{"id":"https://openalex.org/W7160860372","doi":"https://doi.org/10.1109/tip.2026.3690309","title":"ReCoTR: Reducing Semantic Cognitive Shift via Dual-Consensus Token Compression for Remote Sensing Image-Text Retrieval","display_name":"ReCoTR: Reducing Semantic Cognitive Shift via Dual-Consensus Token Compression for Remote Sensing Image-Text Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160860372","doi":"https://doi.org/10.1109/tip.2026.3690309","pmid":"https://pubmed.ncbi.nlm.nih.gov/42113666"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3690309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3690309","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5109747583","display_name":"Jirui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I4210149102","display_name":"Sanya University","ror":"https://ror.org/04fa2qd52","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210149102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jirui Huang","raw_affiliation_strings":["Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, China","institution_ids":["https://openalex.org/I196699116","https://openalex.org/I4210149102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508336","display_name":"Yuehua Chen","orcid":"https://orcid.org/0000-0002-4646-4017"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxiong Chen","raw_affiliation_strings":["Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2903-6723","affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569906","display_name":"Chuang Du","orcid":"https://orcid.org/0000-0002-6238-1908"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I4210149102","display_name":"Sanya University","ror":"https://ror.org/04fa2qd52","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210149102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Du","raw_affiliation_strings":["Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, China"],"raw_orcid":"https://orcid.org/0009-0003-4047-6900","affiliations":[{"raw_affiliation_string":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, China","institution_ids":["https://openalex.org/I196699116","https://openalex.org/I4210149102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135877590","display_name":"Shengwu Xiong","orcid":"https://orcid.org/0000-0002-4006-7029"},"institutions":[{"id":"https://openalex.org/I4210100789","display_name":"Wuhan College","ror":"https://ror.org/01dashf18","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210100789"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwu Xiong","raw_affiliation_strings":["Interdisciplinary Artificial Intelligence Research Institute, Wuhan College, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4006-7029","affiliations":[{"raw_affiliation_string":"Interdisciplinary Artificial Intelligence Research Institute, Wuhan College, Wuhan, China","institution_ids":["https://openalex.org/I4210100789"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135829382","display_name":"Xiaoqiang Lu","orcid":"https://orcid.org/0000-0002-7037-5188"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Lu","raw_affiliation_strings":["College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7037-5188","affiliations":[{"raw_affiliation_string":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59011139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"5017","last_page":"5031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.5012000203132629,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.5012000203132629,"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":0.17409999668598175,"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":0.08089999854564667,"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/data-compression","display_name":"Data compression","score":0.5519000291824341},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41839998960494995},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4124000072479248},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.36010000109672546},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.3424000144004822},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.3384999930858612},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.3319000005722046},{"id":"https://openalex.org/keywords/remote-sensing-application","display_name":"Remote sensing application","score":0.3215000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720999717712402},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.645799994468689},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4690000116825104},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.36010000109672546},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.3384999930858612},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.3319000005722046},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C104541649","wikidata":"https://www.wikidata.org/wiki/Q6935090","display_name":"Multispectral pattern recognition","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3690309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3690309","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:42113666","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42113666","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4936741590499878}],"awards":[{"id":"https://openalex.org/G94439722","display_name":null,"funder_award_id":"62571381","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,41,55,129,152],"rapid":[2],"advancement":[3],"of":[4,19,44,57,112],"vision-language":[5],"models":[6],"(VLMs)":[7],"in":[8,47,156,186],"general-purpose":[9],"settings,":[10],"their":[11],"application":[12],"to":[13,54,100,119],"cross-modal":[14,70,166],"retrieval":[15,71,167,179],"and":[16,37,83,140,150,184],"semantic":[17,45,85,103,113,145,189],"understanding":[18],"large-scale":[20],"multimodal":[21],"remote":[22,75,187],"sensing":[23,76,188],"(RS)":[24],"data":[25],"is":[26],"emerging":[27],"as":[28],"a":[29,51,88,97],"key":[30],"enabler":[31],"for":[32,74,115],"urban":[33],"governance,":[34],"environmental":[35],"monitoring,":[36],"disaster":[38],"response.":[39],"However,":[40],"pervasive":[42],"issue":[43],"shift":[46],"RS":[48,165],"image":[49],"poses":[50],"significant":[52],"challenge":[53],"transferability":[56],"pre-trained":[58],"VLMs.":[59],"To":[60],"address":[61],"this":[62],"limitation,":[63],"we":[64,127],"propose":[65],"ReCoTR,":[66],"an":[67],"enhanced":[68],"CLIP-based":[69],"framework":[72],"tailored":[73],"applications.":[77],"ReCoTR":[78,171],"tackles":[79],"region-level":[80],"granularity":[81],"bias":[82],"contextual":[84],"drift":[86],"through":[87],"Dual":[89],"Consensus":[90],"Token":[91,132],"Evaluation":[92],"(DCTE)":[93],"module,":[94],"which":[95],"leverages":[96],"mixture-of-experts":[98],"strategy":[99],"fuse":[101],"inter-modal":[102],"consensus":[104],"with":[105,143],"intra-modal":[106],"structural":[107],"consistency,":[108],"enabling":[109],"fine-grained":[110],"estimation":[111],"confidence":[114],"visual":[116],"tokens.":[117],"Moreover,":[118],"mitigate":[120],"representational":[121],"contamination":[122],"caused":[123],"by":[124],"background":[125],"noise,":[126],"introduce":[128],"Semantic":[130],"Confidence":[131],"Compression":[133],"(SCTC)":[134],"module.":[135],"This":[136],"module":[137],"selectively":[138],"filters":[139],"aggregates":[141],"tokens":[142],"high":[144],"relevance,":[146],"thus":[147],"reducing":[148],"redundancy":[149],"alleviating":[151],"noise":[153],"amplification":[154],"inherent":[155],"CLIP's":[157],"average":[158],"pooling.":[159],"Experimental":[160],"results":[161],"on":[162,176],"three":[163],"benchmark":[164],"datasets":[168],"demonstrate":[169],"that":[170],"consistently":[172],"outperforms":[173],"existing":[174],"methods":[175],"bidirectional":[177],"image-text":[178],"tasks,":[180],"validating":[181],"its":[182],"effectiveness":[183],"robustness":[185],"alignment":[190],"scenarios.":[191],"Our":[192],"source":[193],"codes":[194],"are":[195],"available":[196],"at:":[197],"https://github.com/Jerry710/ReCoTR.git.":[198]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-12T00:00:00"}