{"id":"https://openalex.org/W2766690867","doi":"https://doi.org/10.1145/3123266.3123364","title":"Video Question Answering via Hierarchical Dual-Level Attention Network Learning","display_name":"Video Question Answering via Hierarchical Dual-Level Attention Network Learning","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2766690867","doi":"https://doi.org/10.1145/3123266.3123364","mag":"2766690867"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","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/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057700970","display_name":"Jinghao Lin","orcid":"https://orcid.org/0000-0002-9067-5946"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghao Lin","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075649586","display_name":"Xinghua Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghua Jiang","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013345","display_name":"Xiaofei He","orcid":"https://orcid.org/0009-0001-9107-2354"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei He","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079260216"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.9115,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.92044817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1050","last_page":"1058"},"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":0.9976999759674072,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9972000122070312,"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":0.9261970520019531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8432899713516235},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7192642688751221},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6289047598838806},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5434293150901794},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5236099362373352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5174282193183899},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5153862237930298},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.512638509273529},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4624716341495514},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.44609925150871277},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4208148121833801},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38947373628616333}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9261970520019531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8432899713516235},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7192642688751221},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6289047598838806},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5434293150901794},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5236099362373352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174282193183899},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5153862237930298},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.512638509273529},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4624716341495514},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.44609925150871277},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4208148121833801},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38947373628616333},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W1522734439","https://openalex.org/W1531374185","https://openalex.org/W1586939924","https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W1950136256","https://openalex.org/W1977800965","https://openalex.org/W2020600820","https://openalex.org/W2028285070","https://openalex.org/W2040614160","https://openalex.org/W2064675550","https://openalex.org/W2066610120","https://openalex.org/W2069682406","https://openalex.org/W2078784669","https://openalex.org/W2082828292","https://openalex.org/W2116435618","https://openalex.org/W2139343345","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2156303437","https://openalex.org/W2180092181","https://openalex.org/W2280737108","https://openalex.org/W2289324734","https://openalex.org/W2293453011","https://openalex.org/W2340502990","https://openalex.org/W2463565445","https://openalex.org/W2508497007","https://openalex.org/W2524259110","https://openalex.org/W2527195341","https://openalex.org/W2553418567","https://openalex.org/W2561715562","https://openalex.org/W2591644541","https://openalex.org/W2605350416","https://openalex.org/W2618530766","https://openalex.org/W2735159761","https://openalex.org/W2737435850","https://openalex.org/W2739103128","https://openalex.org/W2741530248","https://openalex.org/W2741903908","https://openalex.org/W2951008357","https://openalex.org/W2951619830","https://openalex.org/W2952005526","https://openalex.org/W2963191264","https://openalex.org/W2963293463","https://openalex.org/W2963843052","https://openalex.org/W2963890755","https://openalex.org/W2963917086","https://openalex.org/W2963954913","https://openalex.org/W3099768435"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W2810129309"],"abstract_inverted_index":{"Video":[0],"question":[1,30,40,49,71,143,150],"answering":[2,31,50,72,151],"is":[3],"a":[4],"challenging":[5],"task":[6],"in":[7,90],"visual":[8,29],"information":[9,89],"retrieval,":[10],"which":[11,42],"provides":[12],"the":[13,17,23,27,35,54,58,67,74,84,91,105,112,125,136,157],"accurate":[14],"answer":[15],"from":[16,73],"referenced":[18],"video":[19,48,59,70,92,114,139,142,149],"contents":[20],"according":[21],"to":[22,53,110,134],"given":[24],"question.":[25],"However,":[26],"existing":[28],"approaches":[32],"mainly":[33],"tackle":[34],"problem":[36,68],"of":[37,56,69,76,159],"static":[38],"image":[39],"answering,":[41],"may":[43],"be":[44],"ineffectively":[45],"applied":[46],"for":[47,130,141],"directly,":[51],"due":[52],"insufficiency":[55],"modeling":[57],"temporal":[60],"dynamics.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"study":[66],"viewpoint":[75],"hierarchical":[77,106],"dual-level":[78],"attention":[79,108,120,128],"network":[80],"learning.":[81],"We":[82,102,122,145],"obtain":[83],"object":[85],"appearance":[86],"and":[87,97,118],"movement":[88],"based":[93],"on":[94],"both":[95],"frame-level":[96],"segment-level":[98],"feature":[99],"representation":[100,140],"methods.":[101],"then":[103],"develop":[104],"duallevel":[107],"networks":[109,133],"learn":[111,135],"question-aware":[113],"representations":[115],"with":[116],"word-level":[117],"question-level":[119,126],"mechanisms.":[121],"next":[123],"devise":[124],"fusion":[127],"mechanism":[129],"our":[131,160],"proposed":[132],"questionaware":[137],"joint":[138],"answering.":[144],"construct":[146],"two":[147],"large-scale":[148],"datasets.":[152],"The":[153],"extensive":[154],"experiments":[155],"validate":[156],"effectiveness":[158],"method.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}