{"id":"https://openalex.org/W4322707256","doi":"https://doi.org/10.1109/tgrs.2023.3250471","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","display_name":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4322707256","doi":"https://doi.org/10.1109/tgrs.2023.3250471"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2023.3250471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2023.3250471","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/A5101458421","display_name":"Yang Zhan","orcid":"https://orcid.org/0000-0001-7849-634X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Zhan","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022524675","display_name":"Zhitong Xiong","orcid":"https://orcid.org/0000-0002-3953-585X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhitong Xiong","raw_affiliation_strings":["Chair of Data Science in Earth Observation, Technical University of Munich (TUM), Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Data Science in Earth Observation, Technical University of Munich (TUM), Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100334733","display_name":"Yuan Yuan","orcid":"https://orcid.org/0000-0001-7964-6514"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Yuan","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101458421"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":15.7289,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":{"value":0.99459615,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"61","issue":null,"first_page":"1","last_page":"13"},"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":0.9983999729156494,"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":0.9977999925613403,"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":0.851392388343811},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7290410995483398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.663819432258606},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6405895352363586},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5048021078109741},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.43538710474967957},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41295501589775085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3954530954360962},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3724396824836731},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34636378288269043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.851392388343811},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7290410995483398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.663819432258606},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6405895352363586},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5048021078109741},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.43538710474967957},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41295501589775085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3954530954360962},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3724396824836731},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34636378288269043},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2023.3250471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2023.3250471","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":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1195665351","display_name":null,"funder_award_id":"2020YFB2103900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2210533046","display_name":null,"funder_award_id":"61825603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1536680647","https://openalex.org/W1773149199","https://openalex.org/W1825604117","https://openalex.org/W1970381522","https://openalex.org/W2185175083","https://openalex.org/W2247513039","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2279346661","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2558809543","https://openalex.org/W2561715562","https://openalex.org/W2770129969","https://openalex.org/W2779054585","https://openalex.org/W2896457183","https://openalex.org/W2904910963","https://openalex.org/W2907143950","https://openalex.org/W2946086442","https://openalex.org/W2952524542","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2963150697","https://openalex.org/W2963383024","https://openalex.org/W2963735856","https://openalex.org/W2963914122","https://openalex.org/W2964022527","https://openalex.org/W2964345792","https://openalex.org/W2970603850","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W2992240579","https://openalex.org/W3006154882","https://openalex.org/W3011819854","https://openalex.org/W3012111773","https://openalex.org/W3034764937","https://openalex.org/W3034772468","https://openalex.org/W3034952258","https://openalex.org/W3035026422","https://openalex.org/W3035268124","https://openalex.org/W3093355642","https://openalex.org/W3096609285","https://openalex.org/W3098232790","https://openalex.org/W3098351727","https://openalex.org/W3100245404","https://openalex.org/W3104529101","https://openalex.org/W3110435696","https://openalex.org/W3125237740","https://openalex.org/W3133500032","https://openalex.org/W3163747765","https://openalex.org/W3165084071","https://openalex.org/W3174004334","https://openalex.org/W3179868941","https://openalex.org/W3194015448","https://openalex.org/W3208803664","https://openalex.org/W3213288046","https://openalex.org/W4206111836","https://openalex.org/W4210820868","https://openalex.org/W4214490042","https://openalex.org/W4221145450","https://openalex.org/W4225517085","https://openalex.org/W4225991573","https://openalex.org/W4229439310","https://openalex.org/W4283029876","https://openalex.org/W4289126595","https://openalex.org/W4293428450","https://openalex.org/W4304084012","https://openalex.org/W4305005880","https://openalex.org/W4312351586","https://openalex.org/W4312794139","https://openalex.org/W4313145013","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6753640285","https://openalex.org/W6757135208","https://openalex.org/W6757817989","https://openalex.org/W6797397777","https://openalex.org/W6810258035","https://openalex.org/W6845668075"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"In":[0,232],"this":[1,78,233],"article,":[2],"we":[3,80,104,144],"introduce":[4],"the":[5,19,28,66,84,92,106,126,155,167,195,198,219],"task":[6],"of":[7,30,110,128,203],"visual":[8,50,68,140,151,174,205],"grounding":[9,69,141,152],"for":[10,91,136,255],"remote":[11,23,117],"sensing":[12,24,118],"data":[13],"(RSVG).":[14],"RSVG":[15,93,111,258],"aims":[16],"to":[17,82,123,211,246],"localize":[18],"referred":[20],"objects":[21],"in":[22,77,115],"(RS)":[25],"images":[26,72,183],"with":[27,186,194,218],"guidance":[29],"natural":[31,41,149],"language.":[32],"To":[33,192,216],"retrieve":[34],"rich":[35],"information":[36],"from":[37],"RS":[38,48,53,57,71],"imagery":[39],"using":[40],"language,":[42],"many":[43],"research":[44,127],"tasks,":[45],"such":[46],"as":[47,101],"image":[49,54,150],"question":[51],"answering,":[52],"captioning,":[55],"and":[56,86,138,159,189,207,228,243],"image\u2013text":[58],"retrieval,":[59],"have":[60],"been":[61],"investigated":[62],"a":[63,170],"lot.":[64],"However,":[65],"object-level":[67],"on":[70,113,154,166],"is":[73,179],"still":[74],"underexplored.":[75],"Thus,":[76],"work,":[79],"propose":[81],"construct":[83],"dataset":[85,132],"explore":[87],"deep":[88],"learning":[89],"models":[90],"task.":[94],"Specifically,":[95],"our":[96,235],"contributions":[97],"can":[98,238,251],"be":[99],"summarized":[100],"follows.":[102],"First,":[103],"build":[105],"new":[107,131],"large-scale":[108,187],"benchmark":[109,145],"based":[112,165],"detection":[114],"optical":[116],"(DIOR)":[119],"dataset,":[120,158],"termed":[121],"DIOR-RSVG,":[122],"fully":[124],"advance":[125],"RSVG.":[129],"This":[130,249],"includes":[133],"image/expression/box":[134],"triplets":[135],"training":[137],"evaluating":[139],"models.":[142,259],"Second,":[143],"extensive":[146],"state-of-the-art":[147],"(SOTA)":[148],"methods":[153],"constructed":[156],"DIOR-RSVG":[157],"some":[160],"insightful":[161],"analyses":[162],"are":[163,184],"provided":[164],"results.":[168],"Third,":[169],"novel":[171],"transformer-based":[172],"multigranularity":[173,208],"language":[175],"fusion":[176],"(MGVLF)":[177],"module":[178,200],"proposed.":[180],"Remotely":[181],"sensed":[182],"usually":[185],"variations":[188],"cluttered":[190,220],"backgrounds.":[191],"deal":[193],"scale-variation":[196],"problem,":[197,222],"MGVLF":[199,223],"takes":[201],"advantage":[202],"multiscale":[204],"features":[206,245],"textual":[209],"embeddings":[210],"learn":[212],"more":[213,240],"discriminative":[214],"representations.":[215],"cope":[217],"background":[221],"adaptively":[224],"filters":[225],"irrelevant":[226],"noise":[227],"enhances":[229],"salient":[230],"features.":[231],"way,":[234],"proposed":[236],"model":[237],"incorporate":[239],"effective":[241],"multilevel":[242],"multimodal":[244],"boost":[247],"performance.":[248],"work":[250],"provide":[252],"useful":[253],"insights":[254],"developing":[256],"better":[257]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":72},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":7}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2023-03-02T00:00:00"}
