{"id":"https://openalex.org/W4402979063","doi":"https://doi.org/10.1109/icme57554.2024.10687903","title":"Robust VQA via Internal and External Interaction of Modal Information and Question Transformation","display_name":"Robust VQA via Internal and External Interaction of Modal Information and Question Transformation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979063","doi":"https://doi.org/10.1109/icme57554.2024.10687903"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687903","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5113409454","display_name":"Dahe Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dahe Peng","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113409455","display_name":"Rongrong Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Shen","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":"https://orcid.org/0000-0002-5313-6134"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Li","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113409454"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14577621,"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/T10028","display_name":"Topic Modeling","score":0.989799976348877,"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/T10028","display_name":"Topic Modeling","score":0.989799976348877,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9225999712944031,"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/modal","display_name":"Modal","score":0.7219536304473877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.582061231136322},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5694042444229126}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7219536304473877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.582061231136322},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5694042444229126},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687903","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4],"a":[5,25,65,107],"critical":[6],"multimodal":[7],"task.":[8],"Many":[9],"VQA":[10,28],"models":[11],"have":[12],"been":[13],"shown":[14],"to":[15,30,84,106,115],"rely":[16],"on":[17,132],"language":[18,50],"prior.":[19],"To":[20],"this":[21],"end,":[22],"we":[23,63],"propose":[24],"new":[26],"unbiased":[27],"method":[29,126],"solve":[31],"the":[32,37,53,82,90,99,112,118,133],"question":[33,101],"of":[34,39,44,49,55,60,92],"bias":[35],"from":[36],"perspective":[38],"internal":[40,56],"and":[41,47,57,71,73,110],"external":[42,58],"interaction":[43,59],"modal":[45,61],"information":[46],"transformation":[48],"question.":[51],"In":[52,89],"part":[54,91],"information,":[62],"design":[64],"module":[66,75],"that":[67,76,124],"interacts":[68,78],"with":[69,79],"questions":[70],"images":[72],"another":[74],"only":[77],"itself":[80],"within":[81],"image":[83],"generate":[85],"advanced":[86],"visual":[87],"features.":[88],"linguistic":[93],"prior":[94],"capture":[95],"branch,":[96],"We":[97],"transform":[98],"original":[100],"into":[102],"three":[103,113],"sub-questions":[104,114],"according":[105],"certain":[108],"strategy,":[109],"input":[111],"participate":[116],"in":[117],"training":[119],"process.":[120],"Extensive":[121],"experiments":[122],"show":[123],"our":[125],"achieves":[127],"very":[128],"competitive":[129],"performance":[130],"(61.45%)":[131],"VQA-CP":[134],"v2":[135],"dataset.":[136]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}