{"id":"https://openalex.org/W4411631881","doi":"https://doi.org/10.1145/3731715.3733298","title":"Contextual Reasoning for Robust Composed Image Retrieval with Vision-Language Models","display_name":"Contextual Reasoning for Robust Composed Image Retrieval with Vision-Language Models","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411631881","doi":"https://doi.org/10.1145/3731715.3733298"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia 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/A5073018274","display_name":"Peng Gao","orcid":"https://orcid.org/0009-0000-0848-9814"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]},{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal University - Hong Kong Baptist University United International College","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]},{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Hong Kong Baptist University, Kowloon Tong, Hong Kong, China and Beijing Normal University-Hong Kong Baptist University United International College, Zhu Hai, Guang Dong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Kowloon Tong, Hong Kong, China and Beijing Normal University-Hong Kong Baptist University United International College, Zhu Hai, Guang Dong, China","institution_ids":["https://openalex.org/I141568987","https://openalex.org/I25254941","https://openalex.org/I12615008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692762","display_name":"Yujian Lee","orcid":"https://orcid.org/0009-0003-2514-3913"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yujian Lee","raw_affiliation_strings":["Hong Kong Baptist University, Kowloon Tong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Kowloon Tong, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407730","display_name":"Xubo Liu","orcid":"https://orcid.org/0009-0004-9950-2672"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey, Guildford, England, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, England, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341698","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-1681-7926"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]},{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]},{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal University - Hong Kong Baptist University United International College","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Beijing Normal University-Hong Kong Baptist University United International College, Zhu Hai, Guang Dong, China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University-Hong Kong Baptist University United International College, Zhu Hai, Guang Dong, China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I25254941","https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059312754","display_name":"Zailong Chen","orcid":"https://orcid.org/0009-0003-8431-5471"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zailong Chen","raw_affiliation_strings":["University of Wollonggong, Wollongong, New South Wales, Australia"],"affiliations":[{"raw_affiliation_string":"University of Wollonggong, Wollongong, New South Wales, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109637442","display_name":"Yiyang Hu","orcid":"https://orcid.org/0000-0003-3478-3616"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiyang Hu","raw_affiliation_strings":["Hong Kong Baptist University, Kowloon Tong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Kowloon Tong, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111209168","display_name":"Guquan Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guquan Jing","raw_affiliation_strings":["Hong Kong Baptist University, Kowloon Tong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Kowloon Tong, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013967667","display_name":"Yunting Lai","orcid":"https://orcid.org/0000-0003-0770-4847"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yunting Lai","raw_affiliation_strings":["Hong Kong Baptist University, Kowloon Tong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Kowloon Tong, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5073018274"],"corresponding_institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987","https://openalex.org/I25254941"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16312627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"357"},"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":0.9991000294685364,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503493428230286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6258466243743896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.537712574005127},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5198965072631836},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47814878821372986},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.44970816373825073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503493428230286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258466243743896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.537712574005127},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5198965072631836},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47814878821372986},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.44970816373825073}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia 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":32,"referenced_works":["https://openalex.org/W2144499799","https://openalex.org/W2194775991","https://openalex.org/W2905544595","https://openalex.org/W3026458074","https://openalex.org/W3154902219","https://openalex.org/W3198377975","https://openalex.org/W3203247393","https://openalex.org/W3206012133","https://openalex.org/W3206569427","https://openalex.org/W4214540501","https://openalex.org/W4312940158","https://openalex.org/W4313855701","https://openalex.org/W4386075952","https://openalex.org/W4386290297","https://openalex.org/W4386501573","https://openalex.org/W4387954097","https://openalex.org/W4390872842","https://openalex.org/W4390879096","https://openalex.org/W4392904577","https://openalex.org/W4393149559","https://openalex.org/W4393154871","https://openalex.org/W4393159792","https://openalex.org/W4394625619","https://openalex.org/W4395483878","https://openalex.org/W4399547912","https://openalex.org/W4402917078","https://openalex.org/W4403791707","https://openalex.org/W4403792529","https://openalex.org/W4405584917","https://openalex.org/W6600018615","https://openalex.org/W6600266142","https://openalex.org/W6601700763"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Composed":[0],"Image":[1],"Retrieval":[2],"(CIR)":[3],"combines":[4],"a":[5,64,80,115,130,149],"reference":[6,54,100],"image":[7,142,162],"with":[8,111],"modification":[9,28,109],"text":[10,29,110,144,160],"for":[11,98],"precise":[12],"and":[13,42,55,71,101,143,157,161,182,202],"flexible":[14],"searches.":[15],"However,":[16],"existing":[17,92],"methods":[18],"face":[19],"two":[20],"key":[21],"challenges:":[22],"first,":[23],"the":[24,31,50,86,108,120,166,179,193],"limited":[25],"information":[26,113],"in":[27,91,165],"hampers":[30],"model's":[32,121,180],"ability":[33],"to":[34,39,74,84],"understand":[35],"user":[36,124],"intent,":[37],"leading":[38],"reduced":[40],"accuracy":[41],"diversity;":[43],"second,":[44],"reliance":[45],"on":[46,187],"unidirectional":[47],"constraints":[48,138],"overlooks":[49],"complementary":[51],"role":[52],"of":[53,88,123],"target":[56,102],"captions.":[57],"In":[58,104],"this":[59],"paper,":[60],"we":[61,78,106,147],"propose":[62],"CR-CIR":[63],"novel":[65],"framework":[66],"that":[67,154,192],"leverages":[68],"Contextual":[69],"Reasoning":[70,132],"vision-language":[72],"models":[73],"enhance":[75,107],"CIR.":[76],"Specifically,":[77],"use":[79],"VLM":[81,116],"(e.g.,":[82,117],"BLIP2)":[83],"address":[85],"scarcity":[87],"textual":[89],"annotations":[90],"datasets":[93,190],"by":[94,139],"generating":[95],"descriptive":[96],"captions":[97],"both":[99,141],"images.":[103],"addition,":[105],"contextual":[112],"using":[114],"MiniCPM),":[118],"enriching":[119],"understanding":[122],"intent.":[125],"Then":[126],"our":[127],"method":[128,195],"incorporates":[129],"Dual":[131],"Modification":[133],"Module,":[134],"which":[135],"imposes":[136],"bidirectional":[137],"integrating":[140],"modalities.":[145],"Additionally,":[146],"introduce":[148],"Modality":[150],"Shift":[151],"Regularization":[152],"Loss":[153],"assumes":[155],"symmetry":[156],"correlation":[158],"between":[159],"domain":[163],"transformations":[164],"latent":[167],"space.":[168],"This":[169],"new":[170],"loss":[171],"function":[172],"enforces":[173],"consistent":[174],"modality":[175],"shifts,":[176],"significantly":[177],"enhancing":[178],"interpretative":[181],"generalization":[183],"abilities.":[184],"Experimental":[185],"results":[186],"benchmark":[188],"CIR":[189],"demonstrate":[191],"proposed":[194],"achieves":[196],"state-of-the-art":[197],"(SOTA)":[198],"performance.":[199],"Our":[200],"code":[201],"dataset":[203],"will":[204],"be":[205],"available":[206],"at":[207],"https://github.com/kola1124/CR-CIR.git.":[208]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
