{"id":"https://openalex.org/W4411086303","doi":"https://doi.org/10.1109/tcsvt.2025.3577246","title":"Multi-Modal Prompts With Primitives Enhancement for Compositional Zero-Shot Learning","display_name":"Multi-Modal Prompts With Primitives Enhancement for Compositional Zero-Shot Learning","publication_year":2025,"publication_date":"2025-06-06","ids":{"openalex":"https://openalex.org/W4411086303","doi":"https://doi.org/10.1109/tcsvt.2025.3577246"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3577246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3577246","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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":null,"display_name":"Yutang Jin","orcid":"https://orcid.org/0009-0006-9898-0407"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yutang Jin","raw_affiliation_strings":["State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China","College of Computer Science and Technology, State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China"],"raw_orcid":"https://orcid.org/0009-0006-9898-0407","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China","institution_ids":["https://openalex.org/I178232147"]},{"raw_affiliation_string":"College of Computer Science and Technology, State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071943020","display_name":"Shiming Chen","orcid":"https://orcid.org/0000-0001-9633-3392"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Shiming Chen","raw_affiliation_strings":["Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0001-9633-3392","affiliations":[{"raw_affiliation_string":"Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianle Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166719","display_name":"WengFu Group (China)","ror":"https://ror.org/05nqkcp91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210166719"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianle Tong","raw_affiliation_strings":["Guizhou Suanjia Computing Services Company Ltd., Guiyang, China","Guizhou Suanjia Computing Service Co., Ltd., Guiyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guizhou Suanjia Computing Services Company Ltd., Guiyang, China","institution_ids":["https://openalex.org/I4210166719"]},{"raw_affiliation_string":"Guizhou Suanjia Computing Service Co., Ltd., Guiyang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069969191","display_name":"Weiping Ding","orcid":"https://orcid.org/0000-0002-3180-7347"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Ding","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Nantong University, Nantong, China"],"raw_orcid":"https://orcid.org/0000-0002-3180-7347","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101688864","display_name":"Yisong Wang","orcid":"https://orcid.org/0000-0003-2126-7006"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisong Wang","raw_affiliation_strings":["State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China","College of Computer Science and Technology, State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China"],"raw_orcid":"https://orcid.org/0000-0003-2126-7006","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China","institution_ids":["https://openalex.org/I178232147"]},{"raw_affiliation_string":"College of Computer Science and Technology, State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China","institution_ids":["https://openalex.org/I178232147"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I178232147"],"apc_list":null,"apc_paid":null,"fwci":1.025,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75559768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"35","issue":"12","first_page":"11754","last_page":"11769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11609","display_name":"Geophysical Methods and Applications","score":0.9927999973297119,"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"}},"topics":[{"id":"https://openalex.org/T11609","display_name":"Geophysical Methods and Applications","score":0.9927999973297119,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.948199987411499,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6695300340652466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5949249863624573},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5640053749084473},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4463462233543396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4224187731742859},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3528027832508087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33494287729263306},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08646780252456665}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6695300340652466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5949249863624573},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5640053749084473},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4463462233543396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4224187731742859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3528027832508087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