{"id":"https://openalex.org/W4387933309","doi":"https://doi.org/10.1145/3630101","title":"Hierarchical Synergy-Enhanced Multimodal Relational Network for Video Question Answering","display_name":"Hierarchical Synergy-Enhanced Multimodal Relational Network for Video Question Answering","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4387933309","doi":"https://doi.org/10.1145/3630101"},"language":"en","primary_location":{"id":"doi:10.1145/3630101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630101","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630101","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630101","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102012008","display_name":"Min Peng","orcid":"https://orcid.org/0000-0001-7445-5567"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Peng","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, China and Chongqing School, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, China and Chongqing School, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210123021","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074407139","display_name":"Xiaohu Shao","orcid":"https://orcid.org/0000-0003-1141-6020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohu Shao","raw_affiliation_strings":["Beijing IDRIVERPLUS Technology Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Beijing IDRIVERPLUS Technology Co., Ltd, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102842773","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0001-9117-8282"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090238197","display_name":"Xiangdong Zhou","orcid":"https://orcid.org/0000-0002-4451-5327"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Zhou","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210123021"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102012008"],"corresponding_institution_ids":["https://openalex.org/I4210123021","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2435,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5379497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"22"},"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":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9943000078201294,"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":0.8003196716308594},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6315274834632874},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6055935621261597},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6046321392059326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5707114934921265},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.552829921245575},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.49884724617004395},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4580996334552765},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4412892460823059},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3636559247970581},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11460483074188232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003196716308594},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6315274834632874},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6055935621261597},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6046321392059326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5707114934921265},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.552829921245575},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.49884724617004395},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4580996334552765},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4412892460823059},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3636559247970581},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11460483074188232},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"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},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630101","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630101","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3630101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630101","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630101","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G378428083","display_name":null,"funder_award_id":"62106247","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387933309.pdf","grobid_xml":"https://content.openalex.org/works/W4387933309.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2123442489","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2606982687","https://openalex.org/W2607303097","https://openalex.org/W2608239929","https://openalex.org/W2737435850","https://openalex.org/W2751525844","https://openalex.org/W2765716052","https://openalex.org/W2904452845","https://openalex.org/W2912894426","https://openalex.org/W2951161814","https://openalex.org/W2952620298","https://openalex.org/W2954199749","https://openalex.org/W2962934715","https://openalex.org/W2962949233","https://openalex.org/W2964057271","https://openalex.org/W2964101993","https://openalex.org/W2969663619","https://openalex.org/W2974161034","https://openalex.org/W2981582341","https://openalex.org/W2997344006","https://openalex.org/W2998166190","https://openalex.org/W3010593057","https://openalex.org/W3016658915","https://openalex.org/W3027790991","https://openalex.org/W3034730770","https://openalex.org/W3047995861","https://openalex.org/W3092661441","https://openalex.org/W3099768435","https://openalex.org/W3119243803","https://openalex.org/W3122622502","https://openalex.org/W3159630763","https://openalex.org/W3167092180","https://openalex.org/W3168640669","https://openalex.org/W3171694158","https://openalex.org/W3173432693","https://openalex.org/W3174364033","https://openalex.org/W3175961224","https://openalex.org/W3176398504","https://openalex.org/W3181758331","https://openalex.org/W3196930868","https://openalex.org/W3197457832","https://openalex.org/W3209229003","https://openalex.org/W4226289673","https://openalex.org/W4234552385","https://openalex.org/W4291149472","https://openalex.org/W4295036294","https://openalex.org/W4315880881","https://openalex.org/W4385573551"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297"],"abstract_inverted_index":{"Video":[0],"question":[1,28],"answering":[2],"(VideoQA)":[3],"is":[4,153,165],"challenging":[5],"as":[6],"it":[7],"requires":[8],"reasoning":[9],"about":[10],"natural":[11],"language":[12],"and":[13,29,49,55,93,104,112,127,152,158],"multimodal":[14,53,79,110,129],"interactive":[15],"relations.":[16],"Most":[17],"existing":[18],"methods":[19,41,170],"apply":[20],"attention":[21],"mechanisms":[22],"to":[23,33,58,83,107,125,134,167],"extract":[24,34],"interactions":[25,51,106],"between":[26,47,102],"the":[27,30,43,61,100,163,178,181],"video":[31],"or":[32],"effective":[35,109],"spatio-temporal":[36],"relational":[37,80],"representations.":[38],"However,":[39],"these":[40,85],"neglect":[42],"implication":[44],"of":[45,64,138,144,180,184],"relations":[46],"intra-":[48,103],"inter-modal":[50,105],"for":[52],"learning,":[54],"they":[56],"fail":[57],"fully":[59],"exploit":[60],"synergistic":[62,116,136],"effect":[63],"multiscale":[65],"semantics":[66,130],"in":[67],"answer":[68,139],"reasoning.":[69,140],"In":[70],"this":[71],"article,":[72],"we":[73,88],"propose":[74],"a":[75,91,114,121],"novel":[76],"hierarchical":[77,115],"synergy-enhanced":[78],"network":[81],"(HMRNet)":[82],"address":[84],"issues.":[86],"Specifically,":[87],"devise":[89],"(i)":[90],"compact":[92],"unified":[94],"relation-oriented":[95],"interaction":[96,123],"module":[97],"that":[98,119,162],"explores":[99],"relation":[101],"enable":[108],"learning;":[111],"(ii)":[113],"memory":[117],"unit":[118],"leverages":[120],"memory-based":[122],"scheme":[124],"complement":[126],"fuse":[128],"at":[131],"multiple":[132],"scales":[133],"achieve":[135],"enhancement":[137],"With":[141],"careful":[142],"design":[143],"each":[145],"component,":[146],"our":[147,185],"HMRNet":[148,164],"has":[149],"fewer":[150],"parameters":[151],"computationally":[154],"efficient.":[155],"Extensive":[156],"experiments":[157],"qualitative":[159],"analyses":[160],"demonstrate":[161,177],"superior":[166],"previous":[168],"state-of-the-art":[169],"on":[171],"eight":[172],"benchmark":[173],"datasets.":[174],"We":[175],"also":[176],"effectiveness":[179],"different":[182],"components":[183],"method.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}