{"id":"https://openalex.org/W4415708567","doi":"https://doi.org/10.1109/icme59968.2025.11209245","title":"DLVQA: A Dynamic Loss Approach For Visual Question Answering with Language Biases","display_name":"DLVQA: A Dynamic Loss Approach For Visual Question Answering with Language Biases","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708567","doi":"https://doi.org/10.1109/icme59968.2025.11209245"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5056873506","display_name":"Shuocheng Wang","orcid":"https://orcid.org/0000-0002-2362-3003"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuocheng Wang","raw_affiliation_strings":["Xiamen University,School of Information,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Information,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439373","display_name":"Zhenzhen Wang","orcid":"https://orcid.org/0000-0002-8775-7481"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Wang","raw_affiliation_strings":["Xiamen University,School of Information,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Information,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101590561","display_name":"Qingfeng Wu","orcid":"https://orcid.org/0000-0001-9201-0211"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfeng Wu","raw_affiliation_strings":["Xiamen University,School of Information,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Information,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26549362,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9894000291824341,"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":0.9894000291824341,"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":0.002300000051036477,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0017000000225380063,"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/question-answering","display_name":"Question answering","score":0.7990999817848206},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6769000291824341},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6029999852180481},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5497999787330627},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5095999836921692},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.39169999957084656},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38909998536109924},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.35659998655319214}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7990999817848206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737500011920929},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6769000291824341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6182000041007996},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46160000562667847},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37049999833106995},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2963644680","https://openalex.org/W3035517717","https://openalex.org/W3110575265","https://openalex.org/W3161559655","https://openalex.org/W3177934633","https://openalex.org/W3192587235","https://openalex.org/W4214825151","https://openalex.org/W4364377616","https://openalex.org/W4379660316","https://openalex.org/W4390872646","https://openalex.org/W4390873086"],"related_works":[],"abstract_inverted_index":{"This":[0,135],"study":[1],"tackles":[2],"the":[3,19,23,30,37,58,81,99,129,143,148,163,180],"language-dependent":[4],"bias":[5,79,185],"in":[6,112],"Visual":[7],"Question":[8],"Answering":[9],"(VQA)":[10],"models,":[11],"where":[12],"models":[13],"tend":[14],"to":[15,145],"rely":[16],"heavily":[17],"on":[18,45,108,173],"semantic":[20],"relationship":[21],"between":[22],"question":[24,133],"and":[25,49,115,124,139,152],"predefined":[26],"answers,":[27],"often":[28],"at":[29,57,76],"cost":[31],"of":[32,36,60,88,102,132,137,150,171,182],"a":[33,69],"deeper":[34],"understanding":[35],"image":[38],"content.":[39],"While":[40],"existing":[41],"methods":[42],"have":[43,54],"focused":[44],"improving":[46],"model":[47,144],"architectures":[48],"applying":[50],"data":[51],"augmentation,":[52],"few":[53],"explored":[55],"solutions":[56],"level":[59],"answer":[61,187],"feature":[62,82,188],"representation.":[63],"To":[64],"address":[65],"this,":[66],"we":[67],"propose":[68],"novel":[70],"dynamic":[71],"loss":[72],"function":[73],"framework":[74,86],"aimed":[75],"mitigating":[77],"linguistic":[78],"from":[80],"space":[83],"perspective.":[84],"The":[85],"consists":[87],"two":[89,174],"key":[90],"components:":[91],"(1)":[92],"an":[93,117,168],"answer-frequency-based":[94],"margining":[95,119],"mechanism,":[96],"which":[97],"balances":[98],"training":[100],"weights":[101],"answers":[103],"with":[104],"different":[105],"frequencies":[106],"based":[107],"their":[109],"statistical":[110],"occurrence":[111],"large-scale":[113],"datasets,":[114,177],"(2)":[116],"adaptive":[118,140],"component":[120],"that":[121,158],"dynamically":[122],"detects":[123],"corrects":[125],"potential":[126],"biases,":[127],"considering":[128],"unique":[130],"nature":[131],"branches.":[134],"fusion":[136],"frequency-based":[138],"margins":[141],"allows":[142],"better":[146],"regulate":[147],"learning":[149],"high-":[151],"low-frequency":[153],"answers.":[154],"Extensive":[155],"experiments":[156],"show":[157],"our":[159],"approach":[160],"significantly":[161],"enhances":[162],"VQA":[164],"model\u2019s":[165],"performance,":[166],"achieving":[167],"average":[169],"improvement":[170],"21%":[172],"representative":[175],"VQA-CP":[176],"thereby":[178],"demonstrating":[179],"effectiveness":[181],"addressing":[183],"language":[184],"through":[186],"learning.":[189]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-30T00:00:00"}