{"id":"https://openalex.org/W4387968406","doi":"https://doi.org/10.1145/3581783.3612239","title":"Advancing Video Question Answering with a Multi-modal and Multi-layer Question Enhancement Network","display_name":"Advancing Video Question Answering with a Multi-modal and Multi-layer Question Enhancement Network","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968406","doi":"https://doi.org/10.1145/3581783.3612239"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-1582-5764","affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101758971","display_name":"Fenglei Zhang","orcid":"https://orcid.org/0009-0001-8758-2773"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenglei Zhang","raw_affiliation_strings":["Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0001-8758-2773","affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052168662","display_name":"Xin Luo","orcid":"https://orcid.org/0000-0002-6901-5476"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Luo","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-6901-5476","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015170265","display_name":"Fan Liu","orcid":"https://orcid.org/0000-0002-4547-3982"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fan Liu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4547-3982","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039731055","display_name":"Yinwei Wei","orcid":"https://orcid.org/0000-0003-1791-3159"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yinwei Wei","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1791-3159","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100457438"],"corresponding_institution_ids":["https://openalex.org/I44445938"],"apc_list":null,"apc_paid":null,"fwci":0.942,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77672209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3985","last_page":"3993"},"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":0.9923999905586243,"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":0.9857000112533569,"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":0.8014512658119202},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7003238797187805},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6453604698181152},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.6071102619171143},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6065942645072937},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5640086531639099},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5157065987586975},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5149227380752563},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5118257403373718},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5047925710678101},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5003058910369873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46344876289367676},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4355160593986511},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.43216097354888916},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33797022700309753},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3290918171405792},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.0892903208732605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014512658119202},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7003238797187805},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6453604698181152},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6071102619171143},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6065942645072937},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5640086531639099},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5157065987586975},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5149227380752563},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5118257403373718},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5047925710678101},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5003058910369873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46344876289367676},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4355160593986511},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.43216097354888916},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33797022700309753},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3290918171405792},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0892903208732605},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612239","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1082305147","display_name":null,"funder_award_id":"HR0011-22-2-0047","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5630254371","display_name":null,"funder_award_id":"62236003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7231895066","display_name":null,"funder_award_id":"U1936203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7696304900","display_name":null,"funder_award_id":"62006142","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"},{"id":"https://openalex.org/F4320324777","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2565656701","https://openalex.org/W2606982687","https://openalex.org/W2735159761","https://openalex.org/W2741903908","https://openalex.org/W2751525844","https://openalex.org/W2765716052","https://openalex.org/W2766690867","https://openalex.org/W2770959695","https://openalex.org/W2890904455","https://openalex.org/W2904291752","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2998166190","https://openalex.org/W3034336960","https://openalex.org/W3034425145","https://openalex.org/W3100712674","https://openalex.org/W3155230099","https://openalex.org/W3155817208","https://openalex.org/W3171694158","https://openalex.org/W3173367591","https://openalex.org/W3203995540","https://openalex.org/W4200631219","https://openalex.org/W4226424035","https://openalex.org/W4281773633","https://openalex.org/W4285600797","https://openalex.org/W4304092645","https://openalex.org/W4312246181","https://openalex.org/W6600474606","https://openalex.org/W6794467314"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W165915117","https://openalex.org/W2326995835","https://openalex.org/W2743859443","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2477150073","https://openalex.org/W2019547100","https://openalex.org/W4387947522"],"abstract_inverted_index":{"Video":[0],"question":[1,54,66,74,114,126,131,158],"answering":[2],"is":[3,110],"an":[4],"increasingly":[5],"vital":[6],"research":[7],"field,":[8],"spurred":[9],"by":[10,79,112],"the":[11,19,49,62,103,119,147,154],"rapid":[12],"proliferation":[13],"of":[14,52,102,122,149,156],"video":[15,38],"content":[16],"online":[17],"and":[18,28,40,64,83,115,124],"urgent":[20],"need":[21],"for":[22],"intelligent":[23],"systems":[24],"that":[25],"can":[26],"comprehend":[27],"interact":[29],"with":[30],"this":[31,58],"content.":[32],"Existing":[33],"methodologies":[34],"often":[35],"lean":[36],"towards":[37],"understanding":[39],"cross-modal":[41],"information":[42],"interaction":[43],"modeling":[44],"but":[45],"tend":[46],"to":[47,138],"overlook":[48],"crucial":[50],"aspect":[51],"comprehensive":[53],"understanding.":[55,75],"To":[56],"address":[57],"gap,":[59],"we":[60,89],"introduce":[61],"multi-modal":[63,130],"multi-layer":[65,91],"enhancement":[67],"network,":[68],"a":[69,94,99],"groundbreaking":[70],"framework":[71],"emphasizing":[72],"nuanced":[73],"Our":[76],"approach":[77],"begins":[78],"extracting":[80],"object,":[81],"appearance,":[82],"motion":[84],"features":[85],"from":[86,93],"videos.":[87],"Subsequently,":[88],"harness":[90],"outputs":[92],"pre-trained":[95],"language":[96],"model,":[97],"ensuring":[98],"thorough":[100],"grasp":[101],"question.":[104],"Integrating":[105],"object":[106],"data":[107],"into":[108],"appearance":[109,123],"guided":[111],"global":[113],"frame":[116],"representation,":[117],"facilitating":[118],"adaptive":[120],"acquisition":[121],"motion-enhanced":[125],"representation.":[127],"By":[128],"amalgamating":[129],"insights,":[132],"our":[133,150],"methodology":[134],"adeptly":[135],"determines":[136],"answers":[137],"questions.":[139],"Experimental":[140],"results":[141],"conducted":[142],"on":[143],"three":[144],"benchmarks":[145],"demonstrate":[146],"superiority":[148],"tailored":[151],"approach,":[152],"underscoring":[153],"importance":[155],"advanced":[157],"comprehension":[159],"in":[160],"VideoQA.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}