{"id":"https://openalex.org/W4415708638","doi":"https://doi.org/10.1109/icme59968.2025.11209393","title":"Slot Inversion for Asymmetric Composed Image Retrieval","display_name":"Slot Inversion for Asymmetric Composed Image Retrieval","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708638","doi":"https://doi.org/10.1109/icme59968.2025.11209393"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5091626025","display_name":"Haiwen Li","orcid":"https://orcid.org/0000-0001-7223-1754"},"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,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057033260","display_name":"Zining Chen","orcid":"https://orcid.org/0009-0007-4214-1054"},"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":"Zining Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414402","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0003-1331-997X"},"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":"Ying Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101754632","display_name":"Fei Su","orcid":"https://orcid.org/0000-0003-4245-4687"},"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,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113395474","display_name":"Zhicheng Zhao","orcid":"https://orcid.org/0009-0002-5354-8515"},"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,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5874999761581421,"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":0.5874999761581421,"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":0.26330000162124634,"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":0.08540000021457672,"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/image-retrieval","display_name":"Image retrieval","score":0.7397000193595886},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.6237000226974487},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45559999346733093},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.373199999332428},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3249000012874603},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3089999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555000185966492},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.7397000193595886},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6237000226974487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46939998865127563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41850000619888306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.373199999332428},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.28369998931884766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":9,"referenced_works":["https://openalex.org/W3172514680","https://openalex.org/W3181190847","https://openalex.org/W3203247393","https://openalex.org/W4312825288","https://openalex.org/W4386071700","https://openalex.org/W4386076539","https://openalex.org/W4394625619","https://openalex.org/W4399251441","https://openalex.org/W4403760443"],"related_works":[],"abstract_inverted_index":{"Composed":[0,49],"Image":[1,50],"Retrieval":[2,51],"(CIR)":[3],"is":[4,58,103,137],"a":[5,41,80],"challenging":[6],"vision-language":[7],"(VL)":[8],"task":[9],"that":[10],"retrieves":[11],"target":[12],"images":[13],"using":[14],"multi-modal":[15],"(image+text)":[16],"queries.":[17],"Although":[18],"significant":[19],"progress":[20],"has":[21],"been":[22],"made":[23],"in":[24,30],"existing":[25],"CIR":[26],"approaches,":[27],"their":[28],"deployment":[29],"resource-constrained":[31],"scenarios":[32],"remains":[33],"problematic.":[34],"To":[35],"address":[36],"this":[37],"issue,":[38],"we":[39,78],"propose":[40],"novel":[42],"framework,":[43],"named":[44],"Slot":[45],"Inversion":[46],"for":[47],"Asymmetric":[48],"(Slot4ACir),":[52],"where":[53],"an":[54,90],"asymmetric":[55],"retrieval":[56],"scheme":[57],"adopted:":[59],"lightweight":[60,81],"models":[61,71],"are":[62],"employed":[63],"on":[64,73,85,125],"the":[65,74,100,111,117,130],"query":[66],"side,":[67],"while":[68],"large-scale":[69],"VL":[70],"operate":[72],"gallery":[75],"side.":[76],"Specifically,":[77],"introduce":[79],"inversion":[82],"module":[83],"based":[84],"slot":[86],"attention,":[87],"which":[88],"maps":[89],"image":[91],"into":[92],"multiple":[93],"textual":[94],"tokens":[95],"with":[96],"distinct":[97],"semantics.":[98],"Additionally,":[99],"LLM":[101],"sampler":[102],"proposed":[104],"to":[105],"facilitate":[106],"richer":[107],"semantic":[108],"interactions,":[109],"and":[110],"distillation":[112],"alignment":[113],"(DTA)":[114],"loss":[115],"enables":[116],"extraction":[118],"of":[119,132],"more":[120],"informative":[121],"representations.":[122],"Extensive":[123],"experiments":[124],"two":[126],"popular":[127],"benchmarks":[128],"demonstrate":[129],"effectiveness":[131],"our":[133],"approach.":[134],"The":[135],"code":[136],"now":[138],"available":[139],"at":[140],"https://github.com/JThuge/Slot4ACir.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}