{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T06:35:10Z","timestamp":1777962910960,"version":"3.51.4"},"reference-count":33,"publisher":"Informa UK Limited","issue":"18","funder":[{"DOI":"10.13039\/501100001691","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["23K03478"],"award-info":[{"award-number":["23K03478"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020963","name":"JST Moonshot","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003051","name":"NEDO","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003051","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2024,9,16]]},"DOI":"10.1080\/01691864.2024.2381812","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T18:11:19Z","timestamp":1722535879000},"page":"1277-1286","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":1,"title":["Co-scale cross-attentional transformer for rearrangement target detection"],"prefix":"10.1080","volume":"38","author":[{"given":"Haruka","family":"Matsuo","sequence":"first","affiliation":[{"name":"Faculty of Science and Technology, Keio University, Yokohama, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shintaro","family":"Ishikawa","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, Keio University, Yokohama, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0261-0510","authenticated-orcid":false,"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, Keio University, Yokohama, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2024,8]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40648-019-0129-y"},{"key":"e_1_3_3_3_1","unstructured":"Batra D Chang A Chernova S et\u00a0al. Rearrangement: a challenge for embodied AI. arXiv preprint. 2020. arXiv:2011.01975."},{"key":"e_1_3_3_4_1","doi-asserted-by":"crossref","unstructured":"Sakurada K Shibuya M Wang W. Weakly supervised silhouette-based semantic scene change detection. In: ICRA; 2020. p.\u00a06861\u20136867.","DOI":"10.1109\/ICRA40945.2020.9196985"},{"key":"e_1_3_3_5_1","doi-asserted-by":"crossref","unstructured":"Chen S Yang K Stiefelhagen R. DR-TANet: dynamic receptive temporal attention network for street scene change detection. In: IV; 2021. p. 502\u2013509.\u00a0Nagoya Japan.","DOI":"10.1109\/IV48863.2021.9575362"},{"key":"e_1_3_3_6_1","doi-asserted-by":"crossref","unstructured":"Xu W Xu Y Chang T et\u00a0al. Co-scale conv-attentional image transformers. In: ICCV; 2021. p.\u00a09981\u20139990.","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"e_1_3_3_7_1","doi-asserted-by":"crossref","unstructured":"Varghese A Gubbi J Ramaswamy A et al. ChangeNet: a deep learning architecture for visual change detection. In: ECCV Workshops; 2018.\u00a0Munich Germany.","DOI":"10.1007\/978-3-030-11012-3_10"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030484"},{"key":"e_1_3_3_9_1","first-page":"1","article-title":"A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection","volume":"60","author":"Shi Q","year":"2022","unstructured":"Shi Q, Liu M, Li S, et\u00a0al. A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection. TGRS. 2022;60:1\u201316.","journal-title":"TGRS"},{"key":"e_1_3_3_10_1","doi-asserted-by":"crossref","unstructured":"Park JM Kim UH Lee SH et al. Dual task learning by leveraging both dense correspondence and mis-correspondence for robust change detection with imperfect matches. In: CVPR; 2022. p. 13749\u201313759.\u00a0New Orleans LA USA.","DOI":"10.1109\/CVPR52688.2022.01338"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101688"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs10030471"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3011913"},{"key":"e_1_3_3_14_1","doi-asserted-by":"crossref","unstructured":"Bandara C Patel V. A transformer-based siamese network for change detection. In: IGARSS; 2022. p. 207\u2013210.\u00a0Kuala Lumpur Malaysia.","DOI":"10.1109\/IGARSS46834.2022.9883686"},{"key":"e_1_3_3_15_1","unstructured":"Yan T Wan Z Zhang P. Fully transformer network for change detection of remote sensing images. In: ACCV; 2022. p. 1691\u20131708.\u00a0Macau China."},{"key":"e_1_3_3_16_1","first-page":"1","article-title":"Remote\u00a0sensing\u00a0image\u00a0changedetection with\u00a0transformers","volume":"60","author":"Chen H","year":"2021","unstructured":"Chen H, Qi Z, Shi Z. Remote\u00a0sensing\u00a0image\u00a0changedetection with\u00a0transformers. GRS. 2021;60:1\u201314.","journal-title":"GRS"},{"key":"e_1_3_3_17_1","doi-asserted-by":"crossref","unstructured":"Liu Z Lin Y Cao Y et\u00a0al. Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV; 2021. p.\u00a010012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_3_18_1","doi-asserted-by":"crossref","unstructured":"Sakurada K. Okatani T. Change detection from a street image pair using CNN features and superpixel segmentation. In: BMVC; 2015.\u00a0Swansea UK.","DOI":"10.5244\/C.29.61"},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9734-5"},{"key":"e_1_3_3_20_1","doi-asserted-by":"crossref","unstructured":"Park JM Jang JH Yoo SM et\u00a0al. ChangeSim: towards end-to-end online scene change detection in industrial indoor environments. In: IROS; 2021. p.\u00a08578\u20138585.","DOI":"10.1109\/IROS51168.2021.9636350"},{"key":"e_1_3_3_21_1","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S et al. Deep residual learning for image recognition. In: CVPR; 2016. p. 770\u2013778.\u00a0Las Vegas NV USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_22_1","doi-asserted-by":"crossref","unstructured":"Krontiris A Shome R Dobson A et al. Rearranging similar objects with a manipulator using pebble graphs. In: IEEE-RAS International Conference on Humanoid Robots; 2014. p. 1081\u20131087.\u00a0Madrid Spain.","DOI":"10.1109\/HUMANOIDS.2014.7041499"},{"key":"e_1_3_3_23_1","doi-asserted-by":"crossref","unstructured":"King J Ranganeni V Srinivasa S. Unobservable Monte Carlo planning for nonprehensile rearrangement tasks. In: ICRA; 2017. p. 4681\u20134688.\u00a0Singapore.","DOI":"10.1109\/ICRA.2017.7989544"},{"key":"e_1_3_3_24_1","doi-asserted-by":"crossref","unstructured":"Shome R Bekris KE. Synchronized multi-arm rearrangement guided by mode graphs with capacity constraints. In: The Fourteenth Workshop on the Algorithmic Foundations of Robotics; 2021. p. 243\u2013260.\u00a0Oulu Finland.","DOI":"10.1007\/978-3-030-66723-8_15"},{"key":"e_1_3_3_25_1","doi-asserted-by":"crossref","unstructured":"Weihs L Deitke M Kembhavi A et\u00a0al. Visual room rearrangement. In: CVPR; 2021. p.\u00a05922\u20135931.","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"e_1_3_3_26_1","unstructured":"Trabucco B Sigurdsson G Piramuthu R et al. A simple approach for visual room rearrangement: 3D mapping and semantic search. In: ICLR; 2023.\u00a0Kigali Rwanda."},{"key":"e_1_3_3_27_1","doi-asserted-by":"crossref","unstructured":"Matsubara T Otsuki S Wada Y et al. Shared transformer encoder with mask-based 3D model estimation for container mass estimation. In: ICASSP; 2022. p. 9142\u20139146.\u00a0Singapore.","DOI":"10.1109\/ICASSP43922.2022.9747110"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2021.1913446"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.08.002"},{"key":"e_1_3_3_30_1","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A Fischer P Ilg E et al. Flownet: learning optical flow with convolutional networks. In: ICCV; 2015. p. 2758\u20132766.\u00a0Santiago Chile.","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_3_3_31_1","doi-asserted-by":"crossref","unstructured":"Rahman A Wang Y. Optimizing intersection-over-union in deep neural networks for image segmentation. In: ISVC; 2016. p. 234\u2013244.\u00a0Las Vegas NV USA.","DOI":"10.1007\/978-3-319-50835-1_22"},{"key":"e_1_3_3_32_1","doi-asserted-by":"crossref","unstructured":"Milletari F Navab N Ahmadi SA. V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV; 2016. p. 565\u2013571.\u00a0Stanford CA USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_3_3_33_1","unstructured":"Kolve E Mottaghi R Han W et\u00a0al. AI2-THOR: an interactive 3D environment for visual AI. arXiv preprint. 2017; arXiv:1712.05474."},{"key":"e_1_3_3_34_1","doi-asserted-by":"crossref","unstructured":"Kirillov A Mintun E Ravi N et al. Segment Anything. In: ICCV; 2023. p. 4015\u20134026.\u00a0Paris France.","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2024.2381812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:38:32Z","timestamp":1729186712000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2024.2381812"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":33,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2024,9,16]]}},"alternative-id":["10.1080\/01691864.2024.2381812"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2024.2381812","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2024-01-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-11","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}