{"id":"https://openalex.org/W2751608058","doi":"https://doi.org/10.1109/icme.2017.8019540","title":"Adaptive attention fusion network for visual question answering","display_name":"Adaptive attention fusion network for visual question answering","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2751608058","doi":"https://doi.org/10.1109/icme.2017.8019540","mag":"2751608058"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2017.8019540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","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/A5102375302","display_name":"Geonmo Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geonmo Gu","raw_affiliation_strings":["Image and Video Systems Lab., KAIST, Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab., KAIST, Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646694","display_name":"Seong Tae Kim","orcid":"https://orcid.org/0000-0002-2132-6021"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong Tae Kim","raw_affiliation_strings":["Image and Video Systems Lab., Korea Advanced Institute of Science and Technology, Daejeon, Daejeon, KR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab., Korea Advanced Institute of Science and Technology, Daejeon, Daejeon, KR","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Image and Video Systems Lab., Korea Advanced Institute of Science and Technology, Daejeon, Daejeon, KR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab., Korea Advanced Institute of Science and Technology, Daejeon, Daejeon, KR","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"997","last_page":"1002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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":0.9959999918937683,"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/question-answering","display_name":"Question answering","score":0.8512821793556213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7840836048126221},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.7301200032234192},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6284399032592773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6261107921600342},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6100199818611145},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5932079553604126},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5851073861122131},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.540263295173645},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5224567651748657},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42180997133255005},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4015205204486847},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33829593658447266},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08226335048675537}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8512821793556213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840836048126221},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.7301200032234192},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6284399032592773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6261107921600342},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6100199818611145},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5932079553604126},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5851073861122131},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.540263295173645},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5224567651748657},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42180997133255005},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4015205204486847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33829593658447266},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08226335048675537},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2017.8019540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1575833922","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2136480620","https://openalex.org/W2142192571","https://openalex.org/W2143017621","https://openalex.org/W2293453011","https://openalex.org/W2463565445","https://openalex.org/W2546696630","https://openalex.org/W2962835968","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963579811","https://openalex.org/W2963668159","https://openalex.org/W2963672682","https://openalex.org/W2963954913","https://openalex.org/W4251372957","https://openalex.org/W6622239757","https://openalex.org/W6634232107","https://openalex.org/W6636501129","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6697449767","https://openalex.org/W6719057275"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W4286432911","https://openalex.org/W2147241511","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W4200629926"],"abstract_inverted_index":{"Automatic":[0],"understanding":[1],"of":[2,5,34,40,66,116],"the":[3,28,32,35,55,59,80,84,94,100,108],"content":[4],"a":[6,21],"reference":[7],"image":[8],"and":[9,73,77],"natural":[10],"language":[11],"questions":[12],"is":[13],"needed":[14],"in":[15,114],"Visual":[16],"Question":[17],"Answering":[18],"(VQA).":[19],"Generating":[20],"visual":[22],"attention":[23,60],"map":[24],"that":[25,107],"focuses":[26],"on":[27,63,93],"regions":[29],"related":[30],"to":[31,82,98],"context":[33],"question":[36,74],"can":[37],"improve":[38],"performance":[39],"VQA.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"adaptive":[47],"attention-based":[48],"VQA":[49],"network.":[50],"The":[51],"proposed":[52,101,109],"method":[53,110],"utilizes":[54],"complementary":[56],"information":[57,81],"from":[58],"maps":[61],"depending":[62],"three":[64],"levels":[65],"word":[67],"embedding":[68],"(word":[69],"level,":[70,72],"phrase":[71],"level":[75],"embedding),":[76],"adaptively":[78],"fuses":[79],"represent":[83],"image-question":[85],"pair":[86],"appropriately.":[87],"Comparative":[88],"experiments":[89],"have":[90,105],"been":[91],"conducted":[92],"public":[95],"COCO-QA":[96],"database":[97],"validate":[99],"method.":[102],"Experimental":[103],"results":[104],"shown":[106],"outperforms":[111],"previous":[112],"methods":[113],"terms":[115],"accuracy.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}