{"id":"https://openalex.org/W7108336954","doi":"https://doi.org/10.1145/3767695.3769474","title":"A Combination-based Framework for Generative Text-image Retrieval: Dual Identifiers and Hybrid Retrieval Strategies","display_name":"A Combination-based Framework for Generative Text-image Retrieval: Dual Identifiers and Hybrid Retrieval Strategies","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7108336954","doi":"https://doi.org/10.1145/3767695.3769474"},"language":null,"primary_location":{"id":"doi:10.1145/3767695.3769474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3767695.3769474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","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":"Kaipeng Li","orcid":"https://orcid.org/0009-0004-4406-2956"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaipeng Li","raw_affiliation_strings":["Graduate School of Comprehensive Human Sciences, University of Tsukuba, Tsukuba, Ibaraki, Japan"],"raw_orcid":"https://orcid.org/0009-0004-4406-2956","affiliations":[{"raw_affiliation_string":"Graduate School of Comprehensive Human Sciences, University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haitao Yu","orcid":"https://orcid.org/0000-0002-1569-8507"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haitao Yu","raw_affiliation_strings":["Institute of Library, Information and Media Science, University of Tsukuba, Tsukuba, Ibaraki, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1569-8507","affiliations":[{"raw_affiliation_string":"Institute of Library, Information and Media Science, University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yubo Fang","orcid":"https://orcid.org/0009-0000-2864-0251"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yubo Fang","raw_affiliation_strings":["Graduate School of Comprehensive Human Sciences, University of Tsukuba, Tsukuba, Ibaraki, Japan"],"raw_orcid":"https://orcid.org/0009-0000-2864-0251","affiliations":[{"raw_affiliation_string":"Graduate School of Comprehensive Human Sciences, University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chao Lei","orcid":"https://orcid.org/0009-0007-4319-4078"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chao Lei","raw_affiliation_strings":["Graduate School of Comprehensive Human Sciences, University of Tsukuba, Tsukuba, Ibaraki, Japan"],"raw_orcid":"https://orcid.org/0009-0007-4319-4078","affiliations":[{"raw_affiliation_string":"Graduate School of Comprehensive Human Sciences, University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146399215"],"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":"281","last_page":"291"},"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":0.4327000081539154,"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":0.4327000081539154,"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":0.23819999396800995,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.17810000479221344,"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/identifier","display_name":"Identifier","score":0.7107999920845032},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.657800018787384},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.5447999835014343},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47530001401901245},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4713999927043915},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45260000228881836},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41769999265670776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324000000953674},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7107999920845032},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.657800018787384},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49149999022483826},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41769999265670776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38670000433921814},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.3822999894618988},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767695.3769474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3767695.3769474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7405089139938354}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2144211451","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2546696630","https://openalex.org/W2618530766","https://openalex.org/W2883311563","https://openalex.org/W2962964995","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W3175888430","https://openalex.org/W4312629998","https://openalex.org/W4312910992","https://openalex.org/W4312911498","https://openalex.org/W4312974539","https://openalex.org/W4386072185","https://openalex.org/W4386075677","https://openalex.org/W4386302269","https://openalex.org/W4387848863","https://openalex.org/W4389519018","https://openalex.org/W4389523905","https://openalex.org/W4393153307","https://openalex.org/W4396723267","https://openalex.org/W4400528921","https://openalex.org/W4405165403","https://openalex.org/W4408326921","https://openalex.org/W4409150075","https://openalex.org/W4412376905"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,36,163,195,210,225,243,259,294,310],"plays":[2],"a":[3,41,69,80,83,96,123,131,236],"fundamental":[4],"role":[5],"in":[6,82,110,122,226,254,257,304],"bridging":[7],"distinct":[8],"information":[9,170],"sources,":[10],"such":[11,266],"as":[12,40,166,267],"text,":[13],"images,":[14],"and":[15,72,261,284],"videos.":[16],"Different":[17],"from":[18],"the":[19,45,60,74,87,93,111,117,143,150,158,169,174,191,247,268,273,281,285,293,305],"traditional":[20],"methods":[21],"that":[22,63,106,239],"predominantly":[23],"rely":[24],"on":[25,178,201],"discriminative":[26],"matching":[27],"via":[28],"cross-attention":[29],"or":[30],"joint":[31],"embedding":[32],"spaces,":[33],"generative":[34,135,193,209,242,308],"cross-modal":[35,136],"has":[37],"recently":[38],"emerged":[39],"new":[42],"paradigm.":[43],"Despite":[44],"improvements":[46,256],"achieved":[47],"by":[48,68,76,173,245],"recent":[49],"studies,":[50],"there":[51],"are":[52,301],"still":[53,218],"many":[54],"open":[55],"questions.":[56],"For":[57],"instance,":[58],"given":[59],"conventional":[61],"setting":[62],"representing":[64],"each":[65],"candidate":[66,277],"item":[67,107],"unique":[70],"identifier":[71,99],"expanding":[73],"prefix":[75,94],"one":[77],"token":[78],"at":[79],"time":[81],"greedy":[84],"manner":[85],"during":[86,149],"constrained":[88,151],"beam":[89,152,282],"search":[90,153],"process,":[91,154],"once":[92],"of":[95,119,145,160,222,228,270,275,287,298,307],"relevant":[97],"item's":[98],"is":[100],"pruned,":[101],"it":[102,217],"becomes":[103],"impossible":[104],"for":[105,134],"to":[108,116,167,279],"appear":[109],"final":[112],"result":[113],"list,":[114],"leading":[115],"risk":[118],"getting":[120],"stuck":[121],"local":[124],"optimum.":[125],"In":[126],"this":[127,232],"paper,":[128],"we":[129,139,234],"develop":[130],"combination-based":[132],"framework":[133],"retrieval.":[137],"Specifically,":[138],"not":[140],"only":[141],"explore":[142],"effectiveness":[144],"imposing":[146],"dual":[147,202],"identifiers":[148,203,213],"but":[155],"also":[156],"investigate":[157],"benefits":[159],"combining":[161,288],"different":[162],"strategies":[164,290],"so":[165],"mitigate":[168],"loss":[171],"caused":[172],"discrete":[175,212],"representations.":[176],"Based":[177],"two":[179],"benchmark":[180],"collections,":[181],"our":[182,197],"extensive":[183],"empirical":[184],"experiments":[185],"reveal":[186],"that:":[187],"(1)":[188],"Compared":[189],"with":[190,211],"state-of-the-art":[192],"text-image":[194,309],"method,":[196],"proposed":[198],"approach":[199],"based":[200],"achieves":[204],"substantially":[205],"improved":[206],"performance.":[207,229,295],"Although":[208],"offers":[214],"higher":[215],"efficiency,":[216],"falls":[219],"significantly":[220,291],"short":[221],"dense":[223,251],"embedding-based":[224],"terms":[227],"To":[230],"overcome":[231],"limitation,":[233],"propose":[235],"hybrid":[237],"strategy":[238],"performs":[240],"initial":[241],"followed":[244],"reranking":[246],"top-k":[248],"candidates":[249],"using":[250],"embeddings,":[252],"resulting":[253],"notable":[255],"both":[258],"performance":[260],"efficiency.":[262],"(2)":[263],"The":[264],"factors,":[265],"choice":[269],"base":[271],"LLMs,":[272],"number":[274],"top":[276],"items":[278],"rerank,":[280],"size":[283],"way":[286],"ranking":[289],"influence":[292],"Careful":[296],"examinations":[297],"these":[299],"factors":[300],"highly":[302],"recommended":[303],"development":[306],"methods.":[311]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-03T00:00:00"}