{"id":"https://openalex.org/W4416254915","doi":"https://doi.org/10.1145/3786798","title":"Cross-Modal Full-Mode Fine-Grained Alignment for Text-to-Image Person Retrieval","display_name":"Cross-Modal Full-Mode Fine-Grained Alignment for Text-to-Image Person Retrieval","publication_year":2026,"publication_date":"2026-01-03","ids":{"openalex":"https://openalex.org/W4416254915","doi":"https://doi.org/10.1145/3786798"},"language":"en","primary_location":{"id":"doi:10.1145/3786798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3786798","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.13754","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hao Yin","orcid":"https://orcid.org/0009-0004-9807-9251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yin","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-9807-9251","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Man","orcid":"https://orcid.org/0000-0001-9684-4424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Man","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9684-4424","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feiyu Chen","orcid":"https://orcid.org/0000-0002-0928-6899"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210131342","display_name":"Yibin University","ror":"https://ror.org/03w8m2977","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131342"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyu Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China  and Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":"https://orcid.org/0000-0002-0928-6899","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China  and Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I4210131342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210131342","display_name":"Yibin University","ror":"https://ror.org/03w8m2977","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131342"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China  and Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":"https://orcid.org/0000-0003-2615-1555","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China  and Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I4210131342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210131342","display_name":"Yibin University","ror":"https://ror.org/03w8m2977","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131342"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China  and Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China  and Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I4210131342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.1542,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.98009671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.5640000104904175,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.5640000104904175,"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":0.2689000070095062,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.042899999767541885,"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/matching","display_name":"Matching (statistics)","score":0.6365000009536743},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.612500011920929},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.515999972820282},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5128999948501587},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5077000260353088},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.45669999718666077},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.450300008058548},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44179999828338623},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8600999712944031},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.612500011920929},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5128999948501587},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5077000260353088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44179999828338623},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3786798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3786798","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2509.13754","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.13754","pdf_url":"https://arxiv.org/pdf/2509.13754","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,"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.2509.13754","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.13754","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,"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:2509.13754","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.13754","pdf_url":"https://arxiv.org/pdf/2509.13754","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,"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":[],"awards":[{"id":"https://openalex.org/G2064659031","display_name":null,"funder_award_id":"62302080","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4488764924","display_name":null,"funder_award_id":"Guike AB24010112","funder_id":"https://openalex.org/F4320336589","funder_display_name":"Guangxi Key Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336589","display_name":"Guangxi Key Research and Development Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-Image":[0],"Person":[1],"Retrieval":[2],"(TIPR)":[3],"is":[4,28,234],"a":[5,19,40,109,204],"cross-modal":[6,56,110,194],"matching":[7,118,227],"task":[8],"designed":[9],"to":[10,18,29,64,77,88,147],"identify":[11],"the":[12,34,62,79,129,156,162,182,199],"person":[13],"images":[14],"that":[15],"best":[16],"correspond":[17],"given":[20],"textual":[21,35],"description.":[22],"The":[23,229],"key":[24],"difficulty":[25],"in":[26,161],"TIPR":[27],"realize":[30],"robust":[31],"correspondence":[32],"between":[33,91],"and":[36,93,124,202],"visual":[37],"modalities":[38],"within":[39],"unified":[41],"latent":[42],"representation":[43],"space.":[44],"To":[45,102],"address":[46],"this":[47],"challenge,":[48],"prior":[49],"approaches":[50],"incorporate":[51],"attention":[52],"mechanisms":[53],"for":[54,181,208,231],"implicit":[55,126,188],"local":[57,68,209],"alignment.":[58,171,210],"However,":[59],"they":[60],"lack":[61,183],"ability":[63],"verify":[65],"whether":[66],"all":[67,225],"features":[69],"are":[70],"correctly":[71],"aligned.":[72],"Moreover,":[73],"existing":[74,125],"methods":[75],"tend":[76],"emphasize":[78],"utilization":[80],"of":[81,184,187],"hard":[82,205],"negative":[83,94],"samples":[84],"during":[85],"model":[86],"optimization":[87],"strengthen":[89],"discrimination":[90],"positive":[92,100,150,158],"pairs,":[95],"often":[96],"neglecting":[97],"incorrectly":[98],"matched":[99],"pairs.":[101,152],"mitigate":[103],"these":[104],"problems,":[105],"we":[106,138,173],"propose":[107,139],"FMFA,":[108],"Full-Mode":[111],"Fine-Grained":[112,121],"Alignment":[113,122],"framework,":[114],"which":[115,178],"enhances":[116],"global":[117,170,226],"through":[119],"Explicit":[120],"(EFA)":[123],"relational":[127,189],"reasoning\u2014hence":[128],"term":[130],"\u201cfull-mode\u201d\u2014without":[131],"introducing":[132],"extra":[133],"supervisory":[134],"signals.":[135],"In":[136],"particular,":[137],"an":[140,175],"Adaptive":[141],"Similarity":[142],"Distribution":[143],"Matching":[144],"(A-SDM)":[145],"module":[146],"rectify":[148],"unmatched":[149,157],"sample":[151],"A-SDM":[153],"adaptively":[154],"pulls":[155],"pairs":[159],"closer":[160],"joint":[163],"embedding":[164],"space,":[165],"thereby":[166],"achieving":[167],"more":[168],"precise":[169],"Additionally,":[172],"introduce":[174],"EFA":[176,191],"module,":[177],"makes":[179],"up":[180],"verification":[185],"capability":[186],"reasoning.":[190],"strengthens":[192],"explicit":[193],"fine-grained":[195],"interactions":[196],"by":[197],"sparsifying":[198],"similarity":[200],"matrix":[201],"employs":[203],"coding":[206],"method":[207,214,233],"We":[211],"evaluate":[212],"our":[213,232],"on":[215],"three":[216],"public":[217],"datasets,":[218],"where":[219],"it":[220],"attains":[221],"state-of-the-art":[222],"results":[223],"among":[224],"methods.":[228],"code":[230],"publicly":[235],"accessible":[236],"at":[237],"https://github.com/yinhao1102/FMFA":[238],".":[239]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}