie","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00259"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"ref52","article-title":"K-net: Towards unified image segmentation","volume-title":"NeurIPS","author":"Zhang","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00132"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref57","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"ICLR","author":"Zhu","year":"2020"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341519.pdf?arnumber=10341519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:24:25Z","timestamp":1755105865000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341519\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341519","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}