{"id":"https://openalex.org/W4417073308","doi":"https://doi.org/10.1145/3743093.3770960","title":"Leveraging Pseudo-triplet and Flexible Prompt for Zero-shot Composed Image Retrieval","display_name":"Leveraging Pseudo-triplet and Flexible Prompt for Zero-shot Composed Image Retrieval","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073308","doi":"https://doi.org/10.1145/3743093.3770960"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770960","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770960","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770960","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/10.1145/3743093.3770960","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113549084","display_name":"H. Gin 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":0.9343000054359436,"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":0.9343000054359436,"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":0.04820000007748604,"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":0.007699999958276749,"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":0.6873000264167786},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6309999823570251},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.551800012588501},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4810999929904938},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4560999870300293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4047999978065491},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3880000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986999750137329},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6873000264167786},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6309999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6114000082015991},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4810999929904938},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3880000114440918},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2689000070095062},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770960","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770960","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770960","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:10.1145/3743093.3770960","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770960","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770960","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"},{"id":"https://openalex.org/G5006410657","display_name":null,"funder_award_id":"62371235","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073308.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2111993661","https://openalex.org/W2340690086","https://openalex.org/W2723293840","https://openalex.org/W2886641317","https://openalex.org/W2905544595","https://openalex.org/W2956018683","https://openalex.org/W2964236337","https://openalex.org/W3110536152","https://openalex.org/W3133524129","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3198377975","https://openalex.org/W3203247393","https://openalex.org/W3206569427","https://openalex.org/W4230405732","https://openalex.org/W4312310776","https://openalex.org/W4386071547","https://openalex.org/W4386071700","https://openalex.org/W4386328612","https://openalex.org/W4388192471","https://openalex.org/W4390873539","https://openalex.org/W4391660239","https://openalex.org/W4392172801","https://openalex.org/W4393159792","https://openalex.org/W4400526206","https://openalex.org/W4402716416","https://openalex.org/W4402727158","https://openalex.org/W4402915471","https://openalex.org/W4409370087"],"related_works":[],"abstract_inverted_index":{"Compared":[0],"to":[1,46,65,97,121,157,210],"supervised":[2,114],"composed":[3,213],"image":[4,91,167,190],"retrieval":[5],"(CIR),":[6],"which":[7,178],"requires":[8],"a":[9,55,66,93,123,133,176,212],"large":[10],"number":[11],"of":[12,72,85],"manually":[13],"labeled":[14],"triplets":[15],"(reference":[16],"image,":[17],"modification":[18],"text,":[19],"target":[20],"image)":[21],"for":[22,35,39],"training,":[23,118],"Zero-shot":[24],"Composed":[25],"Image":[26],"Retrieval":[27],"(ZS-CIR)":[28],"only":[29],"needs":[30],"easily":[31],"available":[32,240],"image-caption":[33,50],"pairs":[34,51],"training.":[36],"Prior":[37],"works":[38],"ZS-CIR":[40,135,220,234],"have":[41],"primarily":[42],"used":[43,219],"textual":[44],"inversion":[45],"convert":[47],"images":[48],"from":[49],"into":[52,92,175,206],"pseudo-words":[53,61],"using":[54,160],"pre-trained":[56],"Vision-language":[57],"Model":[58],"(VLM).":[59],"These":[60],"are":[62,173,198],"then":[63],"concatenated":[64,199],"template,":[67],"such":[68,222],"as":[69,223],"\u201ca":[70],"photo":[71],"$\u201d.":[73],"We":[74],"find":[75],"that":[76,88,229],"this":[77,129],"fixed":[78,145],"template":[79],"representation":[80],"hinders":[81],"the":[82,100,104,108,150,155,182,195,201,207],"generalization":[83],"ability":[84],"ZS-CIR,":[86],"and":[87,140,153,169,185,191,204,226],"converting":[89],"an":[90],"single":[94],"pseudo-token":[95],"fails":[96],"accurately":[98],"represent":[99],"information":[101],"contained":[102],"in":[103,126],"image.":[105],"Additionally,":[106],"given":[107],"high":[109],"performance":[110],"demonstrated":[111],"by":[112,181],"traditional":[113],"CIR":[115],"after":[116],"triplet":[117],"we":[119,131,148],"aim":[120],"achieve":[122],"similar":[124],"structure":[125],"ZS-CIR.":[127],"In":[128],"paper,":[130],"propose":[132],"novel":[134],"paradigm":[136],"based":[137],"on":[138,217],"pseudo-triplets":[139,159],"flexible":[141],"prompts,":[142],"rather":[143],"than":[144],"templates.":[146],"Specifically,":[147],"fine-tune":[149],"vision":[151],"encoder":[152,209],"split":[154,171,202],"caption":[156,192,203],"generate":[158],"random":[161],"patch":[162],"masking.":[163],"The":[164,236],"obtained":[165],"masked":[166],"tokens":[168],"corresponding":[170],"captions":[172],"fed":[174,205],"Q-former,":[177],"is":[179,239],"guided":[180],"learned":[183,196],"queries":[184,187,197],"generates":[186],"containing":[188],"both":[189],"information.":[193],"Finally,":[194],"with":[200],"text":[208],"obtain":[211],"query.":[214],"Extensive":[215],"experiments":[216],"commonly":[218],"benchmarks":[221],"CIRR,":[224],"FashionIQ,":[225],"CIRCO":[227],"demonstrate":[228],"our":[230],"method":[231],"outperforms":[232],"previous":[233],"approaches.":[235],"source":[237],"code":[238],"at":[241],"https://github.com/After-lifes/PFP.":[242]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-06T00:00:00"}