{"id":"https://openalex.org/W4408354084","doi":"https://doi.org/10.1109/icassp49660.2025.10889170","title":"CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models","display_name":"CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354084","doi":"https://doi.org/10.1109/icassp49660.2025.10889170"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"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/A5103885616","display_name":"Y. Wang","orcid":"https://orcid.org/0000-0002-3210-2330"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeyuan Wang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062149619","display_name":"Dehong Gao","orcid":"https://orcid.org/0000-0002-6636-5702"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehong Gao","raw_affiliation_strings":["Northwestern Polytechnical University,School of Cybersecurity,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Cybersecurity,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100744772","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-4028-0938"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023108787","display_name":"Rujiao Long","orcid":"https://orcid.org/0000-0003-1330-3193"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rujiao Long","raw_affiliation_strings":["Alibaba Group,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088303755","display_name":"Yi Lei","orcid":"https://orcid.org/0000-0003-4171-8695"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yi","raw_affiliation_strings":["Alibaba Group,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070472433","display_name":"Xiaoyan Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Cai","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972632","display_name":"Libin Yang","orcid":"https://orcid.org/0000-0002-7203-0810"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libin Yang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Cybersecurity,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Cybersecurity,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667959","display_name":"Jinxia Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxia Zhang","raw_affiliation_strings":["Southeast University,The Key Laboratory of Measurement and Control of CSE, Ministry of Education, School of Automation,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,The Key Laboratory of Measurement and Control of CSE, Ministry of Education, School of Automation,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063370205","display_name":"Shanqing Yu","orcid":"https://orcid.org/0000-0001-5170-8082"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanqing Yu","raw_affiliation_strings":["Zhejiang University of Technology,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016704080","display_name":"Qi Xuan","orcid":"https://orcid.org/0000-0002-1042-470X"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Xuan","raw_affiliation_strings":["Zhejiang University of Technology,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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/T10028","display_name":"Topic Modeling","score":0.9930999875068665,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9836000204086304,"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/modal","display_name":"Modal","score":0.7413160800933838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722237229347229},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4902358651161194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4338744282722473},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40135183930397034},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.18640556931495667},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.07360753417015076}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7413160800933838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722237229347229},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4902358651161194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4338744282722473},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40135183930397034},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.18640556931495667},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.07360753417015076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W3035485997","https://openalex.org/W3165938948","https://openalex.org/W4381334414","https://openalex.org/W4389519547","https://openalex.org/W4389523832","https://openalex.org/W4390873481","https://openalex.org/W4402704565","https://openalex.org/W4402716166","https://openalex.org/W4402727558","https://openalex.org/W4402727669","https://openalex.org/W4402727764","https://openalex.org/W4402753733","https://openalex.org/W4402753807","https://openalex.org/W4402754296","https://openalex.org/W4402951581","https://openalex.org/W4403081466","https://openalex.org/W4404783556","https://openalex.org/W4409366315","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6803953248","https://openalex.org/W6810334672","https://openalex.org/W6849177959","https://openalex.org/W6851950068","https://openalex.org/W6853116092","https://openalex.org/W6853242345","https://openalex.org/W6854347851"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,50],"impressive":[1],"performance":[2,156,169],"of":[3,57,118,144,170],"Large":[4],"Language":[5],"Model":[6],"(LLM)":[7],"has":[8,17],"prompted":[9],"researchers":[10],"to":[11,30,44,62,73,102,113],"develop":[12],"Multi-modal":[13],"LLM":[14],"(MLLM),":[15],"which":[16],"shown":[18],"great":[19],"potential":[20],"for":[21],"various":[22],"multi-modal":[23,34,95],"tasks.":[24,159],"However,":[25],"current":[26],"MLLM":[27,112],"often":[28],"struggles":[29],"effectively":[31],"address":[32],"fine-grained":[33,83],"challenges.":[35],"We":[36],"argue":[37],"that":[38,163],"this":[39,90,164],"limitation":[40],"is":[41,181],"closely":[42],"linked":[43],"the":[45,71,106,111,115,119,122,128,135,168],"models\u2019":[46],"visual":[47,58,85,138,152],"grounding":[48,153],"capabilities.":[49],"restricted":[51],"spatial":[52],"awareness":[53],"and":[54,154,176],"perceptual":[55],"acuity":[56],"encoders":[59],"frequently":[60],"lead":[61],"interference":[63],"from":[64,100],"irrelevant":[65],"background":[66],"information":[67],"in":[68,148,157],"images,":[69],"causing":[70],"models":[72],"overlook":[74],"subtle":[75],"but":[76],"crucial":[77],"details.":[78],"As":[79],"a":[80],"result,":[81],"achieving":[82],"regional":[84],"comprehension":[86],"becomes":[87],"difficult.":[88],"In":[89,105,121],"paper,":[91],"we":[92,109,125],"break":[93],"down":[94],"understanding":[96],"into":[97],"two":[98],"stages,":[99],"Coarse":[101],"Fine":[103],"(CoF).":[104],"first":[107],"stage,":[108,124],"prompt":[110,139],"locate":[114],"approximate":[116],"area":[117],"answer.":[120],"second":[123],"further":[126],"enhance":[127],"model\u2019s":[129],"focus":[130],"on":[131],"relevant":[132],"areas":[133],"within":[134],"image":[136],"through":[137],"engineering,":[140],"adjusting":[141],"attention":[142],"weights":[143],"pertinent":[145],"regions.":[146],"This,":[147],"turn,":[149],"improves":[150],"both":[151],"overall":[155],"downstream":[158],"Our":[160,178],"experiments":[161],"show":[162],"approach":[165,180],"significantly":[166],"boosts":[167],"baseline":[171],"models,":[172],"demonstrating":[173],"notable":[174],"generalization":[175],"effectiveness.":[177],"CoF":[179],"available":[182],"online":[183],"at":[184],"https://github.com/Gavin001201/CoF.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}