{"id":"https://openalex.org/W3093534251","doi":"https://doi.org/10.1145/3382507.3418886","title":"Temporal Attention and Consistency Measuring for Video Question Answering","display_name":"Temporal Attention and Consistency Measuring for Video Question Answering","publication_year":2020,"publication_date":"2020-10-21","ids":{"openalex":"https://openalex.org/W3093534251","doi":"https://doi.org/10.1145/3382507.3418886","mag":"3093534251"},"language":"en","primary_location":{"id":"doi:10.1145/3382507.3418886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3382507.3418886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","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/A5100758898","display_name":"Lingyu Zhang","orcid":"https://orcid.org/0000-0002-2197-1303"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lingyu Zhang","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049207791","display_name":"Richard J. Radke","orcid":"https://orcid.org/0000-0001-5064-7775"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard J. Radke","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100758898"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50467164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"510","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9975000023841858,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.8129088878631592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8008207082748413},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7376465797424316},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6047176718711853},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5803594589233398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5700405836105347},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5025651454925537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49229466915130615},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42134231328964233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37552598118782043},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10592544078826904}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.8129088878631592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008207082748413},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7376465797424316},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6047176718711853},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5803594589233398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5700405836105347},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5025651454925537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49229466915130615},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42134231328964233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37552598118782043},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10592544078826904},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3382507.3418886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3382507.3418886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4869332778","display_name":null,"funder_award_id":"IIP-1631674","funder_id":"https://openalex.org/F4320309085","funder_display_name":"Center for Selective C-H Functionalization, National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320309085","display_name":"Center for Selective C-H Functionalization, National Science Foundation","ror":"https://ror.org/02h8v7m77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W41740415","https://openalex.org/W1595942023","https://openalex.org/W1933349210","https://openalex.org/W1975325338","https://openalex.org/W1995820507","https://openalex.org/W2064675550","https://openalex.org/W2095176743","https://openalex.org/W2131774270","https://openalex.org/W2142900973","https://openalex.org/W2148839887","https://openalex.org/W2157331557","https://openalex.org/W2560730294","https://openalex.org/W2599765304","https://openalex.org/W2605585413","https://openalex.org/W2737435850","https://openalex.org/W2741903908","https://openalex.org/W2747681861","https://openalex.org/W2768874814","https://openalex.org/W2788713610","https://openalex.org/W2894729651","https://openalex.org/W2895776773","https://openalex.org/W2950761309","https://openalex.org/W2962938145","https://openalex.org/W2963177403","https://openalex.org/W2963293463","https://openalex.org/W2963446712","https://openalex.org/W2963541336","https://openalex.org/W2963613897","https://openalex.org/W2964010806","https://openalex.org/W2964306921","https://openalex.org/W2967701209","https://openalex.org/W2981040244","https://openalex.org/W2981101532","https://openalex.org/W3022759717","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/W4212839359"],"abstract_inverted_index":{"Social":[0],"signal":[1],"processing":[2],"algorithms":[3],"have":[4],"become":[5],"increasingly":[6],"better":[7],"at":[8],"solving":[9],"well-defined":[10],"prediction":[11],"and":[12,25,30,87,92,95,110,152],"estimation":[13],"problems":[14],"in":[15,67,89,129],"audiovisual":[16,46],"recordings":[17,47],"of":[18,40,48,117,140,150],"group":[19],"discussion.":[20],"However,":[21],"much":[22],"human":[23,49,65],"behavior":[24],"communication":[26],"is":[27,53],"less":[28],"structured":[29],"more":[31],"subtle.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"address":[37],"the":[38,56,90,102,105,108,111,121,124,141,145],"problem":[39],"generic":[41],"question":[42,63,91],"answering":[43],"from":[44],"diverse":[45],"interaction.":[50],"The":[51],"goal":[52],"to":[54,60,123],"select":[55],"correct":[57],"free-text":[58,62],"answer":[59],"a":[61,68,79,96,130],"about":[64],"interaction":[66],"video.":[69],"We":[70,133],"propose":[71],"an":[72],"RNN-based":[73],"model":[74,137],"with":[75],"two":[76],"novel":[77],"ideas:":[78],"temporal":[80],"attention":[81],"module":[82,99],"that":[83,100,135],"highlights":[84],"key":[85],"words":[86],"phrases":[88],"candidate":[93,112],"answers,":[94],"consistency":[97,118],"measurement":[98],"scores":[101,119],"similarity":[103],"between":[104],"multimodal":[106],"data,":[107],"question,":[109],"answers.":[113],"This":[114],"small":[115],"set":[116],"forms":[120],"input":[122],"final":[125],"question-answering":[126],"stage,":[127],"resulting":[128],"lightweight":[131],"model.":[132],"demonstrate":[134],"our":[136],"achieves":[138],"state":[139],"art":[142],"accuracy":[143],"on":[144],"Social-IQ":[146],"dataset":[147],"containing":[148],"hundreds":[149],"videos":[151],"question/answer":[153],"pairs.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}