{"id":"https://openalex.org/W4387969154","doi":"https://doi.org/10.1145/3581783.3612374","title":"A Prior Instruction Representation Framework for Remote Sensing Image-text Retrieval","display_name":"A Prior Instruction Representation Framework for Remote Sensing Image-text Retrieval","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969154","doi":"https://doi.org/10.1145/3581783.3612374"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5060268420","display_name":"Jiancheng Pan","orcid":"https://orcid.org/0000-0001-5968-5209"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiancheng Pan","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5968-5209","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101571340","display_name":"Qing Ma","orcid":"https://orcid.org/0000-0003-1749-9509"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Ma","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1749-9509","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013768600","display_name":"Cong Bai","orcid":"https://orcid.org/0000-0002-6177-3862"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Bai","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6177-3862","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060268420"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":4.1017,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95511901,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"611","last_page":"620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.9979000091552734,"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":0.8416234254837036},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6725486516952515},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6317061185836792},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5704960823059082},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5545616149902344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.528915524482727},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5263582468032837},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5225800275802612},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48984262347221375},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.48042893409729004},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4515497088432312},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.44288545846939087},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40641582012176514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34120190143585205},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33184167742729187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416234254837036},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6725486516952515},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6317061185836792},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5704960823059082},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5545616149902344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.528915524482727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5263582468032837},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5225800275802612},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48984262347221375},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.48042893409729004},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4515497088432312},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.44288545846939087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40641582012176514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34120190143585205},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33184167742729187},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G389909570","display_name":null,"funder_award_id":"62102365","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G491842903","display_name":null,"funder_award_id":"61976192","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5251875183","display_name":null,"funder_award_id":"61976192","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G8847732984","display_name":null,"funder_award_id":"LR21F020002","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","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/W1905882502","https://openalex.org/W1958291604","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2138621090","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2401246392","https://openalex.org/W2515866431","https://openalex.org/W2618530766","https://openalex.org/W2779054585","https://openalex.org/W2801122074","https://openalex.org/W2803930360","https://openalex.org/W2962749812","https://openalex.org/W2962964995","https://openalex.org/W2964979676","https://openalex.org/W2981851019","https://openalex.org/W2982220924","https://openalex.org/W3004137323","https://openalex.org/W3092820619","https://openalex.org/W3100245404","https://openalex.org/W3105577662","https://openalex.org/W3138516171","https://openalex.org/W3140792177","https://openalex.org/W3173748501","https://openalex.org/W3207918547","https://openalex.org/W3208803664","https://openalex.org/W3217792975","https://openalex.org/W4224911357","https://openalex.org/W4306933361","https://openalex.org/W4308743547","https://openalex.org/W4312808420","https://openalex.org/W4313350201","https://openalex.org/W4365801687","https://openalex.org/W4379806246","https://openalex.org/W4390874575","https://openalex.org/W6600384961"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,33,93],"prior":[4,38,160],"instruction":[5,162],"representation":[6,132],"framework":[7],"(PIR)":[8],"for":[9,100],"remote":[10,16,87],"sensing":[11,17,88],"image-text":[12],"retrieval,":[13],"aimed":[14],"at":[15,185],"vision-language":[18],"understanding":[19],"tasks":[20],"to":[21,40,61,66,96,122,129,140,145],"solve":[22],"the":[23,30,82,86,102,118,125,142,147,152,172],"semantic":[24,105,148],"noise":[25],"problem.":[26],"Our":[27],"highlight":[28],"is":[29,138],"proposal":[31],"of":[32,44,85,104],"paradigm":[34],"that":[35,158],"draws":[36],"on":[37,79,115,175],"knowledge":[39,84,161],"instruct":[41],"adaptive":[42],"learning":[43],"vision":[45,72,165],"and":[46,57,144,166,169,180],"text":[47,108,131,167],"representations.":[48],"Concretely,":[49],"two":[50,176],"progressive":[51],"attention":[52],"encoder":[53],"(PAE)":[54],"structures,":[55],"Spatial-PAE":[56,80],"Temporal-PAE,":[58],"are":[59,183],"proposed":[60,139],"perform":[62],"long-range":[63],"dependency":[64],"modeling":[65],"enhance":[67,130,164],"key":[68,98],"feature":[69],"representation.":[70],"In":[71,107],"representation,":[73,109],"Vision":[74],"Instruction":[75],"Representation":[76],"(VIR)":[77],"based":[78,114],"exploits":[81],"prior-guided":[83],"scene":[89],"recognition":[90],"by":[91],"building":[92],"belief":[94],"matrix":[95],"select":[97],"features":[99],"reducing":[101],"impact":[103],"noise.":[106],"Language":[110],"Cycle":[111],"Attention":[112],"(LCA)":[113],"Temporal-PAE":[116],"uses":[117],"previous":[119],"time":[120,127],"step":[121,128],"cyclically":[123],"activate":[124],"current":[126],"capability.":[133],"A":[134],"cluster-wise":[135],"affiliation":[136],"loss":[137],"constrain":[141],"inter-classes":[143],"reduce":[146],"confusion":[149],"zones":[150],"in":[151],"common":[153],"subspace.":[154],"Comprehensive":[155],"experiments":[156],"demonstrate":[157],"using":[159],"could":[163,170],"representations":[168],"outperform":[171],"state-of-the-art":[173],"methods":[174],"benchmark":[177],"datasets,":[178],"RSICD":[179],"RSITMD.":[181],"Codes":[182],"available":[184],"https://github.com/Zjut-MultimediaPlus/PIR-pytorch.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":12}],"updated_date":"2026-05-22T09:01:20.584952","created_date":"2025-10-10T00:00:00"}