{"id":"https://openalex.org/W4416011372","doi":"https://doi.org/10.1109/tgrs.2025.3630131","title":"SARCLIP: The First Vision\u2013Language Foundation Model for SAR Image","display_name":"SARCLIP: The First Vision\u2013Language Foundation Model for SAR Image","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416011372","doi":"https://doi.org/10.1109/tgrs.2025.3630131"},"language":null,"primary_location":{"id":"doi:10.1109/tgrs.2025.3630131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3630131","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-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/A5100399559","display_name":"Pengfei Wang","orcid":"https://orcid.org/0000-0002-4218-5467"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wang","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4218-5467","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046722995","display_name":"Zhuhao Lu","orcid":"https://orcid.org/0009-0002-8687-6793"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuhao Lu","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-8687-6793","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087088267","display_name":"Yajun Li","orcid":"https://orcid.org/0000-0002-1500-1829"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajun Li","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1500-1829","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086537869","display_name":"Baogang Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baogang Ding","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ding Zhang","orcid":"https://orcid.org/0009-0004-1346-5090"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Zhang","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-1346-5090","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29648896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7110000252723694,"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":0.7110000252723694,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1624000072479248,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.011699999682605267,"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/upsampling","display_name":"Upsampling","score":0.7080000042915344},{"id":"https://openalex.org/keywords/synthetic-aperture-radar","display_name":"Synthetic aperture radar","score":0.6230000257492065},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5289999842643738},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.45410001277923584},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4374000132083893},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4196999967098236},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4075999855995178},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38019999861717224},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3407000005245209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840399980545044},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7080000042915344},{"id":"https://openalex.org/C87360688","wikidata":"https://www.wikidata.org/wiki/Q740686","display_name":"Synthetic aperture radar","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5898000001907349},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5289999842643738},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48410001397132874},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.45410001277923584},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4075999855995178},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C10929652","wikidata":"https://www.wikidata.org/wiki/Q7279985","display_name":"Radar imaging","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C109094680","wikidata":"https://www.wikidata.org/wiki/Q6060432","display_name":"Inverse synthetic aperture radar","level":4,"score":0.260699987411499},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C181843262","wikidata":"https://www.wikidata.org/wiki/Q640492","display_name":"Digital elevation model","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3630131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3630131","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4287257669","display_name":null,"funder_award_id":"62371192","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2928007866","https://openalex.org/W2997464028","https://openalex.org/W3012162230","https://openalex.org/W3038948729","https://openalex.org/W3193997983","https://openalex.org/W3196551448","https://openalex.org/W3200733355","https://openalex.org/W4200381407","https://openalex.org/W4221044012","https://openalex.org/W4224911357","https://openalex.org/W4226089519","https://openalex.org/W4289203581","https://openalex.org/W4309651788","https://openalex.org/W4312219282","https://openalex.org/W4312272363","https://openalex.org/W4312761738","https://openalex.org/W4312795296","https://openalex.org/W4312910992","https://openalex.org/W4313121711","https://openalex.org/W4313156423","https://openalex.org/W4380142917","https://openalex.org/W4382677398","https://openalex.org/W4385573131","https://openalex.org/W4386065386","https://openalex.org/W4386076385","https://openalex.org/W4386076402","https://openalex.org/W4386076509","https://openalex.org/W4386952228","https://openalex.org/W4387402974","https://openalex.org/W4390872394","https://openalex.org/W4390873321","https://openalex.org/W4390874575","https://openalex.org/W4394938913","https://openalex.org/W4402473945","https://openalex.org/W4402713111","https://openalex.org/W4402727764"],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"models":[1,24],"have":[2],"achieved":[3,210],"remarkable":[4],"breakthroughs":[5],"across":[6,204,237],"various":[7,205],"domains,":[8],"with":[9],"the":[10,66,105,113,129,136,201,217,222],"widely":[11],"use":[12],"of":[13,107,121,155,158],"Masked":[14],"Image":[15],"Modeling":[16],"(MIM)":[17],"and":[18,37,53,94,138,169,183],"Self-Supervised":[19],"Learning":[20],"(SSL).":[21],"However,":[22,59],"these":[23,47],"lack":[25,106],"language":[26],"comprehension,":[27],"which":[28,86,117],"limits":[29],"their":[30],"ability":[31],"to":[32,90,103,134,221],"generalize":[33],"in":[34,56,144,234],"downstream":[35,173,239],"tasks":[36],"zero-shot":[38,177,227],"applications.":[39],"The":[40],"CLIP":[41,202,224,231],"(Contrastive":[42],"Language-Image":[43],"Pretraining)":[44],"model":[45,63,81,206],"overcomes":[46],"challenges":[48],"by":[49,142,232],"integrating":[50],"textual":[51,88],"information":[52,139],"performs":[54],"exceptionally":[55],"remote":[57],"sensing.":[58],"no":[60],"such":[61],"multimodal":[62],"exists":[64],"for":[65,84],"SAR":[67,108,146],"(Synthetic":[68],"Aperture":[69],"Radar)":[70],"domain.":[71],"To":[72],"bridge":[73],"this":[74],"gap,":[75],"we":[76,111,148,187],"propose":[77,112,149],"SARCLIP,":[78],"a":[79,151,162,189,211],"vision-language":[80,97,130],"specially":[82],"designed":[83],"SAR,":[85],"leverages":[87],"supervision":[89],"enhance":[91],"visual":[92],"representation":[93],"achieves":[95],"fine-grained":[96],"alignment":[98],"through":[99,161],"modality":[100],"alignment.":[101],"Firstly,":[102],"overcome":[104],"image-text":[109,175],"datasets,":[110],"Detection-to-Caption":[114],"(D2C)":[115],"algorithm,":[116],"transforms":[118],"heterogeneous":[119],"format":[120],"object":[122,184],"detection":[123],"into":[124],"diverse":[125],"captions,":[126],"ultimately":[127],"creating":[128],"dataset,":[131],"MMSAR.":[132],"Additionally,":[133],"address":[135],"distortion":[137],"loss":[140],"caused":[141],"downsampling":[143],"high-resolution":[145],"images,":[147],"AnyReader,":[150],"dynamic":[152],"module":[153],"capable":[154],"processing":[156],"images":[157],"any":[159],"size":[160],"low-resolution":[163],"encoder.":[164],"We":[165],"validate":[166],"SARCLIP\u2019s":[167],"generalization":[168],"performance":[170],"on":[171,216],"five":[172],"tasks:":[174],"retrieval,":[176],"classification,":[178,180,228],"few-shot":[179],"linear":[181],"probing":[182],"counting.":[185],"Especially,":[186],"introduce":[188],"new":[190],"counting":[191],"benchmark,":[192],"SARCount.":[193],"Our":[194],"results":[195],"demonstrate":[196],"that":[197],"SARCLIP":[198,209,229],"consistently":[199],"outperforms":[200],"baseline":[203],"sizes.":[207],"Impressively,":[208],"7.07%":[212],"higher":[213],"average":[214,235],"recall":[215],"retrieval":[218],"task":[219],"compared":[220],"largest":[223],"model.":[225],"In":[226],"surpasses":[230],"7.8%":[233],"accuracy":[236],"three":[238],"datasets.":[240]},"counts_by_year":[],"updated_date":"2025-11-20T23:13:51.555489","created_date":"2025-11-07T00:00:00"}