{"id":"https://openalex.org/W4408355901","doi":"https://doi.org/10.1109/icassp49660.2025.10888636","title":"ViCo: A Multitask Video-enhanced and Cognition-preserving Modality Alignment Training Framework","display_name":"ViCo: A Multitask Video-enhanced and Cognition-preserving Modality Alignment Training Framework","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355901","doi":"https://doi.org/10.1109/icassp49660.2025.10888636"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888636","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":"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/A5109151274","display_name":"Zhiyi Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhenda Yu","raw_affiliation_strings":["Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037950203","display_name":"Jin Chen","orcid":"https://orcid.org/0009-0003-7984-8054"},"institutions":[{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Chen","raw_affiliation_strings":["Duke Kunshan University,Suzhou,China","TeleAI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"TeleAI,Beijing,China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101529934","display_name":"Junyi Shen","orcid":"https://orcid.org/0009-0004-5094-2941"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayu Shen","raw_affiliation_strings":["Xi’an Jiaotong University,School of Mathematics and Statistics,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Mathematics and Statistics,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082212103","display_name":"Lanxiang Zhou","orcid":"https://orcid.org/0009-0009-7003-287X"},"institutions":[{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanxiang Zhou","raw_affiliation_strings":["TeleAI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"TeleAI,Beijing,China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071029549","display_name":"Han Fang","orcid":"https://orcid.org/0000-0002-0450-5087"},"institutions":[{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Fang","raw_affiliation_strings":["TeleAI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"TeleAI,Beijing,China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047237045","display_name":"Xianghao Zang","orcid":"https://orcid.org/0000-0001-8421-7167"},"institutions":[{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghao Zang","raw_affiliation_strings":["TeleAI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"TeleAI,Beijing,China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093130774","display_name":"Chao Ban","orcid":"https://orcid.org/0009-0000-8114-103X"},"institutions":[{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Ban","raw_affiliation_strings":["TeleAI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"TeleAI,Beijing,China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084302554","display_name":"Jingfeng Chen","orcid":"https://orcid.org/0000-0001-6383-6532"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]},{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfeng Chen","raw_affiliation_strings":["Duke Kunshan University,Suzhou,China","TeleAI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"TeleAI,Beijing,China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101320954","display_name":"Zhongjiang He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjiang He","raw_affiliation_strings":["TeleAI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"TeleAI,Beijing,China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359490","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0002-6315-4838"},"institutions":[{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["TeleAI,Beijing,China"],"affiliations":[{"raw_affiliation_string":"TeleAI,Beijing,China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029992293","display_name":"Ziyue LI","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zerui Li","raw_affiliation_strings":["Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center,Institute of Artificial Intelligence,Hefei,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080869524","display_name":"Yanmei Kang","orcid":"https://orcid.org/0000-0001-8608-9242"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmei Kang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Mathematics and Statistics,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Mathematics and Statistics,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5109151274"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0441422,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9800000190734863,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9800000190734863,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9697999954223633,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.921500027179718,"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/computer-science","display_name":"Computer science","score":0.7331562042236328},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7321749925613403},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5981659293174744},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45778170228004456},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3233606815338135},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17728319764137268},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05329310894012451}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331562042236328},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7321749925613403},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5981659293174744},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45778170228004456},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3233606815338135},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17728319764137268},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05329310894012451},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888636","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2963541336","https://openalex.org/W3034730770","https://openalex.org/W3168640669","https://openalex.org/W3175961224","https://openalex.org/W4200631219","https://openalex.org/W4312246181","https://openalex.org/W4383112678","https://openalex.org/W4386071468","https://openalex.org/W4386076661","https://openalex.org/W4387546363","https://openalex.org/W4389519587","https://openalex.org/W4389524050","https://openalex.org/W4390190760","https://openalex.org/W4390871765","https://openalex.org/W4390889724","https://openalex.org/W4409363283","https://openalex.org/W6769627184","https://openalex.org/W6772396866","https://openalex.org/W6778883912","https://openalex.org/W6803023527","https://openalex.org/W6810738896","https://openalex.org/W6846867676","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6851948999","https://openalex.org/W6852932568","https://openalex.org/W6856051742","https://openalex.org/W6856154222","https://openalex.org/W6856533554","https://openalex.org/W6856965252","https://openalex.org/W6859788467","https://openalex.org/W6860679478","https://openalex.org/W6862844530"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433"],"abstract_inverted_index":{"The":[0,185],"rapid":[1],"development":[2],"of":[3,52,58,90],"multimodal":[4,35],"large":[5,27],"language":[6,28],"models":[7,29],"(MLLMs)":[8],"has":[9],"brought":[10],"significant":[11],"breakthroughs":[12],"to":[13,31,40,48,77,102,120],"this":[14],"field.":[15],"However,":[16],"current":[17],"MLLMs":[18],"typically":[19],"rely":[20],"on":[21,26,154,176],"vision":[22,53,127],"instruction":[23,54,128],"tuning":[24],"based":[25],"(LLMs)":[30],"endow":[32],"them":[33],"with":[34],"capabilities,":[36],"which":[37,98,130],"may":[38],"lead":[39],"low":[41],"video":[42,83,135,178],"utilization":[43,180],"and":[44,147,168,181],"catastrophic":[45,96,141,182],"forgetting":[46,183],"due":[47],"the":[49,86,92,132,177],"task-specific":[50],"nature":[51],"tuning.":[55],"Take":[56],"case":[57],"multiple-choice":[59],"Video":[60],"Question":[61],"Answering":[62],"(VideoQA)":[63],"as":[64],"an":[65],"example,":[66],"requiring":[67],"only":[68],"selecting":[69],"correct":[70,93],"answers":[71],"makes":[72],"it":[73,160],"easier":[74],"for":[75],"LLMs":[76,101,119],"shortcut":[78],"rather":[79],"than":[80],"fully":[81],"comprehend":[82],"content.":[84],"Moreover,":[85],"fixed":[87],"task":[88],"format":[89],"\u2019\u2019predicting":[91],"option\"":[94],"risks":[95],"forgetting,":[97,142],"can":[99],"cause":[100],"lose":[103],"their":[104],"origin":[105],"cognitive":[106],"abilities.":[107],"To":[108],"address":[109],"this,":[110],"we":[111,171],"propose":[112],"ViCo,":[113],"a":[114,122],"training":[115],"framework":[116],"that":[117],"enables":[118],"perform":[121],"specific":[123],"auxiliary":[124],"tasks":[125],"during":[126],"tuning,":[129],"helps":[131],"model":[133],"leverage":[134],"information":[136,179],"more":[137],"thoroughly":[138],"while":[139],"mitigating":[140],"thereby":[143],"improving":[144],"modality":[145],"alignment":[146],"enhancing":[148],"performance.":[149],"We":[150],"evaluate":[151],"our":[152],"method":[153],"several":[155],"strong":[156],"VideoQA":[157],"benchmarks,":[158],"where":[159],"outperforms":[161],"all":[162],"state-of-the-art":[163],"methods,":[164],"demonstrating":[165],"its":[166],"effectiveness":[167],"generality.":[169],"Additionally,":[170],"also":[172],"provide":[173],"extensive":[174],"analysis":[175],"resulting.":[184],"code":[186],"will":[187],"be":[188],"made":[189],"available":[190],"at":[191],"https://github.com/dunknsabsw/ViCo.":[192]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}