{"id":"https://openalex.org/W4409657081","doi":"https://doi.org/10.1145/3696410.3714777","title":"ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning","display_name":"ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657081","doi":"https://doi.org/10.1145/3696410.3714777"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714777","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696410.3714777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","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":"https://openalex.org/A5102705773","display_name":"Pengfei Luo","orcid":"https://orcid.org/0000-0003-0889-7660"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Luo","raw_affiliation_strings":["School of Computer Science and Technology, State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0889-7660","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101481194","display_name":"Jingbo Zhou","orcid":"https://orcid.org/0000-0003-2677-7021"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhou","raw_affiliation_strings":["Business Intelligence Lab, Baidu Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2677-7021","affiliations":[{"raw_affiliation_string":"Business Intelligence Lab, Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025292786","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0003-4246-5386"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xu","raw_affiliation_strings":["School of Computer Science and Technology, State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4246-5386","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109191842","display_name":"Yuan Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Xia","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-3993-3632","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009732907","display_name":"Linli Xu","orcid":"https://orcid.org/0000-0003-0227-3793"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linli Xu","raw_affiliation_strings":["School of Computer Science and Technology, State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0227-3793","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["School of Computer Science and Technology, State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4835-4102","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.3323,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97745826,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1666","last_page":"1682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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":0.778475821018219},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5450525283813477},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4870636761188507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4776969254016876},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45304372906684875},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3448057472705841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778475821018219},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5450525283813477},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4870636761188507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4776969254016876},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45304372906684875},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3448057472705841}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714777","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696410.3714777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2026103844","https://openalex.org/W2046589280","https://openalex.org/W2081059587","https://openalex.org/W2092361219","https://openalex.org/W2114207967","https://openalex.org/W2118597426","https://openalex.org/W2185175083","https://openalex.org/W2768603575","https://openalex.org/W2905544595","https://openalex.org/W3016211260","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3172514680","https://openalex.org/W3176909828","https://openalex.org/W4225750637","https://openalex.org/W4299670242","https://openalex.org/W4301356211","https://openalex.org/W4312825288","https://openalex.org/W4312940158","https://openalex.org/W4361194219","https://openalex.org/W4367310104","https://openalex.org/W4386071700","https://openalex.org/W4386080721","https://openalex.org/W4396718663","https://openalex.org/W4400526206","https://openalex.org/W4402727158","https://openalex.org/W4402727764","https://openalex.org/W4403780651","https://openalex.org/W4409362682","https://openalex.org/W6601141708","https://openalex.org/W6601796474"],"related_works":["https://openalex.org/W2087793626","https://openalex.org/W3188962172","https://openalex.org/W3204019825","https://openalex.org/W1986902711","https://openalex.org/W2396760013","https://openalex.org/W2148433556","https://openalex.org/W2171776552","https://openalex.org/W98391849","https://openalex.org/W1600907701","https://openalex.org/W2726741344"],"abstract_inverted_index":{"With":[0],"the":[1,19,32,52,115,119,137,148,154,159,162,179,219],"proliferation":[2],"of":[3,25,34,54,122,139,161,171,221],"images":[4],"in":[5,49,118,153],"online":[6],"content,":[7,80],"language-guided":[8],"image":[9,79],"retrieval":[10,85,133,188],"(LGIR)":[11],"has":[12,39],"emerged":[13],"as":[14,142],"a":[15,23,99,130,143],"research":[16],"hotspot":[17],"over":[18],"past":[20],"decade,":[21],"encompassing":[22],"variety":[24],"subtasks":[26],"with":[27,136],"diverse":[28,126],"input":[29],"forms.":[30],"While":[31],"development":[33],"large":[35],"multimodal":[36],"models":[37],"(LMMs)":[38],"significantly":[40],"facilitated":[41],"these":[42],"tasks,":[43],"existing":[44],"approaches":[45],"often":[46],"address":[47],"them":[48],"isolation,":[50],"requiring":[51],"construction":[53],"separate":[55],"systems":[56,86],"for":[57,84],"each":[58],"task.":[59],"This":[60],"not":[61],"only":[62],"increases":[63],"system":[64],"complexity":[65],"and":[66,77,90,181,195,214],"maintenance":[67],"costs,":[68],"but":[69],"also":[70],"exacerbates":[71],"challenges":[72],"stemming":[73],"from":[74],"language":[75],"ambiguity":[76],"complex":[78],"making":[81],"it":[82],"difficult":[83],"to":[87,107,146],"provide":[88],"accurate":[89],"reliable":[91],"results.":[92,149],"To":[93,150],"this":[94],"end,":[95],"we":[96,157,184],"propose":[97],"ImageScope,":[98],"training-free,":[100],"three-stage":[101],"framework":[102,163],"that":[103,207],"leverages":[104],"collective":[105],"reasoning":[106,138],"unify":[108],"LGIR":[109,127,204],"tasks.":[110],"The":[111],"key":[112],"insight":[113],"behind":[114],"unification":[116],"lies":[117],"compositional":[120],"nature":[121],"language,":[123],"which":[124],"transforms":[125],"tasks":[128],"into":[129],"generalized":[131],"text-to-image":[132],"process,":[134],"along":[135],"LMMs":[140],"serving":[141],"universal":[144],"verification":[145],"refine":[147],"be":[151],"specific,":[152],"first":[155],"stage,":[156],"improve":[158],"robustness":[160],"by":[164,190],"synthesizing":[165],"search":[166],"intents":[167],"across":[168],"varying":[169],"levels":[170],"semantic":[172],"granularity":[173],"using":[174],"chain-of-thought":[175],"(CoT)":[176],"reasoning.":[177],"In":[178],"second":[180],"third":[182],"stages,":[183],"then":[185],"reflect":[186],"on":[187,202],"results":[189],"verifying":[191],"predicate":[192],"propositions":[193],"locally,":[194],"performing":[196],"pairwise":[197],"evaluations":[198,213],"globally.":[199],"Experiments":[200],"conducted":[201],"six":[203],"datasets":[205],"demonstrate":[206],"ImageScope":[208],"outperforms":[209],"competitive":[210],"baselines.":[211],"Comprehensive":[212],"ablation":[215],"studies":[216],"further":[217],"confirm":[218],"effectiveness":[220],"our":[222],"design.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-19T15:00:24.278416","created_date":"2025-10-10T00:00:00"}