{"id":"https://openalex.org/W4415540245","doi":"https://doi.org/10.1145/3746027.3754721","title":"Learning Hierarchical Cross-modal Association with Intra-modal Context for Text-Image Person Retrieval","display_name":"Learning Hierarchical Cross-modal Association with Intra-modal Context for Text-Image Person Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540245","doi":"https://doi.org/10.1145/3746027.3754721"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5114208128","display_name":"Yifei Deng","orcid":"https://orcid.org/0000-0002-4949-9995"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifei Deng","raw_affiliation_strings":["State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China and School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China and School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I143868143","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398932","display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":["State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China and School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China and School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143","https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073752594","display_name":"Futian Wang","orcid":"https://orcid.org/0000-0003-4181-8485"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Futian Wang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China and School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China and School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030720334","display_name":"Jin Tang","orcid":"https://orcid.org/0000-0001-8375-3590"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Tang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China and School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China and School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114208128"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I143868143","https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29923523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2723","last_page":"2731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9980000257492065,"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":0.9979000091552734,"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/relevance","display_name":"Relevance (law)","score":0.6773999929428101},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6467000246047974},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5855000019073486},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5514000058174133},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.491100013256073},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44429999589920044},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4399999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544000148773193},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6773999929428101},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770000219345093},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4675999879837036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45910000801086426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45570001006126404},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.40779998898506165},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3499042019","display_name":null,"funder_award_id":"2376004","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":19,"referenced_works":["https://openalex.org/W2963449390","https://openalex.org/W3165835426","https://openalex.org/W3187284461","https://openalex.org/W3206868111","https://openalex.org/W4214736485","https://openalex.org/W4304087170","https://openalex.org/W4312877428","https://openalex.org/W4312998013","https://openalex.org/W4386065462","https://openalex.org/W4386071687","https://openalex.org/W4387968073","https://openalex.org/W4387969466","https://openalex.org/W4388145471","https://openalex.org/W4390874394","https://openalex.org/W4390970441","https://openalex.org/W4392172801","https://openalex.org/W4402753821","https://openalex.org/W4405034605","https://openalex.org/W4409959339"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"Text-Image":[1],"Person":[2],"Retrieval":[3],"(TIPR)":[4],"methods":[5],"have":[6],"made":[7],"substantial":[8],"progress":[9],"in":[10,24,214],"modeling":[11],"cross-modal":[12,62,76,101,143,153,215],"associations":[13],"via":[14],"contrastive":[15],"learning":[16],"frameworks,":[17],"but":[18,136],"usually":[19],"ignore":[20],"the":[21,49,89,124,139,148,188],"fine-grained":[22,51,152,189],"differences":[23],"semantic":[25,52,77,131,154,190],"relevance":[26,111],"among":[27],"different":[28],"samples,":[29],"which":[30,47],"limits":[31],"retrieval":[32,216],"accuracy.":[33],"To":[34,146],"address":[35],"this":[36],"problem,":[37],"we":[38,79,156],"propose":[39,80],"a":[40,81,109,116],"novel":[41],"Hierarchical":[42,82],"Cross-modal":[43],"Association":[44],"framework":[45],"HCA,":[46],"leverages":[48,175],"intra-modal":[50],"relations":[53],"distilled":[54],"by":[55,95],"single-modal":[56],"pretrained":[57],"models":[58],"to":[59,73,107,150,178],"constrain":[60],"hierarchical":[61,75,110],"association":[63,144],"between":[64,133,192],"image":[65,176],"and":[66,100,174,180,194,212],"text":[67,161],"modalities,":[68],"for":[69],"accurate":[70],"TIPR.":[71],"Specifically,":[72],"model":[74,125],"relationships,":[78,155],"Relevance":[83],"Matching":[84],"(HRM)":[85],"module.":[86,165],"It":[87,166],"partitions":[88],"matching":[90],"strength":[91],"of":[92,130,142],"image-text":[93,134],"pairs":[94,135],"jointly":[96],"considering":[97],"identity":[98],"labels":[99],"similarity,":[102],"collaborating":[103],"with":[104,170],"unimodal":[105],"similarity":[106],"construct":[108],"distribution":[112],"that":[113,199],"serves":[114],"as":[115],"soft":[117],"supervision":[118],"signal.":[119],"HRM":[120],"not":[121],"only":[122],"helps":[123],"better":[126],"capture":[127,151],"varying":[128],"levels":[129],"consistency":[132],"also":[137],"enhances":[138],"overall":[140],"accuracy":[141],"learning.":[145],"enhance":[147],"ability":[149],"introduce":[157],"an":[158],"Image-guided":[159],"Ambiguous":[160],"Token":[162],"Modeling":[163],"(IATM)":[164],"replaces":[167],"original":[168],"tokens":[169],"semantically":[171],"ambiguous":[172],"ones":[173],"guidance":[177],"detect":[179],"correct":[181],"these":[182],"tokens.":[183],"This":[184],"process":[185],"further":[186],"improves":[187],"alignment":[191],"images":[193],"texts.":[195],"Experimental":[196],"results":[197],"demonstrate":[198],"HCA":[200],"achieves":[201],"new":[202],"state-of-the-art":[203],"performance":[204],"across":[205],"multiple":[206],"datasets,":[207],"thoroughly":[208],"validating":[209],"its":[210],"effectiveness":[211],"advancement":[213],"tasks.":[217]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}