{"id":"https://openalex.org/W4413145697","doi":"https://doi.org/10.1109/cvpr52734.2025.00375","title":"Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception","display_name":"Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145697","doi":"https://doi.org/10.1109/cvpr52734.2025.00375"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00375","doi":"https://doi.org/10.1109/cvpr52734.2025.00375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00375","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5113358583","display_name":"Ruotian Peng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruotian Peng","raw_affiliation_strings":["South China University of Technology,School of Future Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Future Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101976458","display_name":"Haiying He","orcid":"https://orcid.org/0000-0003-4824-4664","observed_orcids":["https://orcid.org/0000-0003-4824-4664"]},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiying He","raw_affiliation_strings":["China Agricultural University,College of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Agricultural University,College of Science","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006944766","display_name":"Yake Wei","orcid":"https://orcid.org/0009-0008-8779-0637","observed_orcids":["https://orcid.org/0009-0008-8779-0637"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yake Wei","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070584981","display_name":"Yandong Wen","orcid":"https://orcid.org/0000-0001-6330-7438","observed_orcids":["https://orcid.org/0000-0001-6330-7438"]},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yandong Wen","raw_affiliation_strings":["Westlake University,School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University,School of Engineering","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100670614","display_name":"Di Hu","orcid":"https://orcid.org/0000-0002-7118-6733","observed_orcids":["https://orcid.org/0000-0002-7118-6733"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Hu","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9339,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.96755318,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3963","last_page":"3973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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":0.0,"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-captioning","display_name":"image captioning","score":0.9169999957084656},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8740000128746033},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.7039999961853027},{"id":"https://openalex.org/keywords/local-perceptions","display_name":"local perceptions","score":0.6029999852180481},{"id":"https://openalex.org/keywords/feature-integration-theory","display_name":"feature integration theory","score":0.6980000138282776},{"id":"https://openalex.org/keywords/hierarchical-aggregation","display_name":"hierarchical aggregation","score":0.9190000295639038}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7448126077651978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219021320343018},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5935692191123962},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4892692267894745},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4650605320930481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42442038655281067},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36923936009407043},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1134234368801117},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05926045775413513},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00375","doi":"https://doi.org/10.1109/cvpr52734.2025.00375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00375","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416531049","https://openalex.org/W7213788083","https://openalex.org/W4414511109","https://openalex.org/W4394625850","https://openalex.org/W7141761787","https://openalex.org/W7134063634","https://openalex.org/W4416035575","https://openalex.org/W6906209979","https://openalex.org/W3045147787","https://openalex.org/W4413401670"],"abstract_inverted_index":{"High-quality":[0],"image":[1,90],"captions":[2,43],"play":[3],"a":[4,52,82,117,132],"crucial":[5],"role":[6],"in":[7,56,126],"improving":[8],"the":[9,89,101,106,127],"performance":[10],"of":[11,105],"cross-modal":[12],"applications":[13],"such":[14],"as":[15],"text-to-image":[16],"generation,":[17,19],"text-to-video":[18],"and":[20,59,93,124,152],"text-image":[21],"retrieval.":[22],"To":[23,121],"generate":[24,116],"long-form,":[25],"high-quality":[26],"captions,":[27,129,168],"many":[28],"recent":[29],"studies":[30],"have":[31],"employed":[32],"multimodal":[33,170],"large":[34],"language":[35],"models":[36,148,154],"(MLLMs).":[37],"However,":[38],"current":[39],"MLLMs":[40],"often":[41],"produce":[42],"that":[44,54,68,161],"lack":[45],"fine-grained":[46,98],"details":[47,110],"or":[48],"suffer":[49],"from":[50],"hallucinations,":[51],"challenge":[53],"persists":[55],"both":[57,146],"open-source":[58,147],"closed-source":[60,153],"models.":[61],"Inspired":[62],"by":[63],"Feature-Integration":[64],"theory,":[65],"which":[66],"suggests":[67],"attention":[69],"must":[70],"focus":[71],"on":[72],"specific":[73],"regions":[74],"to":[75,96,115,145],"integrate":[76],"visual":[77],"information":[78],"effectively,":[79],"we":[80,130],"propose":[81],"divide-then-aggregate":[83],"strategy.":[84],"Our":[85],"method":[86,163],"first":[87],"divides":[88],"into":[91],"semantic":[92],"spatial":[94],"patches":[95],"extract":[97],"details,":[99],"enhancing":[100],"model\u2019s":[102],"local":[103,109],"perception":[104],"image.":[107],"These":[108],"are":[111,180],"then":[112],"hierarchically":[113],"aggregated":[114],"comprehensive":[118],"global":[119],"description.":[120],"address":[122],"hallucinations":[123],"inconsistencies":[125],"generated":[128],"apply":[131],"semantic-level":[133],"filtering":[134],"process":[135],"during":[136],"hierarchical":[137],"aggregation.":[138],"This":[139],"training-free":[140],"pipeline":[141],"can":[142],"be":[143],"applied":[144],"(LLaVA-1.5,":[149],"LLaVA-1.6,":[150],"Mini-Gemini)":[151],"(Claude-3.5-Sonnet,":[155],"GPT-4o,":[156],"GLM-4V-Plus).":[157],"Extensive":[158],"experiments":[159],"demonstrate":[160],"our":[162],"generates":[164],"more":[165],"detailed,":[166],"reliable":[167],"advancing":[169],"description":[171],"generation":[172],"without":[173],"requiring":[174],"model":[175],"retraining.":[176],"The":[177],"source":[178],"code":[179],"available":[181],"at":[182],"https://github.com/GeWu-Lab/Patch-Matters":[183]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2025-10-10T00:00:00"}