{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T14:46:21Z","timestamp":1780584381522,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00247","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2510-2519","source":"Crossref","is-referenced-by-count":1,"title":["Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention"],"prefix":"10.1109","author":[{"given":"Junhao","family":"Xing","sequence":"first","affiliation":[{"name":"The University of Osaka"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryohei","family":"Miyakawa","sequence":"additional","affiliation":[{"name":"The University of Osaka"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Osaka"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinpeng","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Osaka"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Risa","family":"Shinoda","sequence":"additional","affiliation":[{"name":"The University of Osaka"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroaki","family":"Santo","sequence":"additional","affiliation":[{"name":"The University of Osaka"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yosuke","family":"Toda","sequence":"additional","affiliation":[{"name":"Phytometrics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fumio","family":"Okura","sequence":"additional","affiliation":[{"name":"The University of Osaka"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Achanta","year":"2010","journal-title":"SLIC superpixels"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92659-5_37"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.34133\/plantphenomics.0202"},{"key":"ref5","first-page":"419","article-title":"Open-vocabulary SAM: Segment and recognize twenty-thousand classes interactively","volume-title":"Proceedings of European Conference on Computer Vision (ECCV)","author":"Haobo"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.34133\/plantphenomics.0158"},{"key":"ref8","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Ilya"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/rob.22122"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00362"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial datasets with noise","volume-title":"Proceedings of International Conference on Knowledge Discovery and Data Mining (KDD)","author":"Martin"},{"key":"ref18","first-page":"70","article-title":"Color image segmentation","volume-title":"Proceedings of IEEE International Conference on Image Processing (ICIP)","volume":"3","author":"Meyer"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.10.013"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref21","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Ravi"},{"key":"ref22","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160918"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_19"},{"key":"ref25","article-title":"Hierarchical open-vocabulary universal image segmentation","volume-title":"Proceedings of Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346760"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3419548"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00302"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3147462"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2024.100515"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref32","article-title":"Segment everything everywhere all at once","volume-title":"Proceedings of Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Zou"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492452.pdf?arnumber=11492452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:42Z","timestamp":1778047002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00247","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}