{"id":"https://openalex.org/W4304084012","doi":"https://doi.org/10.1145/3503161.3548316","title":"Visual Grounding in Remote Sensing Images","display_name":"Visual Grounding in Remote Sensing Images","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304084012","doi":"https://doi.org/10.1145/3503161.3548316"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548316","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548316","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5033224121","display_name":"Yuxi Sun","orcid":"https://orcid.org/0000-0002-3040-5880"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxi Sun","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086115549","display_name":"Shanshan Feng","orcid":"https://orcid.org/0000-0002-6161-9232"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Feng","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063318300","display_name":"Xutao Li","orcid":"https://orcid.org/0000-0003-1894-984X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xutao Li","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002523892","display_name":"Yunming Ye","orcid":"https://orcid.org/0000-0002-1807-8581"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunming Ye","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700900","display_name":"Jian Kang","orcid":"https://orcid.org/0000-0001-6284-3044"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Kang","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104114058","display_name":"Xu Huang","orcid":"https://orcid.org/0009-0002-5027-5742"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Huang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"404","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8055287003517151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6260395646095276},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6182919144630432},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4616504907608032},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.41074636578559875},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10822251439094543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055287003517151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6260395646095276},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6182919144630432},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4616504907608032},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.41074636578559875},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10822251439094543},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548316","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548316","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2899355980","display_name":null,"funder_award_id":"62101371","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2048009189","https://openalex.org/W2130578993","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2558809543","https://openalex.org/W2561529111","https://openalex.org/W2760103357","https://openalex.org/W2770129969","https://openalex.org/W2799263800","https://openalex.org/W2907143950","https://openalex.org/W2962749812","https://openalex.org/W2962764817","https://openalex.org/W2963109634","https://openalex.org/W2963735856","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2964979676","https://openalex.org/W2979826702","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3006154882","https://openalex.org/W3012111773","https://openalex.org/W3034952258","https://openalex.org/W3035268124","https://openalex.org/W3093314701","https://openalex.org/W3093355642","https://openalex.org/W3098351727","https://openalex.org/W3110435696","https://openalex.org/W3172066753","https://openalex.org/W3173364567","https://openalex.org/W3174004334","https://openalex.org/W3177271687","https://openalex.org/W3179868941","https://openalex.org/W4206362849","https://openalex.org/W4313229413"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W2772917594","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Ground":[0],"object":[1],"retrieval":[2],"from":[3],"a":[4,18,50,113,122,134,154,158],"large-scale":[5,87,169],"remote":[6,25,76,83,170],"sensing":[7,26,77,84,171],"image":[8,48,137,163,187],"is":[9,145,165,180],"very":[10],"important":[11],"for":[12,189],"lots":[13],"of":[14,21,39,94,133],"applications.":[15],"We":[16,192],"present":[17],"novel":[19],"problem":[20],"visual":[22,115,190],"grounding":[23,29,116],"in":[24,46,58],"images.":[27,78],"Visual":[28],"aims":[30],"to":[31,147,167,182,200],"locate":[32],"the":[33,37,40,59,90,129,184,194,201,212,216],"particular":[34],"objects":[35,96],"(in":[36],"form":[38],"bounding":[41],"box":[42],"or":[43],"segmentation":[44],"mask)":[45],"an":[47],"by":[49,197],"natural":[51,72,81],"language":[52,135,143],"expression.":[53],"The":[54,100,142,162,177],"task":[55],"already":[56],"exists":[57],"computer":[60],"vision":[61],"community.":[62],"However,":[63],"existing":[64,101],"benchmark":[65],"datasets":[66],"and":[67,89,120,139,152,186],"methods":[68,203,214],"mainly":[69],"focus":[70],"on":[71,204,215],"images":[73,85],"rather":[74],"than":[75],"Compared":[79],"with":[80,105,173],"images,":[82],"contain":[86],"scenes":[88,172],"geographical":[91],"spatial":[92],"information":[93],"ground":[95],"(e.g.,":[97],"longitude,":[98],"latitude).":[99],"method":[102,131,196,210],"cannot":[103],"deal":[104],"these":[106],"challenges.":[107],"In":[108,127],"this":[109],"paper,":[110],"we":[111],"collect":[112],"new":[114,123],"dataset,":[117],"called":[118],"RSVG,":[119],"design":[121],"method,":[124],"namely":[125],"GeoVG.":[126],"particular,":[128],"proposed":[130,195,217],"consists":[132],"encoder,":[136,138],"fusion":[140,178],"module.":[141],"encoder":[144,164],"used":[146,181],"learn":[148,168],"numerical":[149],"geospatial":[150,159],"relations":[151],"represent":[153],"complex":[155],"expression":[156],"as":[157],"relation":[160],"graph.":[161],"applied":[166],"adaptive":[174],"region":[175],"attention.":[176],"module":[179],"fuse":[183],"text":[185],"feature":[188],"grounding.":[191],"evaluate":[193],"comparing":[198],"it":[199],"state-of-the-art":[202],"RSVG.":[205],"Experiments":[206],"show":[207],"that":[208],"our":[209],"outperforms":[211],"previous":[213],"datasets.":[218],"https://sunyuxi.github.io/publication/GeoVG":[219]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}