{"id":"https://openalex.org/W4411552994","doi":"https://doi.org/10.1145/3733566.3734431","title":"AMF: Adaptive Modality Fusion for Zero-Shot Composed Image Retrieval","display_name":"AMF: Adaptive Modality Fusion for Zero-Shot Composed Image Retrieval","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411552994","doi":"https://doi.org/10.1145/3733566.3734431"},"language":"en","primary_location":{"id":"doi:10.1145/3733566.3734431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3733566.3734431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","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/A5100585766","display_name":"Shuping Hui","orcid":null},"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":true,"raw_author_name":"Shuping Hui","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0003-1059-6549","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340979","display_name":"Min Wang","orcid":"https://orcid.org/0000-0003-3048-6980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["Hefei Comprehensive National Science Center, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-3048-6980","affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center, Hefei, Anhui, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045796157","display_name":"Hui Wu","orcid":"https://orcid.org/0009-0009-2353-3508"},"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":"Hui Wu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0009-2353-3508","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"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":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-1690-9836","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"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":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-3028","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100585766"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11816941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9986000061035156,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6229175329208374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.598944365978241},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.566872239112854},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5446504950523376},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5260303616523743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5144241452217102},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5128231644630432},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.48675537109375},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4447228014469147},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11232602596282959}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6229175329208374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.598944365978241},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.566872239112854},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5446504950523376},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5260303616523743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5144241452217102},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5128231644630432},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.48675537109375},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4447228014469147},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11232602596282959},{"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/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3733566.3734431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3733566.3734431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","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":6,"referenced_works":["https://openalex.org/W2905544595","https://openalex.org/W4386071700","https://openalex.org/W4390873539","https://openalex.org/W4393159265","https://openalex.org/W4402727158","https://openalex.org/W4405079042"],"related_works":["https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969","https://openalex.org/W2284201331","https://openalex.org/W2095903272","https://openalex.org/W1989561795"],"abstract_inverted_index":{"Composed":[0],"image":[1,11,94,101],"retrieval":[2,46],"seeks":[3],"to":[4,83],"retrieve":[5],"images":[6,28,113],"based":[7],"on":[8,99],"a":[9,13,23,54,63,68,79],"reference":[10],"and":[12,29,33,67,110,114],"text":[14,87,108,115,118],"modification":[15,109],"reflecting":[16],"user":[17],"intent.":[18],"Existing":[19],"approaches":[20],"typically":[21],"utilize":[22],"zero-shot":[24],"learning":[25],"framework,":[26],"aligning":[27],"texts":[30],"during":[31],"training":[32,70],"fusing":[34],"them":[35],"at":[36],"inference.":[37],"However,":[38],"the":[39,73,117,126],"discrepancy":[40],"between":[41],"these":[42],"stages":[43],"can":[44],"hinder":[45],"performance.":[47],"To":[48],"address":[49],"this":[50],"issue,":[51],"we":[52,77,106],"propose":[53],"plug-and-play":[55],"method":[56],"called":[57],"Adaptive":[58],"Modality":[59],"Fusion":[60],"(AMF),":[61],"comprising":[62],"data":[64,74],"collection":[65,75],"stage":[66],"model":[69,82,104],"stage.":[71],"In":[72],"stage,":[76],"employ":[78],"multimodal":[80],"large":[81],"generate":[84],"(reference":[85],"image,":[86],"modification,":[88],"target":[89],"text)":[90],"triplets":[91],"from":[92],"an":[93],"dataset,":[95],"thus":[96],"reducing":[97],"dependence":[98],"scarce":[100],"pairs.":[102],"During":[103],"training,":[105],"incorporate":[107],"adaptively":[111],"fuse":[112],"via":[116],"encoder.":[119],"Extensive":[120],"experiments":[121],"across":[122],"four":[123],"benchmarks":[124],"demonstrate":[125],"superiority":[127],"of":[128],"our":[129],"approach.":[130],"The":[131],"source":[132],"code":[133],"will":[134],"be":[135],"released":[136],"for":[137],"public":[138],"access.":[139]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}