{"id":"https://openalex.org/W7123359385","doi":"https://doi.org/10.1109/tmm.2026.3651040","title":"PPDSA: Privacy-Preserving Cross-Modal Retrieval With Disentangled Soft-Label Alignment","display_name":"PPDSA: Privacy-Preserving Cross-Modal Retrieval With Disentangled Soft-Label Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123359385","doi":"https://doi.org/10.1109/tmm.2026.3651040"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651040","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5122884292","display_name":"Jianting Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I119273862","display_name":"Central South University of Forestry and Technology","ror":"https://ror.org/02czw2k81","country_code":"CN","type":"education","lineage":["https://openalex.org/I119273862"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianting Peng","raw_affiliation_strings":["College of Computer and Mathematics, Central, South University of Forestry and Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0000-4575-2757","affiliations":[{"raw_affiliation_string":"College of Computer and Mathematics, Central, South University of Forestry and Technology, Changsha, China","institution_ids":["https://openalex.org/I119273862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024169213","display_name":"Xuyu Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I119273862","display_name":"Central South University of Forestry and Technology","ror":"https://ror.org/02czw2k81","country_code":"CN","type":"education","lineage":["https://openalex.org/I119273862"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyu Xiang","raw_affiliation_strings":["College of Computer and Mathematics, Central, South University of Forestry and Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2778-7531","affiliations":[{"raw_affiliation_string":"College of Computer and Mathematics, Central, South University of Forestry and Technology, Changsha, China","institution_ids":["https://openalex.org/I119273862"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaohua Qin","orcid":"https://orcid.org/0000-0002-7549-7731"},"institutions":[{"id":"https://openalex.org/I119273862","display_name":"Central South University of Forestry and Technology","ror":"https://ror.org/02czw2k81","country_code":"CN","type":"education","lineage":["https://openalex.org/I119273862"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaohua Qin","raw_affiliation_strings":["College of Computer and Mathematics, Central, South University of Forestry and Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7549-7731","affiliations":[{"raw_affiliation_string":"College of Computer and Mathematics, Central, South University of Forestry and Technology, Changsha, China","institution_ids":["https://openalex.org/I119273862"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yun Tan","orcid":"https://orcid.org/0000-0002-9855-8234"},"institutions":[{"id":"https://openalex.org/I119273862","display_name":"Central South University of Forestry and Technology","ror":"https://ror.org/02czw2k81","country_code":"CN","type":"education","lineage":["https://openalex.org/I119273862"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Tan","raw_affiliation_strings":["College of Computer and Mathematics, Central, South University of Forestry and Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-9855-8234","affiliations":[{"raw_affiliation_string":"College of Computer and Mathematics, Central, South University of Forestry and Technology, Changsha, China","institution_ids":["https://openalex.org/I119273862"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I119273862"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05357262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"2643","last_page":"2653"},"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":0.8048999905586243,"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":0.8048999905586243,"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/T10237","display_name":"Cryptography and Data Security","score":0.06710000336170197,"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"}},{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.024399999529123306,"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/encryption","display_name":"Encryption","score":0.6949999928474426},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6312999725341797},{"id":"https://openalex.org/keywords/plaintext","display_name":"Plaintext","score":0.5475999712944031},{"id":"https://openalex.org/keywords/thumbnail","display_name":"Thumbnail","score":0.4765999913215637},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45649999380111694},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4302999973297119},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4072999954223633},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4043000042438507},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3747999966144562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8974000215530396},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.6949999928474426},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6312999725341797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5981000065803528},{"id":"https://openalex.org/C92717368","wikidata":"https://www.wikidata.org/wiki/Q1162538","display_name":"Plaintext","level":3,"score":0.5475999712944031},{"id":"https://openalex.org/C160174412","wikidata":"https://www.wikidata.org/wiki/Q873806","display_name":"Thumbnail","level":3,"score":0.4765999913215637},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4546000063419342},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3747999966144562},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3716000020503998},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.36719998717308044},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.29179999232292175},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.28439998626708984},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651040","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3637059996","display_name":null,"funder_award_id":"62372478","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":{"Cross-modal":[0],"retrieval":[1,41,97,149,238],"techniques,":[2],"with":[3,246],"their":[4],"efficient":[5],"search":[6],"capabilities,":[7],"have":[8],"garnered":[9],"considerable":[10],"attention":[11],"in":[12,25,33,39,53,70,117,231],"both":[13],"industry":[14],"and":[15,67,154,178,183,201,217,242],"academia.":[16],"Among":[17],"them,":[18],"image-text":[19,181],"cross-modal":[20,27,40,72,85,96,133,141,179,232],"retrieval,":[21,233],"a":[22,57,94,160,167],"classic":[23],"task":[24],"the":[26,64,71,107,125,129,148,174,203,222,237,247],"domain,":[28],"has":[29],"been":[30],"widely":[31],"applied":[32,83],"internet":[34],"applications.":[35],"However,":[36],"image":[37,76,110,126,186,229],"data":[38],"applications":[42],"often":[43],"contains":[44],"rich":[45],"personal":[46],"sensitive":[47],"information,":[48],"which":[49],"is":[50,115,170],"typically":[51],"stored":[52],"plaintext":[54],"format,":[55],"posing":[56],"risk":[58],"of":[59,109,131,151,205,213],"privacy":[60,77,108,230],"leakage.":[61],"Due":[62],"to":[63,84,105,123,139,145,172,194],"unique":[65],"semantic":[66,198],"heterogeneous":[68],"gap":[69],"space,":[73],"existing":[74],"single-modality":[75],"protection":[78],"techniques":[79,191],"cannot":[80],"be":[81],"directly":[82],"scenarios.":[86],"To":[87],"address":[88],"this":[89,91,118,157],"issue,":[90],"paper":[92,158],"proposes":[93],"privacy-preserving":[95],"method":[98,121,224],"based":[99],"on":[100,208,215],"disentangled":[101,161],"soft-label":[102],"alignment(PPDSA).":[103],"Firstly,":[104],"protect":[106],"data,":[111],"thumbnail":[112],"preserving":[113],"encryption":[114],"used":[116,171],"paper.":[119],"This":[120],"aims":[122],"encrypt":[124],"while":[127],"ensuring":[128],"feasibility":[130],"graph-text":[132],"feature":[134],"representation":[135,199],"learning,":[136],"so":[137],"as":[138],"realize":[140],"encrypted":[142,152],"retrieval.":[143],"Second,":[144],"further":[146],"improve":[147],"effect":[150],"images":[153],"normal":[155],"text,":[156],"introduces":[159],"soft":[162,175,188],"label":[163,176,189],"alignment":[164,190],"technique.":[165],"Specifically,":[166],"teacher":[168],"model":[169],"obtain":[173],"matrix,":[177],"(encrypted":[180,185],"pair)":[182,187],"single-modal":[184],"are":[192],"designed":[193],"capture":[195],"more":[196],"fine-grained":[197],"information":[200],"reduce":[202],"interference":[204],"false":[206],"positives":[207],"similarity":[209],"recognition.":[210],"A":[211],"series":[212],"experiments":[214],"Flickr30k":[216],"MSCOCO":[218],"datasets":[219],"show":[220],"that":[221],"proposed":[223],"not":[225],"only":[226],"effectively":[227],"protects":[228],"but":[234],"also":[235],"improves":[236],"performance":[239],"by":[240],"6.7%":[241],"3.7%":[243],"respectively":[244],"compared":[245],"CLIP":[248],"baseline.":[249]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2026-01-14T00:00:00"}