{"id":"https://openalex.org/W4402772609","doi":"https://doi.org/10.1109/cvpr52733.2024.00379","title":"Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation","display_name":"Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402772609","doi":"https://doi.org/10.1109/cvpr52733.2024.00379"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","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/A5115596727","display_name":"Yuan Wang","orcid":"https://orcid.org/0009-0009-8509-6809"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Wang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101887041","display_name":"Rui Sun","orcid":"https://orcid.org/0000-0002-8009-4240"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Sun","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046327635","display_name":"Naisong Luo","orcid":"https://orcid.org/0000-0002-1488-3081"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naisong Luo","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101708528","display_name":"Yuwen Pan","orcid":"https://orcid.org/0000-0003-2219-0717"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwen Pan","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648981","display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0622,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92795722,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3952","last_page":"3963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9860000014305115,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9860000014305115,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9706000089645386,"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/computer-science","display_name":"Computer science","score":0.7450721263885498},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.7327364087104797},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6242241859436035},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6006109714508057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5975452661514282},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5894705653190613},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.569182276725769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5602051615715027},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5196489095687866},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4916074872016907},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36468297243118286},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3620896339416504},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16720232367515564},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07699957489967346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450721263885498},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7327364087104797},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6242241859436035},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6006109714508057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5975452661514282},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5894705653190613},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.569182276725769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5602051615715027},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5196489095687866},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4916074872016907},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36468297243118286},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3620896339416504},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16720232367515564},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07699957489967346},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5295720946","display_name":null,"funder_award_id":"2018166","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G5629680007","display_name":null,"funder_award_id":"JCKY2021130B016","funder_id":"https://openalex.org/F4320335833","funder_display_name":"National Defense Basic Scientific Research Program of China"},{"id":"https://openalex.org/G6545572955","display_name":null,"funder_award_id":"12150007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335833","display_name":"National Defense Basic Scientific Research Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W2220552745","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Open-vocabulary":[0],"semantic":[1],"segmentation":[2],"(OVS)":[3],"aims":[4],"to":[5,43,60],"segment":[6],"images":[7],"of":[8,67,172],"arbitrary":[9],"categories":[10],"specified":[11],"by":[12,91,166],"class":[13],"labels":[14],"or":[15,26],"captions.":[16],"However,":[17],"most":[18],"previous":[19,163],"best-performing":[20],"methods,":[21,29],"whether":[22],"pixel":[23],"grouping":[24],"methods":[25,165],"region":[27,89,103],"recognition":[28],"suffer":[30],"from":[31,64],"false":[32,62],"matches":[33,63],"between":[34,47],"image":[35],"features":[36,50,97,104,120],"and":[37,51,70,98],"category":[38],"labels.":[39],"We":[40],"attribute":[41],"this":[42,55],"the":[44,48,65,117,134,139,144],"natural":[45],"gap":[46],"textual":[49],"visual":[52,83],"features.":[53],"In":[54],"work,":[56],"we":[57],"rethink":[58],"how":[59],"mitigate":[61],"perspective":[66],"image-to-image":[68],"matching":[69,76,100,136],"propose":[71],"a":[72,170],"novel":[73],"relation-aware":[74,107],"intra-modal":[75,118],"(RIM)":[77],"framework":[78],"for":[79],"OVS":[80],"based":[81,105],"on":[82,106,156,178],"foundation":[84],"models.":[85],"RIM":[86,112,161],"achieves":[87],"robust":[88,150],"classification":[90],"firstly":[92],"constructing":[93],"diverse":[94],"image-modal":[95],"reference":[96,119],"then":[99],"them":[101],"with":[102],"ranking":[108],"distribution.":[109],"The":[110],"proposed":[111],"enjoys":[113],"several":[114],"merits.":[115],"First,":[116],"are":[121],"better":[122],"aligned,":[123],"circumventing":[124],"potential":[125],"ambiguities":[126],"that":[127,160],"may":[128],"arise":[129],"in":[130,143,176],"cross-modal":[131],"matching.":[132],"Second,":[133],"ranking-based":[135],"process":[137],"harnesses":[138],"structure":[140],"information":[141],"implicit":[142],"inter-class":[145],"relationships,":[146],"making":[147],"it":[148],"more":[149,173],"than":[151,174],"comparing":[152],"individually.":[153],"Extensive":[154],"experiments":[155],"three":[157],"benchmarks":[158],"demonstrate":[159],"outperforms":[162],"state-of-the-art":[164],"large":[167],"margins,":[168],"obtaining":[169],"lead":[171],"10%":[175],"mIoU":[177],"PASCAL":[179],"VOC":[180],"benchmark.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}