{"id":"https://openalex.org/W4226165889","doi":"https://doi.org/10.1145/3507548.3507567","title":"Keyword-aware Multi-modal Enhancement Attention for Video Question Answering","display_name":"Keyword-aware Multi-modal Enhancement Attention for Video Question Answering","publication_year":2021,"publication_date":"2021-12-04","ids":{"openalex":"https://openalex.org/W4226165889","doi":"https://doi.org/10.1145/3507548.3507567"},"language":"en","primary_location":{"id":"doi:10.1145/3507548.3507567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3507548.3507567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Computer Science and Artificial Intelligence","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/A5100646801","display_name":"Duo Chen","orcid":"https://orcid.org/0000-0002-0951-4687"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Duo Chen","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,National Engineering Research Center of Digital Life, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,National Engineering Research Center of Digital Life, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072166761","display_name":"Fuwei Zhang","orcid":"https://orcid.org/0000-0002-7711-866X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuwei Zhang","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,National Engineering Research Center of Digital Life, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,National Engineering Research Center of Digital Life, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028562449","display_name":"Shirou Ou","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shirou Ou","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,National Engineering Research Center of Digital Life, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,National Engineering Research Center of Digital Life, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000079751","display_name":"Ruomei Wang","orcid":"https://orcid.org/0000-0002-2712-4412"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruomei Wang","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,National Engineering Research Center of Digital Life, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,National Engineering Research Center of Digital Life, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100646801"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43589869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"133"},"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":0.9969000220298767,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.843037486076355},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7500731945037842},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6656312942504883},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5981927514076233},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5694177746772766},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5589835047721863},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5447441339492798},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5399221777915955},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5106754899024963},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49022942781448364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4140048027038574},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33876487612724304},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0650511085987091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843037486076355},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7500731945037842},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6656312942504883},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5981927514076233},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5694177746772766},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5589835047721863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5447441339492798},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5399221777915955},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5106754899024963},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49022942781448364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4140048027038574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33876487612724304},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0650511085987091},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3507548.3507567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3507548.3507567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Computer Science and Artificial Intelligence","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":8,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2334746500","https://openalex.org/W2884454321","https://openalex.org/W2885032934","https://openalex.org/W2909888383","https://openalex.org/W3003260174","https://openalex.org/W3117181316","https://openalex.org/W3174299660"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W4243305035","https://openalex.org/W1537496349","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Video":[0],"question":[1],"answering":[2],"(VideoQA)":[3],"is":[4,56,89,111],"an":[5],"intriguing":[6],"topic":[7],"in":[8,30,41,96],"the":[9,16,22,33,37,93,115,139],"field":[10],"of":[11,15,65,141],"visual":[12],"language.":[13],"Most":[14],"current":[17],"VideoQA":[18,31,55,132],"models":[19],"directly":[20],"harness":[21],"global":[23],"video":[24,44],"information":[25,95,116],"to":[26,58,91,113],"answer":[27],"questions.":[28],"However,":[29],"task,":[32],"answers":[34],"associated":[35,117],"with":[36,118],"questions":[38],"merely":[39],"appear":[40],"a":[42,62,74,83,105],"few":[43],"contents,":[45],"and":[46,51,121,136],"other":[47],"contents":[48],"are":[49],"invalid":[50],"redundant":[52],"information.":[53],"Therefore,":[54],"vulnerable":[57],"be":[59],"interfered":[60],"by":[61],"large":[63,131],"number":[64],"irrelevant":[66],"contents.":[67],"To":[68],"address":[69],"this":[70],"challenge,":[71],"we":[72],"propose":[73],"Keyword-aware":[75],"Multi-modal":[76],"Enhancement":[77],"Attention":[78],"model":[79],"for":[80],"VideoQA.":[81],"Specifically,":[82],"multi-factor":[84],"keyword":[85],"extraction":[86],"(MFKE)":[87],"algorithm":[88],"proposed":[90],"emphasize":[92],"crucial":[94],"multimodal":[97,123],"feature":[98],"extraction.":[99],"Furthermore,":[100],"based":[101],"on":[102,128],"attention":[103,108],"mechanisms,":[104],"keyword-aware":[106],"enhancement":[107],"(KAEA)":[109],"module":[110],"designed":[112],"correlate":[114],"multiple":[119],"modalities":[120],"fuse":[122],"features.":[124],"The":[125],"experimental":[126],"results":[127],"publicly":[129],"available":[130],"datasets,":[133],"namely":[134],"TVQA+":[135],"LifeQA,":[137],"demonstrate":[138],"effectiveness":[140],"our":[142],"model.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
