{"id":"https://openalex.org/W4411403432","doi":"https://doi.org/10.1145/3744910","title":"Interactive Image Retrieval Meets Query Rewriting with Large Language and Vision Language Models","display_name":"Interactive Image Retrieval Meets Query Rewriting with Large Language and Vision Language Models","publication_year":2025,"publication_date":"2025-06-18","ids":{"openalex":"https://openalex.org/W4411403432","doi":"https://doi.org/10.1145/3744910"},"language":"en","primary_location":{"id":"doi:10.1145/3744910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744910","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/interactive-image-retrieval-meets-query-rewriting-with-large-language-and-vision-language-models(6caadbaf-bc4c-45e6-bc5c-c8c74e7481d9).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044091982","display_name":"Hongyi Zhu","orcid":"https://orcid.org/0009-0006-0298-0905"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hongyi Zhu","raw_affiliation_strings":["University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0009-0006-0298-0905","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091066062","display_name":"Jia-Hong Huang","orcid":"https://orcid.org/0000-0001-7943-2591"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jia-Hong Huang","raw_affiliation_strings":["University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-7943-2591","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021445324","display_name":"Yixian Shen","orcid":"https://orcid.org/0000-0001-8447-872X"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yixian Shen","raw_affiliation_strings":["University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8447-872X","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075331928","display_name":"Stevan Rudinac","orcid":"https://orcid.org/0000-0003-1904-8736"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Stevan Rudinac","raw_affiliation_strings":["University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1904-8736","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055639036","display_name":"Evangelos Kanoulas","orcid":"https://orcid.org/0000-0002-8312-0694"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Evangelos Kanoulas","raw_affiliation_strings":["University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-8312-0694","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8858266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"21","issue":"10","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.9178098440170288},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6732376217842102},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.667461633682251},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6408727169036865},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.533452033996582},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5145022869110107},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.514234721660614},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5116506218910217},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5042065382003784},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4393951892852783},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.42952004075050354},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.42767682671546936},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3888915479183197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3788728415966034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9178098440170288},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6732376217842102},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.667461633682251},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6408727169036865},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.533452033996582},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5145022869110107},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.514234721660614},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5116506218910217},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5042065382003784},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4393951892852783},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.42952004075050354},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.42767682671546936},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3888915479183197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3788728415966034},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3744910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744910","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:dare.uva.nl:openaire/6caadbaf-bc4c-45e6-bc5c-c8c74e7481d9","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/interactive-image-retrieval-meets-query-rewriting-with-large-language-and-vision-language-models(6caadbaf-bc4c-45e6-bc5c-c8c74e7481d9).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zhu, H, Huang, J-H, Shen, Y, Rudinac, S & Kanoulas, E 2025, 'Interactive Image Retrieval Meets Query Rewriting with Large Language and Vision Language Models', ACM Transactions on Multimedia Computing Communications and Applications, vol. 21, no. 10, 286. https://doi.org/10.1145/3744910","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:dare.uva.nl:publications/6caadbaf-bc4c-45e6-bc5c-c8c74e7481d9","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/6caadbaf-bc4c-45e6-bc5c-c8c74e7481d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhu, H, Huang, J-H, Shen, Y, Rudinac, S & Kanoulas, E 2025, 'Interactive Image Retrieval Meets Query Rewriting with Large Language and Vision Language Models', ACM Transactions on Multimedia Computing Communications and Applications, vol. 21, no. 10, 286. https://doi.org/10.1145/3744910","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/6caadbaf-bc4c-45e6-bc5c-c8c74e7481d9","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/interactive-image-retrieval-meets-query-rewriting-with-large-language-and-vision-language-models(6caadbaf-bc4c-45e6-bc5c-c8c74e7481d9).