{"id":"https://openalex.org/W7137832591","doi":"https://doi.org/10.1609/aaai.v40i8.37534","title":"Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrieval","display_name":"Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrieval","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137832591","doi":"https://doi.org/10.1609/aaai.v40i8.37534"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37534","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37534","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i8.37534","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129684250","display_name":"Haiwen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwen Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129710661","display_name":"Delong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Delong Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112294881","display_name":"Zhaohui Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohui Hou","raw_affiliation_strings":["SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129732701","display_name":"Zeliang Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeliang Ma","raw_affiliation_strings":["SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704185","display_name":"Fei Su","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications\nBeijing Key Laboratory of Network System and Network Culture\nKey Laboratory of Intereactive Technology and Experience System"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications\nBeijing Key Laboratory of Network System and Network Culture\nKey Laboratory of Intereactive Technology and Experience System","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129642271","display_name":"Zhicheng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Zhao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications\nBeijing Key Laboratory of Network System and Network Culture\nKey Laboratory of Intereactive Technology and Experience System"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications\nBeijing Key Laboratory of Network System and Network Culture\nKey Laboratory of Intereactive Technology and Experience System","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.04202279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6100","last_page":"6108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7996000051498413,"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":0.7996000051498413,"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":0.11050000041723251,"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":0.03400000184774399,"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/encoder","display_name":"Encoder","score":0.5817999839782715},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5311999917030334},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.498199999332428},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46619999408721924},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4593999981880188},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45669999718666077},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.43810001015663147},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43160000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474999785423279},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.498199999332428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4593999981880188},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.43810001015663147},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4251999855041504},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36079999804496765},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37534","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37534","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37534","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37534","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37534","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5237213373184204,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"a":[1,80,96,103,108,112,125,157],"challenging":[2,201],"vision-language":[3],"task,":[4],"Zero-Shot":[5],"Composed":[6],"Image":[7],"Retrieval":[8],"(ZS-CIR)":[9],"is":[10,194],"designed":[11],"to":[12,27,101,134,161,181,196,200],"retrieve":[13],"target":[14,118],"images":[15],"using":[16,138],"bi-modal":[17],"(image+text)":[18],"queries.":[19],"Typical":[20],"ZS-CIR":[21],"methods":[22,40,218],"employ":[23],"an":[24,190],"inversion":[25,52,178],"network":[26],"generate":[28],"pseudo-word":[29],"tokens":[30],"that":[31],"effectively":[32],"represent":[33],"the":[34,38,47,61,66,117,131,135,145,172,177,184,211],"input":[35,67,180],"semantics.":[36],"However,":[37],"inversion-based":[39,217],"suffer":[41],"from":[42,65],"two":[43,86],"inherent":[44],"issues:":[45],"First,":[46],"task":[48,137,152],"discrepancy":[49,63],"exists":[50],"because":[51],"training":[53,72],"and":[54,73,165],"CIR":[55,136],"inference":[56],"involve":[57],"different":[58,167],"objectives.":[59],"Second,":[60],"modality":[62],"arises":[64],"feature":[68],"distribution":[69],"mismatch":[70],"between":[71],"inference.":[74],"To":[75],"this":[76],"end,":[77],"we":[78],"propose":[79],"lightweight":[81],"post-hoc":[82],"framework,":[83],"consisting":[84],"of":[85,119,150,169,213],"components:":[87],"(1)":[88],"A":[89],"new":[90],"text-anchored":[91],"triplet":[92,109,141],"construction":[93],"pipeline":[94],"leverages":[95],"large":[97],"language":[98],"model":[99],"(LLM)":[100],"transform":[102],"standard":[104],"image-text":[105],"dataset":[106],"into":[107],"dataset,":[110],"where":[111],"textual":[113],"description":[114],"serves":[115],"as":[116],"each":[120],"triplet.":[121],"(2)":[122],"The":[123],"MoTa-Adapter,":[124],"novel":[126],"parameter-efficient":[127],"fine-tuning":[128],"method,":[129],"adapts":[130],"dual":[132],"encoder":[133],"our":[139,214],"constructed":[140],"data.":[142],"Specifically,":[143],"on":[144],"text":[146,186],"side,":[147,174],"multiple":[148],"sets":[149],"learnable":[151],"prompts":[153],"are":[154],"integrated":[155],"via":[156],"Mixture-of-Experts":[158],"(MoE)":[159],"layer":[160],"capture":[162],"task-specific":[163],"priors":[164],"handle":[166],"types":[168],"modifications.":[170],"On":[171],"image":[173],"MoTa-Adapter":[175],"modulates":[176],"network's":[179],"better":[182],"match":[183],"downstream":[185],"encoder.":[187],"In":[188],"addition,":[189],"entropy-based":[191],"optimization":[192],"strategy":[193],"proposed":[195,215],"assign":[197],"greater":[198],"weight":[199],"samples,":[202],"thus":[203],"improving":[204],"adaptation":[205],"efficiency.":[206],"Experiments":[207],"show":[208],"that,":[209],"with":[210],"incorporation":[212],"components,":[216],"achieve":[219],"significant":[220],"improvements,":[221],"reaching":[222],"state-of-the-art":[223],"performance":[224],"across":[225],"four":[226],"widely-used":[227],"benchmarks.":[228]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}