{"id":"https://openalex.org/W4415536715","doi":"https://doi.org/10.1145/3746027.3754583","title":"Dialogue-Driven Interactive Dynamic Learning for Text-to-Image Person Retrieval","display_name":"Dialogue-Driven Interactive Dynamic Learning for Text-to-Image Person Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536715","doi":"https://doi.org/10.1145/3746027.3754583"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754583","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754583","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":"conference-paper","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":null,"display_name":"Hongyu Liu","orcid":"https://orcid.org/0009-0009-4244-6696"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Liu","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0009-0009-4244-6696","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091010251","display_name":"Hongwei Ge","orcid":"https://orcid.org/0000-0002-8937-1515"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Ge","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-8937-1515","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010054833","display_name":"Yuxuan Liu","orcid":"https://orcid.org/0000-0003-1168-6645"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Liu","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0003-1168-6645","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044443092","display_name":"Yaqing Hou","orcid":"https://orcid.org/0000-0002-9929-2650"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqing Hou","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-9929-2650","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9177","last_page":"9185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9952999949455261,"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":0.9936000108718872,"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/discriminative-model","display_name":"Discriminative model","score":0.679099977016449},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5654000043869019},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5630000233650208},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5331000089645386},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.45660001039505005},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.44190001487731934},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.41269999742507935},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.3790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503999710083008},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.679099977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5656999945640564},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5654000043869019},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48080000281333923},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.45660001039505005},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.30979999899864197},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.3077000081539154},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.2897999882698059},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754583","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754583","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2963449390","https://openalex.org/W3206868111","https://openalex.org/W4283818632","https://openalex.org/W4297821751","https://openalex.org/W4304087170","https://openalex.org/W4312533058","https://openalex.org/W4312933868","https://openalex.org/W4386065462","https://openalex.org/W4387969466","https://openalex.org/W4388145471","https://openalex.org/W4393148792"],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"person":[1,7,91],"retrieval":[2,20,23,64,76,104],"aims":[3],"to":[4,39,68,127],"identify":[5],"target":[6],"images":[8],"using":[9],"natural":[10],"language":[11],"descriptions.":[12,34],"Current":[13],"state-of-the-art":[14,173],"methods":[15],"predominantly":[16],"rely":[17],"on":[18,27,117,142],"single-round":[19,63],"frameworks,":[21],"where":[22],"accuracy":[24],"heavily":[25],"depends":[26],"the":[28,31,62,69,124],"quality":[29],"of":[30,61,71],"initial":[32,52,136],"textual":[33],"However,":[35],"users":[36],"sometimes":[37],"struggle":[38],"provide":[40],"detailed":[41],"and":[42,74,130,138,162],"distinctive":[43],"descriptions":[44,137],"in":[45,50],"a":[46,118],"single":[47],"attempt,":[48],"resulting":[49],"generic":[51],"queries":[53],"that":[54,122,154,169],"lack":[55],"discriminative":[56],"details.":[57],"This":[58],"fundamental":[59],"limitation":[60],"framework":[65],"frequently":[66],"leads":[67],"misinterpretation":[70],"user":[72],"intent":[73],"suboptimal":[75],"performance.":[77],"To":[78],"address":[79],"this":[80],"limitation,":[81],"we":[82,94,110,145],"propose":[83,147],"Dialogue-driven":[84],"Interactive":[85],"Dynamic":[86,112],"Learning":[87],"(DIDL)":[88],"for":[89],"text-to-image":[90],"retrieval.":[92],"Specifically,":[93],"first":[95],"introduce":[96],"Collaborative":[97],"Query":[98],"Refinement":[99],"(CQR),":[100],"which":[101],"progressively":[102],"refines":[103],"conditions":[105],"through":[106],"multi-round":[107],"dialogues.":[108],"Then,":[109],"design":[111],"Context":[113,150],"Resampling":[114],"(DCR)":[115],"based":[116],"bi-granular":[119],"mask":[120],"strategy":[121],"enhances":[123],"model's":[125],"adaptation":[126],"dialogue-style":[128],"contexts":[129],"effectively":[131],"balances":[132],"its":[133],"attention":[134],"between":[135,158],"supplementary":[139],"information.":[140],"Based":[141],"these":[143],"components,":[144],"further":[146],"cross-modal":[148],"Probabilistic":[149],"Matching":[151],"Modeling":[152],"(ProCMM)":[153],"establishes":[155],"effective":[156],"associations":[157],"static":[159],"visual":[160],"features":[161],"dynamic":[163],"contextual":[164],"semantics.":[165],"Extensive":[166],"experiments":[167],"demonstrate":[168],"our":[170],"approach":[171],"achieves":[172],"performance":[174],"across":[175],"all":[176],"three":[177],"benchmark":[178],"datasets.":[179]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}