{"id":"https://openalex.org/W4393023402","doi":"https://doi.org/10.48550/arxiv.2403.10887","title":"LuoJiaHOG: A Hierarchy Oriented Geo-aware Image Caption Dataset for Remote Sensing Image-Text Retrival","display_name":"LuoJiaHOG: A Hierarchy Oriented Geo-aware Image Caption Dataset for Remote Sensing Image-Text Retrival","publication_year":2024,"publication_date":"2024-03-16","ids":{"openalex":"https://openalex.org/W4393023402","doi":"https://doi.org/10.48550/arxiv.2403.10887"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.10887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.10887","pdf_url":"https://arxiv.org/pdf/2403.10887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.10887","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109739869","display_name":"Yuanxin Zhao","orcid":"https://orcid.org/0009-0007-5250-4306","observed_orcids":["https://orcid.org/0009-0007-5250-4306"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yuanxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007668","display_name":"Mi Zhang","orcid":"https://orcid.org/0000-0003-1601-8363","observed_orcids":["https://orcid.org/0000-0003-1601-8363"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Mi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115593100","display_name":"Bingnan Yang","orcid":"https://orcid.org/0009-0007-9391-9209","observed_orcids":["https://orcid.org/0009-0007-9391-9209"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Bingnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393410","display_name":"Zhan Zhang","orcid":"https://orcid.org/0000-0001-7419-4272","observed_orcids":["https://orcid.org/0000-0001-7419-4272"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057685187","display_name":"Jiaju Kang","orcid":"https://orcid.org/0009-0009-8026-4332","observed_orcids":["https://orcid.org/0009-0009-8026-4332"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Jiaju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100574336","display_name":"Jianya Gong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Jianya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8490999937057495,"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":0.8490999937057495,"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":0.10949999839067459,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.024299999698996544,"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/image-text-retrieval","display_name":"image-text retrieval","score":0.7360000014305115},{"id":"https://openalex.org/keywords/remote-sensing-imagery","display_name":"remote sensing images","score":0.875},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.765999972820282},{"id":"https://openalex.org/keywords/ogc-standards","display_name":"OGC standards","score":0.6740000247955322},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.7149999737739563},{"id":"https://openalex.org/keywords/cross-modal-feature-fusion","display_name":"cross-modal feature fusion","score":0.7599999904632568},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.8140000104904175},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.7253903150558472},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7031136751174927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442567706108093},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40975072979927063},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.38057032227516174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3783043324947357},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34157028794288635},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.26526498794555664},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.10887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.10887","pdf_url":"https://arxiv.org/pdf/2403.10887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.10887","doi":"https://doi.org/10.48550/arxiv.2403.10887","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.10887","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.10887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.10887","pdf_url":"https://arxiv.org/pdf/2403.10887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2365264209","https://openalex.org/W962203960","https://openalex.org/W2509431957","https://openalex.org/W2026999166","https://openalex.org/W1599954583","https://openalex.org/W1996802783","https://openalex.org/W4211007821","https://openalex.org/W2802395037","https://openalex.org/W4389565704","https://openalex.org/W1976216854"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1],"(ITR)":[2],"plays":[3],"a":[4,79,213,223],"significant":[5,29],"role":[6],"in":[7,111,186],"making":[8],"informed":[9],"decisions":[10],"for":[11,216],"various":[12,126],"remote":[13],"sensing":[14],"(RS)":[15],"applications.":[16,228],"Nonetheless,":[17],"creating":[18],"ITR":[19,128,172],"datasets":[20],"containing":[21],"vision":[22],"and":[23,37,54,71,99,116,137,142,152,168,184,205,208],"language":[24],"modalities":[25],"not":[26],"only":[27],"requires":[28],"geo-spatial":[30],"sampling":[31,112],"area":[32],"but":[33],"also":[34],"varing":[35],"categories":[36],"detailed":[38,72],"descriptions.":[39],"To":[40],"this":[41],"end,":[42],"we":[43,77],"introduce":[44],"an":[45,179],"image":[46,204],"caption":[47,73],"dataset":[48],"LuojiaHOG,":[49],"which":[50],"is":[51,123],"geospatial-aware,":[52],"label-extension-friendly":[53],"comprehensive-captioned.":[55],"LuojiaHOG":[56,107,122,207],"involves":[57],"the":[58,109,161],"hierarchical":[59],"spatial":[60],"sampling,":[61],"extensible":[62],"classification":[63],"system":[64],"to":[65,86,145,191],"Open":[66],"Geospatial":[67],"Consortium":[68],"(OGC)":[69],"standards,":[70],"generation.":[74],"In":[75,175],"addition,":[76],"propose":[78],"CLIP-based":[80],"Image":[81],"Semantic":[82],"Enhancement":[83],"Network":[84],"(CISEN)":[85],"promote":[87],"sophisticated":[88],"ITR.":[89],"CISEN":[90,153,177,197,209],"consists":[91],"of":[92,166,181,188,226],"two":[93],"components,":[94],"namely":[95],"dual-path":[96],"knowledge":[97],"transfer":[98],"progressive":[100],"cross-modal":[101],"feature":[102],"fusion.":[103],"Comprehensive":[104],"statistics":[105],"on":[106,121,170],"reveal":[108],"richness":[110],"diversity,":[113],"labels":[114,144],"quantity":[115],"descriptions":[117],"granularity.":[118],"The":[119],"evaluation":[120],"conducted":[124],"across":[125,203],"state-of-the-art":[127],"models,":[129],"including":[130],"ALBEF,":[131],"ALIGN,":[132],"CLIP,":[133],"FILIP,":[134],"Wukong,":[135],"GeoRSCLIP":[136],"CISEN.":[138],"We":[139],"use":[140],"second-":[141],"third-level":[143,171],"evaluate":[146],"these":[147],"vision-language":[148,227],"models":[149],"through":[150],"adapter-tuning":[151],"demonstrates":[154],"superior":[155],"performance.":[156],"For":[157],"instance,":[158],"it":[159],"achieves":[160],"highest":[162],"scores":[163],"with":[164],"WMAP@5":[165,189],"88.47\\%":[167],"87.28\\%":[169],"tasks,":[173],"respectively.":[174],"particular,":[176],"exhibits":[178],"improvement":[180],"approximately":[182],"1.3\\%":[183],"0.9\\%":[185],"terms":[187],"compared":[190],"its":[192],"baseline.":[193],"These":[194],"findings":[195],"highlight":[196],"advancements":[198],"accurately":[199],"retrieving":[200],"pertinent":[201],"information":[202],"text.":[206],"can":[210],"serve":[211],"as":[212],"foundational":[214],"resource":[215],"future":[217],"RS":[218],"image-text":[219],"alignment":[220],"research,":[221],"facilitating":[222],"wide":[224],"range":[225]},"counts_by_year":[],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2025-10-10T00:00:00"}