{"id":"https://openalex.org/W4385681696","doi":"https://doi.org/10.1145/3581783.3612577","title":"Redundancy-aware Transformer for Video Question Answering","display_name":"Redundancy-aware Transformer for Video Question Answering","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385681696","doi":"https://doi.org/10.1145/3581783.3612577"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612577","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.03267","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101762861","display_name":"Yicong Li","orcid":"https://orcid.org/0000-0002-5659-793X"},"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":true,"raw_author_name":"Yicong Li","raw_affiliation_strings":["National University of Singapore, singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5659-793X","affiliations":[{"raw_affiliation_string":"National University of Singapore, singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034737032","display_name":"Xun Yang","orcid":"https://orcid.org/0000-0003-0201-1638"},"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":"Xun Yang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0201-1638","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/A5100601645","display_name":"An Zhang","orcid":"https://orcid.org/0000-0003-1367-711X"},"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":"An Zhang","raw_affiliation_strings":["National University of Singapore, singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1367-711X","affiliations":[{"raw_affiliation_string":"National University of Singapore, singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101876211","display_name":"Chun Feng","orcid":"https://orcid.org/0009-0007-6209-1664"},"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":"Chun Feng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-6209-1664","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/A5100389037","display_name":"Xiang Wang","orcid":"https://orcid.org/0000-0002-6148-6329"},"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":"Xiang Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6148-6329","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"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":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101762861"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":2.3199,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90425102,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3172","last_page":"3180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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":0.9979000091552734,"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":0.7433095574378967},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5895536541938782},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5257821083068848},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5070362091064453},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3282673954963684},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12200358510017395},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.113528311252594},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10155630111694336},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09158322215080261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433095574378967},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5895536541938782},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5257821083068848},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5070362091064453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3282673954963684},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12200358510017395},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.113528311252594},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10155630111694336},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09158322215080261}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612577","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"},{"id":"pmh:oai:arXiv.org:2308.03267","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.03267","pdf_url":"https://arxiv.org/pdf/2308.03267","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.03267","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.03267","pdf_url":"https://arxiv.org/pdf/2308.03267","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G405190135","display_name":null,"funder_award_id":"U22A2094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6730572696","display_name":null,"funder_award_id":"9227010114","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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385681696.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2096516049","https://openalex.org/W2282821441","https://openalex.org/W2562731582","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2788527488","https://openalex.org/W2951323451","https://openalex.org/W2955124656","https://openalex.org/W2963798744","https://openalex.org/W2979997102","https://openalex.org/W2998166190","https://openalex.org/W3034730770","https://openalex.org/W3035517717","https://openalex.org/W3092803144","https://openalex.org/W3109142545","https://openalex.org/W3122890974","https://openalex.org/W3130796238","https://openalex.org/W3132939773","https://openalex.org/W3152619510","https://openalex.org/W3167092180","https://openalex.org/W3168124404","https://openalex.org/W3175961224","https://openalex.org/W3189890868","https://openalex.org/W3195986544","https://openalex.org/W3204980132","https://openalex.org/W3205572000","https://openalex.org/W3205874482","https://openalex.org/W3206633059","https://openalex.org/W3206675006","https://openalex.org/W3217054538","https://openalex.org/W4200631219","https://openalex.org/W4205817612","https://openalex.org/W4221146190","https://openalex.org/W4226407477","https://openalex.org/W4285428166","https://openalex.org/W4285600797","https://openalex.org/W4293567872","https://openalex.org/W4298613318","https://openalex.org/W4304098887","https://openalex.org/W4307123990","https://openalex.org/W4312246181","https://openalex.org/W4312761939","https://openalex.org/W4312974690","https://openalex.org/W4313071966","https://openalex.org/W4323663038","https://openalex.org/W4385245566","https://openalex.org/W4385572712","https://openalex.org/W4386075974","https://openalex.org/W4387968166","https://openalex.org/W6790241037"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W4381058564","https://openalex.org/W3003945460","https://openalex.org/W2964413124","https://openalex.org/W4288267738"],"abstract_inverted_index":{"This":[0],"paper":[1],"identifies":[2],"two":[3],"kinds":[4],"of":[5,153],"redundancy":[6,34,52],"in":[7,27,91,111],"the":[8,13,42,75,97,108,129,145,159],"current":[9,14],"VideoQA":[10,90,178],"paradigm.":[11],"Specifically,":[12],"video":[15,22,103],"encoders":[16],"tend":[17],"to":[18,88],"holistically":[19],"embed":[20],"all":[21,56],"clues":[23,40],"at":[24,41],"different":[25],"granularities":[26],"a":[28,71,82,92,102,138,150],"hierarchical":[29],"manner,":[30],"which":[31,142],"inevitably":[32],"introducesneighboring-frame":[33],"that":[35,86,106,120,156],"can":[36,172],"overwhelm":[37],"detailed":[38],"visual":[39,57,154],"object":[43],"level.":[44],"Subsequently,":[45],"prevailing":[46],"vision-language":[47,67,146],"fusion":[48,135],"designs":[49],"introduce":[50,101],"thecross-modal":[51],"by":[53,148],"exhaustively":[54],"fusing":[55],"elements":[58,155],"with":[59,137],"question":[60],"tokens":[61],"without":[62],"explicitly":[63,143],"differentiating":[64],"their":[65],"pairwise":[66],"interactions,":[68],"thus":[69],"making":[70],"pernicious":[72],"impact":[73],"on":[74,124,176],"answering.":[76],"To":[77,95],"this":[78,166],"end,":[79],"we":[80,100,132,164],"propose":[81],"novel":[83,139],"transformer-based":[84],"architecture,":[85],"aims":[87],"model":[89],"redundancy-aware":[93],"manner.":[94],"address":[96],"neighboring-frame":[98],"redundancy,":[99,131],"encoder":[104],"structure":[105],"emphasizes":[107],"object-level":[109],"change":[110],"neighboring":[112],"frames,":[113],"while":[114],"adopting":[115],"an":[116],"out-of-neighboring":[117],"message-passing":[118],"scheme":[119],"imposes":[121],"attention":[122],"only":[123],"distant":[125],"frames.":[126],"As":[127],"for":[128],"cross-modal":[130],"equip":[133],"our":[134],"module":[136],"adaptive":[140],"sampling,":[141],"differentiates":[144],"interactions":[147],"identifying":[149],"small":[151],"subset":[152],"exclusively":[157],"support":[158],"answer.":[160],"Upon":[161],"these":[162],"advancements,":[163],"find":[165],"\\underlineR":[167],"edundancy-\\underlinea":[168],"ware":[169],"trans\\underlineformer":[170],"(RaFormer)":[171],"achieve":[173],"state-of-the-art":[174],"results":[175],"multiple":[177],"benchmarks.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
