{"id":"https://openalex.org/W4414165907","doi":"https://doi.org/10.1109/tmm.2025.3607726","title":"SPDQ: Synergetic Prompts as Disentanglement Queries for Compositional Zero-Shot Learning","display_name":"SPDQ: Synergetic Prompts as Disentanglement Queries for Compositional Zero-Shot Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414165907","doi":"https://doi.org/10.1109/tmm.2025.3607726"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3607726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607726","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5101376425","display_name":"Han Jiang","orcid":"https://orcid.org/0009-0006-6760-6914"},"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":"Han Jiang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-6760-6914","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083991825","display_name":"Xiaoshan Yang","orcid":"https://orcid.org/0000-0001-5453-9755"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshan Yang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5453-9755","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024701469","display_name":"Chaofan Chen","orcid":"https://orcid.org/0000-0001-7970-7698"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaofan Chen","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7970-7698","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09315004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"8888","last_page":"8899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9449999928474426,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6963000297546387},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.611299991607666},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6104999780654907},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4738999903202057},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.3831999897956848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9077000021934509},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6963000297546387},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6104999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241000056266785},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3607726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607726","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3087610523","display_name":null,"funder_award_id":"U23A20387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6544960559","display_name":null,"funder_award_id":"62322212","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1948251820","https://openalex.org/W2093848332","https://openalex.org/W2250539671","https://openalex.org/W2736809457","https://openalex.org/W2889167066","https://openalex.org/W2905449860","https://openalex.org/W2963518342","https://openalex.org/W2982863468","https://openalex.org/W2986385672","https://openalex.org/W3014225712","https://openalex.org/W3035084814","https://openalex.org/W3094219444","https://openalex.org/W3158711590","https://openalex.org/W3162332195","https://openalex.org/W3164354101","https://openalex.org/W3189076762","https://openalex.org/W3198377975","https://openalex.org/W3212203927","https://openalex.org/W4205991051","https://openalex.org/W4226340378","https://openalex.org/W4292974991","https://openalex.org/W4304080190","https://openalex.org/W4312310776","https://openalex.org/W4312400874","https://openalex.org/W4312539810","https://openalex.org/W4312578829","https://openalex.org/W4312651322","https://openalex.org/W4313175608","https://openalex.org/W4385767718","https://openalex.org/W4386065780","https://openalex.org/W4386065859","https://openalex.org/W4386071547","https://openalex.org/W4386076688","https://openalex.org/W4386172501","https://openalex.org/W4393149562","https://openalex.org/W4393154717","https://openalex.org/W4394625573","https://openalex.org/W4396877720","https://openalex.org/W4402716195","https://openalex.org/W4402727931","https://openalex.org/W4402772357","https://openalex.org/W4402781704","https://openalex.org/W4405003255","https://openalex.org/W4415539521"],"related_works":[],"abstract_inverted_index":{"Compositional":[0],"zero-shot":[1],"learning":[2,83],"(CZSL)":[3],"aims":[4],"to":[5,30,55,68,79,128,141,166,174],"identify":[6],"novel":[7,109],"compositions":[8],"formed":[9],"by":[10,17],"known":[11],"primitives":[12,94],"(attributes":[13],"and":[14,35,146],"objects).":[15],"Motivated":[16],"recent":[18],"advancements":[19],"in":[20,100],"pre-trained":[21],"vision-language":[22],"models":[23],"such":[24],"as":[25,95,97,112],"CLIP,":[26],"many":[27],"methods":[28,44],"attempt":[29],"fine-tune":[31],"CLIP":[32],"for":[33,85,117,156],"CZSL":[34,43,86],"achieve":[36,80],"remarkable":[37],"performance.":[38],"However,":[39],"the":[40,53,88],"existing":[41],"CLIP-based":[42],"focus":[45],"mainly":[46],"on":[47,125,150,186],"text":[48,163],"prompt":[49,72,169],"tuning,":[50],"which":[51,171],"lacks":[52],"flexibility":[54],"dynamically":[56],"adapt":[57],"both":[58],"modalities.":[59],"To":[60],"solve":[61],"this":[62,104],"issue,":[63],"an":[64],"intuitive":[65],"solution":[66],"is":[67,76],"additionally":[69,161],"introduce":[70],"visual":[71,93,177,181],"tuning.":[73],"This":[74],"insight":[75],"not":[77],"trivial":[78],"because":[81],"effectively":[82],"prompts":[84,127,148,165],"involves":[87],"challenge":[89],"of":[90,153],"entanglement":[91],"between":[92],"well":[96],"appearance":[98],"shifts":[99],"different":[101],"compositions.":[102],"In":[103],"paper,":[105],"we":[106,134,160],"propose":[107],"a":[108,137],"Synergetic":[110],"Prompts":[111],"Disentanglement":[113],"Queries":[114],"(SPDQ)":[115],"framework":[116],"CZSL.":[118],"It":[119],"can":[120],"disentangle":[121],"primitive":[122,139],"features":[123,178],"based":[124,149],"synergetic":[126,143,168],"jointly":[129],"alleviate":[130],"these":[131],"challenges.":[132],"Specifically,":[133],"first":[135],"design":[136],"low-rank":[138],"modulator":[140],"produce":[142],"adaptive":[144],"attribute":[145],"object":[147],"prior":[151],"knowledge":[152],"each":[154],"instance":[155],"model":[157],"adaptation.":[158],"Then,":[159],"utilize":[162],"prefix":[164],"construct":[167],"queries,":[170],"are":[172],"used":[173],"resample":[175],"corresponding":[176],"from":[179],"local":[180],"patches.":[182],"Comprehensive":[183],"experiments":[184],"conducted":[185],"three":[187],"benchmarks":[188],"demonstrate":[189],"that":[190],"our":[191],"SPDQ":[192],"approach":[193],"achieves":[194],"state-of-the-art":[195],"results.":[196]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}