{"id":"https://openalex.org/W7160233455","doi":"https://doi.org/10.1109/wacv61042.2026.00247","title":"Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention","display_name":"Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160233455","doi":"https://doi.org/10.1109/wacv61042.2026.00247"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135355957","display_name":"Junhao Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhao Xing","raw_affiliation_strings":["The University of Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072676299","display_name":"Ryohei Miyakawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryohei Miyakawa","raw_affiliation_strings":["The University of Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135413426","display_name":"Yang Yang","orcid":"https://orcid.org/0009-0001-6579-2577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["The University of Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135340769","display_name":"Xinpeng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinpeng Liu","raw_affiliation_strings":["The University of Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081677717","display_name":"Risa Shinoda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Risa Shinoda","raw_affiliation_strings":["The University of Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023086235","display_name":"Hiroaki Santo","orcid":"https://orcid.org/0000-0003-2891-5993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroaki Santo","raw_affiliation_strings":["The University of Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054108408","display_name":"Yosuke Toda","orcid":"https://orcid.org/0000-0003-2421-4743"},"institutions":[{"id":"https://openalex.org/I4210134374","display_name":"Flometrics (United States)","ror":"https://ror.org/04n3ta263","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yosuke Toda","raw_affiliation_strings":["Phytometrics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phytometrics","institution_ids":["https://openalex.org/I4210134374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135383014","display_name":"Fumio Okura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fumio Okura","raw_affiliation_strings":["The University of Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50424679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2510","last_page":"2519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.33480000495910645,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.33480000495910645,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10616","display_name":"Smart Agriculture and AI","score":0.19189999997615814,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.065700002014637,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6495000123977661},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.42910000681877136},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.352400004863739},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32989999651908875}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6495000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6144999861717224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5748000144958496},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.352400004863739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3046000003814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2705000042915344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2264784471","https://openalex.org/W2963150697","https://openalex.org/W2963659353","https://openalex.org/W2999219213","https://openalex.org/W3138516171","https://openalex.org/W4210433707","https://openalex.org/W4212992032","https://openalex.org/W4285541224","https://openalex.org/W4293363567","https://openalex.org/W4306391965","https://openalex.org/W4383109089","https://openalex.org/W4386075561","https://openalex.org/W4390204218","https://openalex.org/W4390874575","https://openalex.org/W4392357656","https://openalex.org/W4399140857","https://openalex.org/W4400062053","https://openalex.org/W4401008913","https://openalex.org/W4402716258","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"segmentation":[1,38,62,74],"models":[2],"achieve":[3],"reasonable":[4],"leaf":[5,77],"instance":[6],"extraction":[7],"from":[8,67],"top-view":[9,68],"crop":[10],"images":[11],"without":[12,91],"training":[13,43],"(i.e.,":[14],"zero-shot).":[15],"However,":[16],"segmenting":[17],"entire":[18],"plant":[19,65,89,99],"individuals":[20,66,90],"with":[21,97],"each":[22],"consisting":[23],"of":[24],"multiple":[25,98],"overlapping":[26],"leaves":[27],"remains":[28],"challenging.":[29],"This":[30],"problem":[31],"is":[32],"referred":[33],"to":[34,87],"as":[35],"a":[36,60,72,80],"hierarchical":[37],"task,":[39],"typically":[40],"requiring":[41],"annotated":[42],"datasets":[44,96],"that":[45,107],"are":[46,123],"often":[47],"species-specific":[48],"and":[49,79,103,114],"require":[50],"significant":[51],"human":[52],"labor.":[53],"To":[54],"address":[55],"this,":[56],"we":[57],"introduce":[58],"ZeroPlantSeg,":[59],"zero-shot":[61,112],"for":[63],"rosette-shaped":[64],"images.":[69],"We":[70],"integrate":[71],"foundation":[73],"model,":[75,82],"extracting":[76],"instances,":[78],"vision-language":[81],"reasoning":[83],"about":[84],"plants\u2019":[85],"structures":[86],"extract":[88],"additional":[92],"training.":[93],"Evaluations":[94],"on":[95],"species,":[100],"growth":[101],"stages,":[102],"shooting":[104],"environments":[105],"demonstrate":[106],"our":[108],"method":[109],"surpasses":[110],"existing":[111],"methods":[113],"achieves":[115],"better":[116],"cross-domain":[117],"performance":[118],"than":[119],"supervised":[120],"methods.":[121],"Implementations":[122],"available":[124],"at":[125],"https://github.com/JunhaoXing/ZeroPlantSeg.":[126]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}