{"id":"https://openalex.org/W4411371543","doi":"https://doi.org/10.1145/3744343","title":"Bool Prompt with Decomposition and Enhancement: Zero-Shot VQA Based on PVLMs","display_name":"Bool Prompt with Decomposition and Enhancement: Zero-Shot VQA Based on PVLMs","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411371543","doi":"https://doi.org/10.1145/3744343"},"language":"en","primary_location":{"id":"doi:10.1145/3744343","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744343","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5059182164","display_name":"Liyong Xu","orcid":"https://orcid.org/0009-0003-4822-1881"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyong Xu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China","School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0003-4822-1881","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031056278","display_name":"Yifan Jiao","orcid":"https://orcid.org/0000-0002-8923-6997"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Jiao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China","School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-8923-6997","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China and the State Key Laboratory of Tibetan Intelligence, Nanjing, China","School of Computer Science, Nanjing University of Posts and Telecommunications, China and The State Key Laboratory of Tibetan Intelligence, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China and the State Key Laboratory of Tibetan Intelligence, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, China and The State Key Laboratory of Tibetan Intelligence, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10596661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"9","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987000226974487,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8016648292541504},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6776859164237976},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5278059244155884},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.43551111221313477},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.12129193544387817},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08298036456108093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016648292541504},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6776859164237976},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5278059244155884},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.43551111221313477},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.12129193544387817},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08298036456108093},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3744343","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744343","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3658883423","display_name":null,"funder_award_id":"BK20230363","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7884838812","display_name":null,"funder_award_id":"62325206 and 62302239","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2501356530","https://openalex.org/W2560730294","https://openalex.org/W2606555609","https://openalex.org/W2618530766","https://openalex.org/W2745461083","https://openalex.org/W2760103357","https://openalex.org/W2916723116","https://openalex.org/W2962529143","https://openalex.org/W2963717374","https://openalex.org/W2965950070","https://openalex.org/W2969663619","https://openalex.org/W3003260174","https://openalex.org/W3128560592","https://openalex.org/W3173220247","https://openalex.org/W4214825151","https://openalex.org/W4225517085","https://openalex.org/W4253732063","https://openalex.org/W4288707709","https://openalex.org/W4378807209","https://openalex.org/W4385570037","https://openalex.org/W4385570433","https://openalex.org/W4385572364","https://openalex.org/W4385574156","https://openalex.org/W4391293808","https://openalex.org/W4391853818","https://openalex.org/W4398232760","https://openalex.org/W4400844648","https://openalex.org/W4403577524","https://openalex.org/W4407156489"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Zero-Shot":[0],"Visual":[1,25],"Question":[2],"Answering":[3],"(ZSVQA)":[4],"aims":[5],"to":[6,33,65,81,120,139,184,196],"answer":[7],"questions":[8,35,145,181],"about":[9],"images":[10],"without":[11],"prior":[12],"training":[13],"on":[14,152,214],"explicit":[15],"image":[16,77,86],"question":[17,50,53,83,126],"pairs.":[18],"Most":[19],"existing":[20],"methods":[21],"usually":[22],"apply":[23],"Pre-trained":[24],"and":[26,46,59,106,127,137,161,182,200,216],"Language":[27],"Models":[28],"(PVLMs)":[29],"by":[30],"designing":[31],"prompts":[32],"convert":[34],"into":[36,146],"predefined":[37],"input":[38],"templates,":[39],"which":[40,150],"(1)":[41],"ignores":[42],"the":[43,49,52,76,82,85,101,115,124,131,141,164,168,176,202,205,209,220,226],"text":[44],"details":[45,74],"associations":[47],"of":[48,68,75,143,159,179,204],"when":[51,84],"is":[54,88,194],"complex,":[55],"hindering":[56],"comprehensive":[57],"understanding,":[58],"(2)":[60],"does":[61],"not":[62],"pay":[63],"attention":[64,183],"local":[66,171,185],"information":[67],"image,":[69,132],"resulting":[70],"in":[71],"overlooking":[72],"some":[73],"that":[78,201,219],"are":[79],"important":[80],"content":[87],"particularly":[89],"complex":[90,180],"or":[91,157],"requires":[92],"detailed":[93],"observation.":[94],"To":[95],"address":[96],"these":[97,135],"challenges,":[98],"we":[99,113],"propose":[100,114],"Bool":[102,116],"Prompt":[103],"with":[104,170],"Decomposition":[105],"Enhancement":[107],"(BPDE)":[108],"framework":[109],"for":[110],"ZSVQA.":[111],"Specifically,":[112],"Sub-Questions":[117,191],"Generating":[118],"module":[119],"extract":[121],"keywords":[122,136],"from":[123,130,163],"original":[125,144,210],"generate":[128],"captions":[129,138,165],"then":[133],"use":[134],"guide":[140],"transformation":[142],"simpler":[147],"bool":[148],"sub-questions,":[149],"focus":[151],"a":[153],"specific":[154],"logical":[155],"point":[156],"piece":[158],"information,":[160,173],"guided":[162],"can":[166,207],"provide":[167],"model":[169],"visual":[172,186],"thereby":[174],"enhancing":[175],"model\u2019s":[177],"understanding":[178],"information.":[187],"Additionally,":[188],"an":[189],"Adaptive":[190],"Selecting":[192],"mechanism":[193],"designed":[195],"ensure":[197],"non-redundant":[198],"selection":[199],"meanings":[203],"sub-questions":[206],"cover":[208],"question.":[211],"Extensive":[212],"experiments":[213],"VQAv2":[215],"AOKVQA":[217],"demonstrate":[218],"proposed":[221],"approach":[222],"performs":[223],"favorably":[224],"against":[225],"state-of-the-art":[227],"methods.":[228]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