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zhu, H, Huang, J-H, Shen, Y, Rudinac, S & Kanoulas, E 2025, 'Interactive Image Retrieval Meets Query Rewriting with Large Language and Vision Language Models', ACM Transactions on Multimedia Computing Communications and Applications, vol. 21, no. 10, 286. https://doi.org/10.1145/3744910","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W54257720","https://openalex.org/W219040644","https://openalex.org/W1654865708","https://openalex.org/W1690919088","https://openalex.org/W1946093182","https://openalex.org/W1992113527","https://openalex.org/W1999970330","https://openalex.org/W2006604430","https://openalex.org/W2030640132","https://openalex.org/W2046434597","https://openalex.org/W2059844599","https://openalex.org/W2065096648","https://openalex.org/W2096733369","https://openalex.org/W2105157020","https://openalex.org/W2105981469","https://openalex.org/W2130660124","https://openalex.org/W2155906060","https://openalex.org/W2294130536","https://openalex.org/W2568262903","https://openalex.org/W2750779823","https://openalex.org/W2760390332","https://openalex.org/W2766630207","https://openalex.org/W2908469318","https://openalex.org/W2963588253","https://openalex.org/W2964157791","https://openalex.org/W2973459786","https://openalex.org/W3011906630","https://openalex.org/W3033159379","https://openalex.org/W3033696290","https://openalex.org/W3036320503","https://openalex.org/W3098468692","https://openalex.org/W3155067862","https://openalex.org/W3166125679","https://openalex.org/W4236965008","https://openalex.org/W4247971859","https://openalex.org/W4249502209","https://openalex.org/W4252959399","https://openalex.org/W4285306484","https://openalex.org/W4286696412","https://openalex.org/W4293248017","https://openalex.org/W4313181088","https://openalex.org/W4361766953","https://openalex.org/W4379806382","https://openalex.org/W4396821179","https://openalex.org/W4399039297","https://openalex.org/W4399778443","https://openalex.org/W4409763338"],"related_works":["https://openalex.org/W4234076403","https://openalex.org/W2052625849","https://openalex.org/W2136177730","https://openalex.org/W2576473474","https://openalex.org/W2572349046","https://openalex.org/W2382153208","https://openalex.org/W1160915619","https://openalex.org/W2027155619","https://openalex.org/W2577784223","https://openalex.org/W2230616111"],"abstract_inverted_index":{"Image":[0],"search":[1,19,25],"is":[2],"a":[3,95,106,128,132,157,200,229],"pivotal":[4],"task":[5],"in":[6,94,118,144,204],"multi-media":[7],"and":[8,34,54,66,164,234],"computer":[9],"vision,":[10],"finding":[11],"applications":[12],"across":[13],"diverse":[14],"domains,":[15],"ranging":[16],"from":[17,40],"internet":[18],"to":[20,110,137,169],"medical":[21],"diagnostics.":[22],"Conventional":[23],"image":[24,82,102,145,171,217],"systems":[26],"operate":[27],"by":[28,148,160],"accepting":[29],"textual":[30],"or":[31],"visual":[32],"queries":[33,88,121],"retrieving":[35],"the":[36,41,67,112,162,170,187,211,220,226],"top-relevant":[37],"candidate":[38],"results":[39],"database.":[42],"However,":[43],"prevalent":[44],"methods":[45,58],"often":[46],"rely":[47],"on":[48,90,105,131],"single-turn":[49],"procedures,":[50],"introducing":[51],"potential":[52],"inaccuracies":[53,143],"limited":[55],"recall.":[56,207],"These":[57],"also":[59],"face":[60],"challenges,":[61],"such":[62],"as":[63],"vocabulary":[64],"mismatch":[65],"semantic":[68],"gap,":[69],"constraining":[70],"their":[71],"overall":[72],"effectiveness.":[73],"To":[74,151],"address":[75],"these":[76],"issues,":[77],"we":[78,126,155,185],"propose":[79],"an":[80,101,214,223],"interactive":[81,216],"retrieval":[83,167,172,218],"system":[84,99,192],"capable":[85],"of":[86,114,189,206,213,222,228],"refining":[87],"based":[89,104,130],"user":[91],"relevance":[92],"feedback":[93],"multi-turn":[96],"setting.":[97],"This":[98],"incorporates":[100],"captioner":[103],"vision-language":[107],"model":[108,135],"(VLM)":[109],"enhance":[111],"quality":[113],"text-based":[115,139],"queries,":[116],"resulting":[117],"more":[119],"informative":[120],"with":[122,199],"each":[123,180],"iteration.":[124],"Moreover,":[125],"introduce":[127],"denoiser":[129],"large":[133],"language":[134],"(LLM)":[136],"refine":[138],"query":[140],"expansions,":[141],"mitigating":[142],"descriptions":[146],"generated":[147],"captioning":[149],"models.":[150],"evaluate":[152],"our":[153,190],"system,":[154,219],"curate":[156],"new":[158],"dataset":[159],"adapting":[161],"MSR-VTT":[163],"MSVD":[165],"video":[166],"datasets":[168],"task,":[173],"offering":[174],"multiple":[175],"relevant":[176],"ground-truth":[177],"images":[178],"for":[179],"query.":[181],"Through":[182],"comprehensive":[183],"experiments,":[184],"validate":[186],"effectiveness":[188],"proposed":[191],"against":[193],"baseline":[194],"methods,":[195],"achieving":[196],"state-of-the-art":[197],"performance":[198],"notable":[201],"10%":[202],"improvement":[203],"terms":[205],"Our":[208],"contributions":[209],"encompass":[210],"development":[212],"innovative":[215],"integration":[221],"LLM-based":[224],"denoiser,":[225],"curation":[227],"meticulously":[230],"designed":[231],"evaluation":[232],"dataset,":[233],"thorough":[235],"experimental":[236],"validation.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}