{"id":"https://openalex.org/W4412825739","doi":"https://doi.org/10.1145/3711896.3736982","title":"Generative Thinking, Corrective Action: User-Friendly Composed Image Retrieval via Automatic Multi-Agent Collaboration","display_name":"Generative Thinking, Corrective Action: User-Friendly Composed Image Retrieval via Automatic Multi-Agent Collaboration","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4412825739","doi":"https://doi.org/10.1145/3711896.3736982"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736982","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3736982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","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/A5079708113","display_name":"Zhangtao Cheng","orcid":"https://orcid.org/0000-0002-0097-3617"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhangtao Cheng","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596729","display_name":"Yuhao Ma","orcid":"https://orcid.org/0000-0001-6134-8359"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Ma","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078656869","display_name":"Jian Lang","orcid":"https://orcid.org/0009-0009-0876-0497"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Lang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014223717","display_name":"Kunpeng Zhang","orcid":"https://orcid.org/0000-0002-1474-3169"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunpeng Zhang","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034789908","display_name":"Ting Zhong","orcid":"https://orcid.org/0000-0002-8163-3146"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Zhong","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102742311","display_name":"Yong J. Wang","orcid":"https://orcid.org/0000-0002-8699-8355"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":["Aiwen Tech, Zhengzhou, Henan, China and Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Aiwen Tech, Zhengzhou, Henan, China and Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403505","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0002-8038-8150"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210139481","display_name":"Science and Technology Department of Sichuan Province","ror":"https://ror.org/04323m874","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210139481"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China and Key Laboratory of Intelligent Digital Media Technology of Sichuan Province, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China and Key Laboratory of Intelligent Digital Media Technology of Sichuan Province, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I4210139481","https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5079708113"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.319,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83494814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"334","last_page":"344"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.988099992275238,"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":0.9864000082015991,"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":0.7881059646606445},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6042828559875488},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5779934525489807},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5581908226013184},{"id":"https://openalex.org/keywords/user-friendly","display_name":"User Friendly","score":0.5530145168304443},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4641749858856201},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4601387083530426},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4537213444709778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4197740852832794},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15003320574760437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7881059646606445},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6042828559875488},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5779934525489807},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5581908226013184},{"id":"https://openalex.org/C61437842","wikidata":"https://www.wikidata.org/wiki/Q281291","display_name":"User Friendly","level":2,"score":0.5530145168304443},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4641749858856201},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4601387083530426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4537213444709778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4197740852832794},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15003320574760437},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3736982","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3736982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","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/W398859631","https://openalex.org/W1861492603","https://openalex.org/W2084092936","https://openalex.org/W2905544595","https://openalex.org/W2963530300","https://openalex.org/W2964211610","https://openalex.org/W3028571922","https://openalex.org/W3095954321","https://openalex.org/W3172514680","https://openalex.org/W3184735396","https://openalex.org/W3203247393","https://openalex.org/W4225832925","https://openalex.org/W4312825288","https://openalex.org/W4313172370","https://openalex.org/W4317619144","https://openalex.org/W4379466097","https://openalex.org/W4386071700","https://openalex.org/W4389980157","https://openalex.org/W4390190619","https://openalex.org/W4390873539","https://openalex.org/W4390874566","https://openalex.org/W4392172801","https://openalex.org/W4395483878","https://openalex.org/W4399911186","https://openalex.org/W4400528838","https://openalex.org/W4401863447","https://openalex.org/W4409149309","https://openalex.org/W4409366118","https://openalex.org/W4410090375","https://openalex.org/W4410226412","https://openalex.org/W6912494966"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W4383031710","https://openalex.org/W3211753092","https://openalex.org/W2386000789"],"abstract_inverted_index":{"Zero-shot":[0],"composed":[1,17,125],"image":[2,22,48],"retrieval":[3,43,63,67],"(ZS-CIR)":[4],"is":[5],"a":[6,16,20,24,75,95,97,100,119,144],"challenging":[7],"task":[8,37],"that":[9,45,103,167],"aims":[10],"to":[11,15,106,132],"retrieve":[12],"images":[13],"similar":[14],"query":[18,126],"of":[19,90,152],"reference":[21],"and":[23,49,65,99,109,127,156],"description,":[25],"without":[26],"relying":[27],"on":[28,30,40,138,163],"training":[29],"triplet":[31],"datasets.":[32],"Existing":[33],"methods":[34,173],"for":[35,82,123,174],"this":[36,130],"often":[38],"rely":[39],"predefined,":[41],"fixed":[42],"processes":[44],"combine":[46],"the":[47,50,115,124,153],"modified":[51],"text":[52],"through":[53],"hand-crafted":[54],"templates,":[55],"which":[56],"suffer":[57],"from":[58],"two":[59],"main":[60],"issues:":[61],"non-adaptive":[62],"queries":[64],"user-unfriendly":[66],"processes.":[68],"To":[69],"address":[70],"these":[71],"limitations,":[72],"we":[73],"propose":[74],"novel":[76],"framework":[77],"-":[78,94,102],"Automatic":[79],"Multi-Agent":[80],"Collaboration":[81],"Zero-Shot":[83],"Composed":[84],"Image":[85],"Retrieval":[86],"(AutoCIR).":[87],"AutoCIR":[88,168],"consists":[89],"three":[91,164],"training-free":[92],"agents":[93],"planner,":[96],"retriever,":[98],"corrector":[101],"work":[104],"together":[105],"iteratively":[107],"identify":[108],"rectify":[110],"mismatches.":[111],"The":[112,140],"planner":[113],"guides":[114],"retriever":[116],"by":[117],"generating":[118],"customized":[120],"target":[121],"caption":[122,131],"further":[128],"refines":[129],"resolve":[133],"any":[134],"semantic":[135],"discrepancies":[136],"based":[137],"feedback.":[139],"corrector,":[141],"equipped":[142],"with":[143],"chain-of-thought":[145],"reasoning":[146],"mechanism,":[147],"conducts":[148],"an":[149],"in-depth":[150],"evaluation":[151],"retrieved":[154],"results":[155],"generates":[157],"appropriate":[158],"self-correction":[159],"actions.":[160],"Extensive":[161],"experiments":[162],"benchmarks":[165],"demonstrate":[166],"consistently":[169],"outperforms":[170],"previous":[171],"competitive":[172],"ZS-CIR.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
