{"id":"https://openalex.org/W4379806246","doi":"https://doi.org/10.1145/3591106.3592236","title":"Reducing Semantic Confusion: Scene-aware Aggregation Network for Remote Sensing Cross-modal Retrieval","display_name":"Reducing Semantic Confusion: Scene-aware Aggregation Network for Remote Sensing Cross-modal Retrieval","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806246","doi":"https://doi.org/10.1145/3591106.3592236"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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, China"],"raw_orcid":"https://orcid.org/0000-0001-5968-5209","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, 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, China"],"raw_orcid":"https://orcid.org/0000-0003-1749-9509","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, 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, China"],"raw_orcid":"https://orcid.org/0000-0002-6177-3862","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, 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":4.9454,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.96525802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"398","last_page":"406"},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8543760776519775},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5530498623847961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5445312857627869},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5165480971336365},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5152955055236816},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4478345215320587},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.428399920463562},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41496044397354126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.398806095123291},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36121928691864014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543760776519775},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5530498623847961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5445312857627869},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5165480971336365},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5152955055236816},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4478345215320587},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.428399920463562},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41496044397354126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.398806095123291},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36121928691864014},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1912954554","https://openalex.org/W2108598243","https://openalex.org/W2250539671","https://openalex.org/W2253590344","https://openalex.org/W2401246392","https://openalex.org/W2515866431","https://openalex.org/W2779054585","https://openalex.org/W2898008292","https://openalex.org/W2919352650","https://openalex.org/W2962964995","https://openalex.org/W2964979676","https://openalex.org/W2969689033","https://openalex.org/W3004137323","https://openalex.org/W3092820619","https://openalex.org/W3100245404","https://openalex.org/W3100892511","https://openalex.org/W3105577662","https://openalex.org/W3140792177","https://openalex.org/W3155230099","https://openalex.org/W3155649272","https://openalex.org/W3197310284","https://openalex.org/W3208803664","https://openalex.org/W3213288046","https://openalex.org/W3217792975","https://openalex.org/W4224911357","https://openalex.org/W4308743547","https://openalex.org/W4312808420"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W4226090359","https://openalex.org/W4382701072","https://openalex.org/W2491314273","https://openalex.org/W2966858528","https://openalex.org/W3192902148","https://openalex.org/W2151687600"],"abstract_inverted_index":{"Recently,":[0],"remote":[1,137],"sensing":[2,77,138],"cross-modal":[3],"retrieval":[4,31,162],"has":[5],"received":[6],"incredible":[7],"attention":[8],"from":[9],"researchers.":[10],"However,":[11],"the":[12,25,84,100,121,132,141,155,168,187],"unique":[13],"nature":[14],"of":[15,86,123,136,143,157,170,191],"remote-sensing":[16],"images":[17],"leads":[18],"to":[19,41,61,82,119,126,153],"many":[20],"semantic":[21,26,43,175],"confusion":[22,44],"zones":[23],"in":[24,173],"space,":[27],"which":[28,164],"greatly":[29],"affects":[30],"performance.":[32],"We":[33],"propose":[34],"a":[35,53,69,74,111,145],"novel":[36],"scene-aware":[37,93],"aggregation":[38,95],"network":[39],"(SWAN)":[40],"reduce":[42],"by":[45,99,104,159],"improving":[46],"scene":[47,75,149],"perception":[48,156],"capability.":[49],"In":[50,108],"visual":[51,54,63,70,94,101,128],"representation,":[52,110],"multiscale":[55],"fusion":[56],"module":[57,78,115],"(VMSF)":[58],"is":[59,80,97,117,151,203],"presented":[60],"fuse":[62],"features":[64,88],"with":[65],"different":[66,90],"scales":[67],"as":[68,131],"representation":[71,96],"backbone.":[72],"Meanwhile,":[73],"fine-grained":[76],"(SFGS)":[79],"proposed":[81,152],"establish":[83],"associations":[85],"salient":[87],"at":[89,205],"granularity.":[91],"A":[92],"formed":[98],"information":[102],"generated":[103],"these":[105],"two":[106,195],"modules.":[107],"textual":[109,112],"coarse-grained":[113],"enhancement":[114],"(TCGE)":[116],"designed":[118],"enhance":[120],"semantics":[122],"text":[124],"and":[125,134,182,189,198],"align":[127],"information.":[129],"Furthermore,":[130],"diversity":[133],"differentiation":[135],"scenes":[139,158],"weaken":[140],"understanding":[142],"scenes,":[144],"new":[146],"metric,":[147],"namely,":[148],"recall":[150],"measure":[154],"evaluating":[160],"scene-level":[161],"performance,":[163],"can":[165],"also":[166],"verify":[167],"effectiveness":[169,188],"our":[171,192],"approach":[172,193],"reducing":[174],"confusion.":[176],"By":[177],"performance":[178],"comparisons,":[179],"ablation":[180],"studies":[181],"visualization":[183],"analysis,":[184],"we":[185],"validated":[186],"superiority":[190],"on":[194],"datasets,":[196],"RSICD":[197],"RSITMD.":[199],"The":[200],"source":[201],"code":[202],"available":[204],"https://github.com/kinshingpoon/SWAN-pytorch.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}