33494287729263306},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08646780252456665},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3577246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3577246","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4286351655","display_name":null,"funder_award_id":"U2433216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6401699566","display_name":null,"funder_award_id":"61976065","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8225248995","display_name":null,"funder_award_id":"U1836205","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1948251820","https://openalex.org/W2093848332","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2736809457","https://openalex.org/W2889167066","https://openalex.org/W2963115613","https://openalex.org/W2963518342","https://openalex.org/W2982863468","https://openalex.org/W2986385672","https://openalex.org/W2998496429","https://openalex.org/W3034862692","https://openalex.org/W3035084814","https://openalex.org/W3112567928","https://openalex.org/W3158711590","https://openalex.org/W3162332195","https://openalex.org/W3164354101","https://openalex.org/W3182683290","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3207076160","https://openalex.org/W4205991051","https://openalex.org/W4229044990","https://openalex.org/W4292974991","https://openalex.org/W4304080190","https://openalex.org/W4312283137","https://openalex.org/W4312400874","https://openalex.org/W4312539810","https://openalex.org/W4312680644","https://openalex.org/W4312815172","https://openalex.org/W4313123992","https://openalex.org/W4319778743","https://openalex.org/W4320713198","https://openalex.org/W4375929081","https://openalex.org/W4382240738","https://openalex.org/W4385245566","https://openalex.org/W4385767718","https://openalex.org/W4386025726","https://openalex.org/W4386065780","https://openalex.org/W4386065859","https://openalex.org/W4386076688","https://openalex.org/W4387449204","https://openalex.org/W4390874575","https://openalex.org/W4391305602","https://openalex.org/W4393149562","https://openalex.org/W4393154717","https://openalex.org/W4393154971","https://openalex.org/W4393159686","https://openalex.org/W4394597571","https://openalex.org/W4394625573","https://openalex.org/W4401024975","https://openalex.org/W4402716195","https://openalex.org/W4402753899","https://openalex.org/W4402772357","https://openalex.org/W4402775923","https://openalex.org/W4403827186","https://openalex.org/W4404563275","https://openalex.org/W4404570953","https://openalex.org/W4405003255","https://openalex.org/W4405778901","https://openalex.org/W4406265446","https://openalex.org/W4408294836"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Compositional":[0],"zero-shot":[1],"learning":[2],"(CZSL)":[3],"aims":[4],"to":[5,45,113,119],"recognize":[6],"novel":[7,156],"compositions":[8],"of":[9,80,123,155,164],"known":[10],"attributes":[11],"and":[12,34,57,73,83,87,142,178],"objects":[13],"without":[14],"requiring":[15],"additional":[16,110],"training":[17],"data.":[18],"Recent":[19],"CZSL":[20,173,180],"methods":[21],"based":[22,136],"on":[23,31,121,137,170],"vision-language":[24],"models(e.g.,":[25],"CLIP)":[26],"suffer":[27],"from":[28,146],"relying":[29],"solely":[30],"text":[32,72,77,149],"prompts":[33,78,93],"neglecting":[35],"the":[36,81,91,99,115,126,147,153,162],"crucial":[37],"primitive":[38],"features":[39,144],"within":[40,125],"compositions,":[41],"which":[42,63,139],"limits":[43],"generalization":[44],"unseen":[46],"compositions.":[47],"To":[48],"overcome":[49],"these":[50],"limitations,":[51],"we":[52,129],"propose":[53],"a":[54,131],"Multi-modal":[55],"Prompt":[56],"Primitives":[58],"Enhancement":[59],"method,":[60],"termed":[61],"MPPE,":[62],"incorporates":[64],"two":[65],"key":[66],"aspects.":[67],"First,":[68],"MPPE":[69],"introduces":[70],"both":[71,176],"visual":[74,92,117],"prompts.":[75],"The":[76],"consist":[79],"composition":[82,157],"its":[84],"corresponding":[85],"attribute":[86,141],"object":[88,143],"prompts,":[89],"while":[90],"leverage":[94],"image":[95],"masks":[96,105],"generated":[97],"by":[98],"segment":[100],"anything":[101],"model":[102],"(SAM).":[103],"These":[104],"are":[106,183],"integrated":[107],"via":[108],"an":[109],"Alpha":[111],"branch":[112],"strengthen":[114],"CLIP":[116,148],"encoder":[118],"focus":[120],"regions":[122],"interest":[124],"image.":[127],"Second,":[128],"design":[130],"primitives":[132],"enhancement":[133],"(PE)":[134],"module":[135],"cross-attention,":[138],"refines":[140],"obtained":[145],"encoder,":[150],"thereby":[151],"enriching":[152],"representation":[154],"features.":[158],"Extensive":[159],"experiments":[160],"demonstrate":[161],"effectiveness":[163],"our":[165],"approach,":[166],"achieving":[167],"state-of-the-art":[168],"performance":[169],"three":[171],"widely-used":[172],"benchmarks":[174],"in":[175],"closed-world":[177],"open-world":[179],"scenarios.":[181],"Codes":[182],"available":[184],"at":[185],"https://github.com/YtJin-git/MPPE.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-06T23:10:59.065948","created_date":"2025-10-10T00:00:00"}