{"id":"https://openalex.org/W4408353052","doi":"https://doi.org/10.1109/icassp49660.2025.10889214","title":"MixSense : Mixture of Vision Sense","display_name":"MixSense : Mixture of Vision Sense","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353052","doi":"https://doi.org/10.1109/icassp49660.2025.10889214"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889214","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/A5111672369","display_name":"Jian Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Lin","raw_affiliation_strings":["Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741933","display_name":"Zhuoran Wang","orcid":"https://orcid.org/0000-0003-3204-3702"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoran Wang","raw_affiliation_strings":["School of Computing and Information, University of Pittsburgh,Pittsburgh,The United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information, University of Pittsburgh,Pittsburgh,The United States","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055301514","display_name":"Qibo Qiu","orcid":"https://orcid.org/0000-0002-2848-6079"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibo Qiu","raw_affiliation_strings":["Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058880754","display_name":"Jianzhong Chen","orcid":"https://orcid.org/0000-0001-5207-4798"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Chen","raw_affiliation_strings":["Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026673299","display_name":"Zixian Ge","orcid":"https://orcid.org/0000-0001-7905-6450"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixian Ge","raw_affiliation_strings":["Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101623674","display_name":"Weizhong Jin","orcid":"https://orcid.org/0000-0001-9335-2336"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhong Jin","raw_affiliation_strings":["Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101455767","display_name":"Yuchao Yan","orcid":"https://orcid.org/0000-0003-3539-5711"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchao Yan","raw_affiliation_strings":["Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053169627","display_name":"Li Yu","orcid":"https://orcid.org/0009-0006-2152-0234"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yu","raw_affiliation_strings":["Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research &amp; Innovation Institute, China Mobile (Zhejiang),Hangzhou,China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.02670902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12496","display_name":"Color perception and design","score":0.09049999713897705,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12496","display_name":"Color perception and design","score":0.09049999713897705,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.07959999889135361,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/sense","display_name":"Sense (electronics)","score":0.6757631301879883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5954930186271667},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45928406715393066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40490424633026123},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08754104375839233}],"concepts":[{"id":"https://openalex.org/C143141573","wikidata":"https://www.wikidata.org/wiki/Q7450971","display_name":"Sense (electronics)","level":2,"score":0.6757631301879883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5954930186271667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45928406715393066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40490424633026123},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08754104375839233},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889214","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2560730294","https://openalex.org/W2963518342","https://openalex.org/W2963622213","https://openalex.org/W2979382951","https://openalex.org/W3096609285","https://openalex.org/W4285294723","https://openalex.org/W4308760226","https://openalex.org/W4389523832","https://openalex.org/W4402727764","https://openalex.org/W4403021005","https://openalex.org/W4403081466","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6796814978","https://openalex.org/W6810081322","https://openalex.org/W6811340617","https://openalex.org/W6843405348","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6853838016","https://openalex.org/W6854262950","https://openalex.org/W6854510102","https://openalex.org/W6854866820","https://openalex.org/W6855297460","https://openalex.org/W6855350031","https://openalex.org/W6857569170","https://openalex.org/W6857872576","https://openalex.org/W6858380932","https://openalex.org/W6862220061"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"It":[0],"is":[1],"a":[2,24,60,95,162],"new":[3,25,96],"trend":[4],"to":[5,11,13,44,80,87,110],"fine-tune":[6],"Large":[7,47],"Multimodal":[8],"Models":[9],"(LMMs)":[10],"adapt":[12],"specific":[14,64,71,119,151],"visual":[15,41,65,102,152],"tasks":[16,72,153],"through":[17],"task-related":[18],"conversation":[19],"data.":[20],"This":[21],"approach":[22],"provides":[23],"paradigm":[26,98],"for":[27],"solving":[28],"various":[29],"vision-language":[30],"tasks,":[31],"however,":[32],"it":[33],"still":[34],"faces":[35],"two":[36,90],"problems:":[37],"(1)":[38],"the":[39,45,52,77,101,111,116,124,128,134,143,148,176],"global":[40],"features":[42,103],"input":[43],"backbone":[46,112],"Language":[48],"Model":[49],"(LLM)":[50],"lack":[51],"focus":[53,117],"on":[54,63,70,118,150,161],"task-specific":[55,136],"information,":[56],"which":[57,75],"may":[58],"lead":[59],"sub-optimal":[61],"performance":[62],"tasks;":[66],"(2)":[67],"The":[68],"hallucinations":[69,146],"are":[73],"underestimated,":[74],"makes":[76],"model":[78,149],"prone":[79],"factual":[81],"errors":[82],"during":[83],"inference.":[84],"In":[85],"order":[86],"solve":[88],"these":[89],"problems,":[91],"we":[92,139],"propose":[93],"MixSense,":[94],"LMM":[97],"that":[99],"aligns":[100],"of":[104,127,145,147,178],"specilized":[105],"models":[106,109],"and":[107,131,154,172],"general":[108],"LLM":[113],"together,":[114],"increasing":[115],"task":[120],"information":[121],"while":[122],"maintaining":[123],"vanilla":[125],"capabilities":[126],"model;":[129],"evaluated":[130],"fine-tuned":[132],"with":[133],"constructed":[135],"negative":[137],"samples,":[138],"can":[140],"further":[141],"assess":[142],"degree":[144],"reduce":[155],"it.":[156],"We":[157],"validate":[158],"our":[159,179],"method":[160],"popular":[163],"Object":[164],"Detection":[165],"(OD)":[166],"task,":[167],"Referring":[168],"Expression":[169],"Comprehension":[170],"(REC),":[171],"extensive":[173],"experiments":[174],"demonstrate":[175],"effectiveness":[177],"proposal.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
