{"id":"https://openalex.org/W3015961436","doi":"https://doi.org/10.1109/icassp40776.2020.9053476","title":"Video Question Generation via Semantic Rich Cross-Modal Self-Attention Networks Learning","display_name":"Video Question Generation via Semantic Rich Cross-Modal Self-Attention Networks Learning","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015961436","doi":"https://doi.org/10.1109/icassp40776.2020.9053476","mag":"3015961436"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5036991952","display_name":"Yu-Siang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yu-Siang Wang","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034130957","display_name":"Hung-Ting Su","orcid":"https://orcid.org/0009-0007-5212-0927"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Ting Su","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034474223","display_name":"Chen-Hsi Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen-Hsi Chang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101507289","display_name":"Zheyu Liu","orcid":"https://orcid.org/0000-0002-1696-6980"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zhe-Yu Liu","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043898632","display_name":"Winston H. Hsu","orcid":"https://orcid.org/0000-0002-3330-0638"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Winston H. Hsu","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036991952"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.4885,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.64665255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2423","last_page":"2427"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9944999814033508,"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":0.845988929271698},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6146093010902405},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5533881187438965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5420873761177063},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48816996812820435},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48674798011779785},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4819376468658447},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4818904995918274},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4499741494655609},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3284139633178711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845988929271698},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6146093010902405},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5533881187438965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5420873761177063},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48816996812820435},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48674798011779785},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4819376468658447},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4818904995918274},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4499741494655609},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3284139633178711},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1586939924","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2581101319","https://openalex.org/W2606982687","https://openalex.org/W2774005037","https://openalex.org/W2902680410","https://openalex.org/W2905141912","https://openalex.org/W2950697717","https://openalex.org/W2962717047","https://openalex.org/W2963109634","https://openalex.org/W2963403868","https://openalex.org/W2963541336","https://openalex.org/W2963565375","https://openalex.org/W2963890755","https://openalex.org/W2963976294","https://openalex.org/W2964241990","https://openalex.org/W3127545373","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6746518932","https://openalex.org/W6756328832","https://openalex.org/W6757670774"],"related_works":["https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2616627668","https://openalex.org/W2083530853","https://openalex.org/W3137121595","https://openalex.org/W2009831055","https://openalex.org/W2393172683","https://openalex.org/W1976369278"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,18,28,55,124],"novel":[3,56,125],"task,":[4],"Video":[5,11,25],"Question":[6],"Generation":[7],"(Video":[8],"QG).":[9],"A":[10],"QG":[12,26],"model":[13,101],"automatically":[14],"generates":[15],"questions":[16],"given":[17],"video":[19,77,94,131],"clip":[20],"and":[21,41,43,67,85,133],"its":[22],"corresponding":[23],"dialogues.":[24],"requires":[27],"range":[29],"of":[30,119,140],"skills":[31],"-":[32],"sentence":[33],"comprehension,":[34],"temporal":[35],"relation,":[36],"the":[37,44,65,76,82,89,93,104,111,115,129,144],"interplay":[38],"between":[39],"vision":[40],"language,":[42],"ability":[45],"to":[46,63,108],"ask":[47],"meaningful":[48],"questions.":[49],"To":[50,70],"address":[51],"this,":[52],"we":[53,74,86,121,134],"propose":[54],"semantic":[57,79],"rich":[58],"cross-modal":[59,90],"self-attention":[60],"(SR-CMSA)":[61],"network":[62],"aggregate":[64],"multi-modal":[66],"diverse":[68],"features.":[69],"be":[71],"more":[72],"precise,":[73],"enhance":[75],"frames":[78],"by":[80],"integrating":[81],"object-level":[83],"information,":[84],"jointly":[87],"consider":[88],"attention":[91],"for":[92,146],"question":[95],"generation":[96],"task.":[97],"Excitingly,":[98],"our":[99],"proposed":[100],"remarkably":[102],"improves":[103],"baseline":[105],"from":[106],"7.58":[107],"14.48":[109],"in":[110,138],"BLEU-4":[112],"score":[113],"on":[114],"TVQA":[116],"dataset.":[117],"Most":[118],"all,":[120],"arguably":[122],"pave":[123],"path":[126],"toward":[127],"understanding":[128],"challenging":[130],"input":[132],"provide":[135],"detailed":[136],"analysis":[137],"terms":[139],"diversity,":[141],"which":[142],"ushers":[143],"avenues":[145],"future":[147],"investigations.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}