{"id":"https://openalex.org/W4417073231","doi":"https://doi.org/10.1145/3743093.3770958","title":"Test-time Filtering Boosts Training-free Zero-shot Composed Image Retrieval","display_name":"Test-time Filtering Boosts Training-free Zero-shot Composed Image Retrieval","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073231","doi":"https://doi.org/10.1145/3743093.3770958"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770958","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770958","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770958","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111182134","display_name":"H. Jonathan Chong","orcid":"https://orcid.org/0009-0004-1960-5584"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyue Chong","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-1960-5584","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056439628","display_name":"Lunbo Li","orcid":"https://orcid.org/0000-0003-0834-2075"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lunbo Li","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0834-2075","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064008061","display_name":"Haofeng Zhang","orcid":"https://orcid.org/0000-0002-4039-7618"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofeng Zhang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4039-7618","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4657999873161316,"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":0.4657999873161316,"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":0.32330000400543213,"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":0.1137000024318695,"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":0.713100016117096},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5722000002861023},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4528000056743622},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.446399986743927},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4368000030517578},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4341999888420105},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41819998621940613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511000037193298},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.713100016117096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6769000291824341},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5722000002861023},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4869999885559082},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4528000056743622},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.446399986743927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.375},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.36959999799728394},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3425999879837036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C180462255","wikidata":"https://www.wikidata.org/wiki/Q3559736","display_name":"Standard test image","level":4,"score":0.27390000224113464},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C2986492983","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image matching","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770958","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770958","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3770958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770958","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770958","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1984527801","display_name":null,"funder_award_id":"2025201015","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073231.pdf","grobid_xml":"https://content.openalex.org/works/W4417073231.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2040347185","https://openalex.org/W2065649161","https://openalex.org/W2138621090","https://openalex.org/W2896348597","https://openalex.org/W2963530300","https://openalex.org/W2963686907","https://openalex.org/W2989176720","https://openalex.org/W3172514680","https://openalex.org/W3176641147","https://openalex.org/W3179233662","https://openalex.org/W3203247393","https://openalex.org/W3206569427","https://openalex.org/W4360884927","https://openalex.org/W4379598302","https://openalex.org/W4386065512","https://openalex.org/W4386071700","https://openalex.org/W4386075759","https://openalex.org/W4386867830","https://openalex.org/W4388192471","https://openalex.org/W4390873539","https://openalex.org/W4391136507","https://openalex.org/W4392172801","https://openalex.org/W4393146540","https://openalex.org/W4393159265","https://openalex.org/W4395483878","https://openalex.org/W4399708354","https://openalex.org/W4400526206","https://openalex.org/W4400530983","https://openalex.org/W4400818431","https://openalex.org/W4402352439","https://openalex.org/W4402670135","https://openalex.org/W4402774099","https://openalex.org/W4403792064","https://openalex.org/W4408005474"],"related_works":[],"abstract_inverted_index":{"Composed":[0],"Image":[1],"Retrieval":[2],"(CIR)":[3],"is":[4,102,188,209],"an":[5,119,135,153],"image":[6,14,61,83,140],"retrieval":[7],"task":[8],"where":[9],"users":[10],"provide":[11],"a":[12,21,66,94],"reference":[13,60,82,124],"along":[15,127],"with":[16,128],"modification":[17,63,130],"text":[18,64],"to":[19,32,56,137,160],"retrieve":[20],"target":[22,88,139],"image.":[23,89],"Zero-shot":[24],"CIR":[25],"(ZS-CIR)":[26],"attracts":[27],"significant":[28],"research":[29],"interest":[30],"owing":[31],"its":[33],"strong":[34],"generalization":[35],"capability":[36],"and":[37,49,62,112,163,195],"independence":[38],"from":[39],"labeled":[40],"training":[41],"data.":[42],"Most":[43],"ZS-CIR":[44,96,192,204],"methods":[45],"employ":[46],"late":[47],"fusion":[48],"textual":[50],"inversion,":[51],"but":[52,84],"these":[53,92,151],"approaches":[54],"fail":[55],"precisely":[57],"convert":[58],"the":[59,70,81,87,129,144,156,167],"into":[65,134,147],"target-aligned":[67],"query.":[68],"Consequently,":[69],"final":[71,145],"query":[72,146],"may":[73],"retain":[74],"redundant":[75],"information\u2014such":[76],"as":[77],"elements":[78],"present":[79],"in":[80,86,104],"absent":[85],"To":[90],"address":[91],"limitations,":[93],"training-free":[95],"method":[97,187],"called":[98],"Test-time":[99],"Filtering":[100],"(TTF)":[101],"proposed":[103,186],"this":[105],"paper,":[106],"leveraging":[107],"Large":[108,114],"Language":[109,115],"Models":[110,116],"(LLMs)":[111],"Multimodal":[113],"(MLLMs).":[117],"Specifically,":[118],"MLLM":[120,154],"generates":[121],"captions":[122],"for":[123],"images,":[125],"which,":[126],"text,":[131],"are":[132,176,183],"fed":[133],"LLM":[136],"produce":[138],"descriptions.":[141],"This":[142],"converts":[143],"plain":[148],"text.":[149],"Using":[150],"results,":[152],"filters":[155],"selected":[157],"candidate":[158,171],"images":[159,172],"select":[161],"positive":[162,174],"negative":[164,181],"samples.":[165],"Finally,":[166],"similarity":[168],"scores":[169],"of":[170,180],"matching":[173],"samples":[175,182],"amplified,":[177],"while":[178],"those":[179],"suppressed.":[184],"The":[185,206],"evaluated":[189],"on":[190],"three":[191],"datasets\u2014CIRR,":[193],"FashionIQ,":[194],"CIRCO\u2014with":[196],"experimental":[197],"results":[198],"demonstrating":[199],"superior":[200],"performance":[201],"over":[202],"prior":[203],"approaches.":[205],"source":[207],"code":[208],"available":[210],"at":[211],"https://github.com/After-lifes/TTF.":[212]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-06T00:00:00"}