{"id":"https://openalex.org/W2982139784","doi":"https://doi.org/10.1145/3343031.3350969","title":"Question-Aware Tube-Switch Network for Video Question Answering","display_name":"Question-Aware Tube-Switch Network for Video Question Answering","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2982139784","doi":"https://doi.org/10.1145/3343031.3350969","mag":"2982139784"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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/A5042851991","display_name":"Tianhao Yang","orcid":"https://orcid.org/0009-0004-8864-0420"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianhao Yang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025747301","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0001-7960-5608"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042851991"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.9232,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89347496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1184","last_page":"1192"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.7956991195678711},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.664031982421875},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6171267032623291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5732690095901489},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5087271332740784},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4705120921134949},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44811636209487915},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4475197196006775},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4154731035232544},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14862743020057678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956991195678711},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.664031982421875},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6171267032623291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5732690095901489},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5087271332740784},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4705120921134949},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44811636209487915},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4475197196006775},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4154731035232544},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14862743020057678},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3350969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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":29,"referenced_works":["https://openalex.org/W10548402","https://openalex.org/W1522734439","https://openalex.org/W1933349210","https://openalex.org/W2095536970","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2425121537","https://openalex.org/W2463565445","https://openalex.org/W2546696630","https://openalex.org/W2558535589","https://openalex.org/W2606982687","https://openalex.org/W2622980782","https://openalex.org/W2735159761","https://openalex.org/W2741903908","https://openalex.org/W2752803734","https://openalex.org/W2765716052","https://openalex.org/W2798786641","https://openalex.org/W2904452845","https://openalex.org/W2962835968","https://openalex.org/W2962911528","https://openalex.org/W2962933067","https://openalex.org/W2962949233","https://openalex.org/W2963150162","https://openalex.org/W2963403868","https://openalex.org/W2963954913","https://openalex.org/W2964345792","https://openalex.org/W3006305366","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W3005627584","https://openalex.org/W4303493643"],"abstract_inverted_index":{"Video":[0],"Question":[1],"&":[2],"Answering":[3],"(VideoQA),":[4],"a":[5,102,116,147],"task":[6],"to":[7,37,63,119,151,178],"answer":[8],"questions":[9,71],"in":[10,84,94],"videos,":[11],"involves":[12],"rich":[13],"spatio-temporal":[14],"content":[15],"(e.g.,":[16],"appearance":[17,31,42,54,88,123,138,154],"and":[18,20,32,35,43,55,61,89,124,135,139,145,192],"motion)":[19],"requires":[21],"multi-hop":[22,166],"reasoning":[23,162,167],"process.":[24,168,184],"However,":[25],"existing":[26],"methods":[27],"usually":[28,59],"deal":[29],"with":[30],"motion":[33,44,56,90,125,140,156],"separately":[34],"fail":[36],"synchronize":[38],"the":[39,85,122,165,175,181,197],"attentions":[40],"on":[41,73,188,203],"features,":[45],"neglecting":[46],"two":[47,189],"key":[48],"properties":[49],"of":[50,76,79],"video":[51,110],"QA:":[52],"(1)":[53,115],"features":[57,80],"are":[58],"concomitant":[60],"complementary":[62],"each":[64,161],"other":[65],"at":[66,81,127,141,160],"time":[67,128,143],"slice":[68,129,144],"level.":[69],"Some":[70],"rely":[72],"joint":[74],"representations":[75],"both":[77],"kinds":[78],"some":[82],"point":[83],"video;":[86],"(2)":[87,146],"have":[91,194],"different":[92],"importance":[93],"multi-step":[95],"reasoning.":[96],"In":[97],"this":[98],"paper,":[99],"we":[100,173],"propose":[101],"novel":[103],"Question-":[104],"Aware":[105],"Tube-Switch":[106],"Network":[107],"(TSN)":[108],"for":[109,180],"question":[111],"answering":[112],"which":[113],"contains":[114],"Mix":[117],"module":[118],"synchronously":[120],"combine":[121],"representation":[126],"level,":[130],"achieving":[131],"fine-grained":[132],"temporal":[133],"alignment":[134],"correspondence":[136],"between":[137],"every":[142],"Switch":[148],"mod-":[149],"ule":[150],"adaptively":[152],"choose":[153],"or":[155],"tube":[157],"as":[158],"primary":[159],"step,":[163],"guiding":[164],"To":[169],"end-to-end":[170],"train":[171],"TSN,":[172],"utilize":[174],"Gumbel-Softmax":[176],"strategy":[177],"account":[179],"discrete":[182],"tube-switch":[183],"Extensive":[185],"experimental":[186],"results":[187],"benchmarks:":[190],"MSVD-QA":[191],"MSRVTT-QA,":[193],"demonstrated":[195],"that":[196],"proposed":[198],"TSN":[199],"consistently":[200],"outperforms":[201],"state-of-the-art":[202],"all":[204],"metrics.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}