{"id":"https://openalex.org/W7164836594","doi":"https://doi.org/10.1145/3805622.3810597","title":"Ask-to-Retrieve: VQA-Guided Information-Gain Question Selection for Interactive Text-to-Image Retrieval","display_name":"Ask-to-Retrieve: VQA-Guided Information-Gain Question Selection for Interactive Text-to-Image Retrieval","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164836594","doi":"https://doi.org/10.1145/3805622.3810597"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810597","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002884659","display_name":"S Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaiwei Xie","raw_affiliation_strings":["Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0008-4079-0349","affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China","institution_ids":["https://openalex.org/I4210106108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034313244","display_name":"Yating Yang","orcid":"https://orcid.org/0000-0002-2639-3944"},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yating Yang","raw_affiliation_strings":["Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-2639-3944","affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China","institution_ids":["https://openalex.org/I4210106108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101910437","display_name":"Bo Ma","orcid":"https://orcid.org/0000-0003-3082-648X"},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ma","raw_affiliation_strings":["Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-3082-648X","affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China","institution_ids":["https://openalex.org/I4210106108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612275","display_name":"Xi Zhou","orcid":"https://orcid.org/0000-0003-2867-1765"},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Zhou","raw_affiliation_strings":["Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-2867-1765","affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China","institution_ids":["https://openalex.org/I4210106108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338337","display_name":"Zi Wang","orcid":"https://orcid.org/0000-0002-7361-1406"},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0001-9285-3040","affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China","institution_ids":["https://openalex.org/I4210106108"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092501202","display_name":"Ahtamjan Ahmat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ahtamjan Ahmat","raw_affiliation_strings":["Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-6660-8989","affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi, China; University of Chinese Academy of Sciences, Beijing, China and Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi, China","institution_ids":["https://openalex.org/I4210106108"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93725765,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1740","last_page":"1748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9671000242233276,"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":0.9671000242233276,"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":0.02199999988079071,"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":0.0024999999441206455,"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":0.7656999826431274},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5418000221252441},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4814000129699707},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4641000032424927},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4571000039577484},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.44209998846054077},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42570000886917114},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4214000105857849},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4156999886035919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768999934196472},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7656999826431274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5806000232696533},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4814000129699707},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4641999900341034},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.44209998846054077},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4214000105857849},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7576503157615662,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2014018052","https://openalex.org/W2024550919","https://openalex.org/W2102563107","https://openalex.org/W2104049510","https://openalex.org/W2157726995","https://openalex.org/W3090449556","https://openalex.org/W4304084237","https://openalex.org/W4312913651","https://openalex.org/W4386065863","https://openalex.org/W4386076084","https://openalex.org/W4389164417","https://openalex.org/W4389518671","https://openalex.org/W4389518951","https://openalex.org/W4401042996","https://openalex.org/W4402667053","https://openalex.org/W4402671616","https://openalex.org/W4407049645","https://openalex.org/W4409269797","https://openalex.org/W4409364271","https://openalex.org/W4412377291","https://openalex.org/W4412945269","https://openalex.org/W7133190413"],"related_works":[],"abstract_inverted_index":{"Interactive":[0],"image":[1,34],"retrieval":[2,9,89,169],"iteratively":[3],"interacts":[4],"with":[5],"users":[6],"to":[7,39,56,63,104,120,135,174],"capture":[8,64,121],"intent":[10],"and":[11,19,150,161,171],"refine":[12],"textual":[13],"queries,":[14],"effectively":[15],"mitigating":[16],"the":[17,57,75,152],"ambiguity":[18],"performance":[20],"degradation":[21],"inherent":[22],"in":[23,87],"single-round":[24],"text-to-image":[25],"retrieval.":[26],"However,":[27],"existing":[28],"LLM-based":[29],"methods":[30],"largely":[31],"rely":[32],"on":[33,158],"captions":[35],"or":[36,61],"dialogue":[37],"history":[38],"extract":[40],"features":[41],"within":[42],"a":[43,99,109,116,126,140],"limited":[44],"candidate":[45],"space.":[46],"Consequently,":[47],"they":[48],"often":[49],"generate":[50],"questions":[51,149],"that":[52,164],"are":[53],"either":[54],"irrelevant":[55],"target\u2019s":[58],"distinctive":[59],"characteristics":[60],"fail":[62],"fine-grained":[65],"visual":[66,118,123],"differences.":[67],"Furthermore,":[68],"an":[69],"effective":[70],"question":[71],"should":[72],"efficiently":[73],"distinguish":[74],"target":[76],"from":[77],"non-target":[78],"samples\u2014a":[79],"critical":[80],"aspect":[81],"overlooked":[82],"by":[83],"prior":[84],"works,":[85],"resulting":[86],"suboptimal":[88],"efficiency.":[90],"To":[91],"bridge":[92],"this":[93,133],"gap,":[94],"we":[95],"present":[96],"A2R":[97],"(Ask-to-Retrieve),":[98],"visually":[100],"grounded":[101],"framework":[102],"designed":[103],"maximize":[105],"information":[106],"gain.":[107],"Specifically,":[108],"Diversity":[110],"Candidate":[111],"Perception":[112],"(DCP)":[113],"module":[114,131,146],"constructs":[115],"compact":[117],"grid":[119,134],"diverse":[122],"semantics.":[124],"Subsequently,":[125],"Discriminative":[127],"Question":[128],"Generation":[129],"(DQG)":[130],"observes":[132],"propose":[136],"discriminative":[137],"questions.":[138],"Finally,":[139],"Maximum":[141],"Information":[142],"Gain":[143],"Decision":[144],"(IGD)":[145],"evaluates":[147],"these":[148],"selects":[151],"one":[153],"maximizing":[154],"entropy":[155],"reduction.":[156],"Experiments":[157],"VisDial,":[159],"COCO,":[160],"Flickr30k":[162],"demonstrate":[163],"our":[165],"method":[166],"achieves":[167],"superior":[168],"accuracy":[170],"efficiency":[172],"compared":[173],"strong":[175],"baselines.":[176]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}