{"id":"https://openalex.org/W4407638878","doi":"https://doi.org/10.1109/tmm.2025.3543031","title":"Rethinking Temporal Context in Video-QA: A Comprehensive Study of Single-Frame Static Bias","display_name":"Rethinking Temporal Context in Video-QA: A Comprehensive Study of Single-Frame Static Bias","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407638878","doi":"https://doi.org/10.1109/tmm.2025.3543031"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3543031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3543031","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5101518959","display_name":"Tianming Liang","orcid":"https://orcid.org/0000-0003-0558-954X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianming Liang","raw_affiliation_strings":["School of Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0558-954X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011689248","display_name":"Linhui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhui Li","raw_affiliation_strings":["School of Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-7036-9238","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102336058","display_name":"Jian\u2013Fang Hu","orcid":"https://orcid.org/0009-0005-2678-5373"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian-Fang Hu","raw_affiliation_strings":["School of Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2678-5373","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776455","display_name":"Xiangyang Yu","orcid":"https://orcid.org/0000-0001-6673-3221"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Yu","raw_affiliation_strings":["Department of Physics, Sun Yat-Sen University, Guangzhou, China","Department of Physics, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Department of Physics, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050904","display_name":"Wei\u2010Shi Zheng","orcid":"https://orcid.org/0000-0001-8327-0003"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Shi Zheng","raw_affiliation_strings":["School of Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8327-0003","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034685928","display_name":"Jianhuang Lai","orcid":"https://orcid.org/0000-0003-3883-2024"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhuang Lai","raw_affiliation_strings":["School of Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3883-2024","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":3.0621,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90707593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"5077","last_page":"5091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9358999729156494,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9358999729156494,"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":0.8260239362716675},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6153619289398193},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5970167517662048},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.346238374710083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3243327736854553},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1566152572631836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260239362716675},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6153619289398193},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5970167517662048},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.346238374710083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3243327736854553},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1566152572631836},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3543031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3543031","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5099999904632568,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1951972270","display_name":null,"funder_award_id":"U22A2095","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5417755279","display_name":null,"funder_award_id":"6247072922","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7876353673","display_name":null,"funder_award_id":"62476296","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":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W2550936021","https://openalex.org/W2606982687","https://openalex.org/W2739879705","https://openalex.org/W2741903908","https://openalex.org/W2743289088","https://openalex.org/W2751525844","https://openalex.org/W2765716052","https://openalex.org/W2798592524","https://openalex.org/W2887783173","https://openalex.org/W2895243423","https://openalex.org/W2897857500","https://openalex.org/W2904452845","https://openalex.org/W2962910007","https://openalex.org/W2962949233","https://openalex.org/W2963140444","https://openalex.org/W2963781647","https://openalex.org/W2963890755","https://openalex.org/W2964220823","https://openalex.org/W2969897437","https://openalex.org/W2982358316","https://openalex.org/W2997344006","https://openalex.org/W2998166190","https://openalex.org/W3004127093","https://openalex.org/W3023993913","https://openalex.org/W3034203264","https://openalex.org/W3034368386","https://openalex.org/W3034730770","https://openalex.org/W3105232955","https://openalex.org/W3105966348","https://openalex.org/W3118473641","https://openalex.org/W3126459021","https://openalex.org/W3166608351","https://openalex.org/W3168640669","https://openalex.org/W3175961224","https://openalex.org/W3181758331","https://openalex.org/W3187433838","https://openalex.org/W3189738989","https://openalex.org/W3196930868","https://openalex.org/W3197457832","https://openalex.org/W3203174623","https://openalex.org/W3205691536","https://openalex.org/W3207409917","https://openalex.org/W4214653736","https://openalex.org/W4226426325","https://openalex.org/W4229449886","https://openalex.org/W4304092631","https://openalex.org/W4312246181","https://openalex.org/W4312273141","https://openalex.org/W4312527924","https://openalex.org/W4312954271","https://openalex.org/W4312974690","https://openalex.org/W4313057181","https://openalex.org/W4313071966","https://openalex.org/W4382457584","https://openalex.org/W4382458595","https://openalex.org/W4383112678","https://openalex.org/W4385245566","https://openalex.org/W4385572645","https://openalex.org/W4386065413","https://openalex.org/W4386075541","https://openalex.org/W4386075830","https://openalex.org/W4386076661","https://openalex.org/W4387546363","https://openalex.org/W4389988129","https://openalex.org/W4390872366"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Video":[0],"question":[1,233,274],"answering":[2],"(Video-QA)":[3],"has":[4],"emerged":[5],"as":[6,83],"a":[7,20,90],"core":[8],"task":[9],"in":[10,66,136,248,271,292],"the":[11,16,29,41,53,131,140,144,179,199,208,232,241,279,293],"vision-language":[12],"domain,":[13],"which":[14,156],"requires":[15],"models":[17],"to":[18,28,32,119,167,189,269],"understand":[19],"given":[21],"video":[22,80,243],"and":[23,46,114,206,237,240,299],"answer":[24],"textual":[25],"questions":[26],"related":[27],"video.":[30],"Compared":[31],"conventional":[33],"image-language":[34],"tasks,":[35],"Video-QA":[36,174],"is":[37,117,165,187],"designed":[38],"for":[39,139,212],"improving":[40],"models'":[42],"capacity":[43],"of":[44,79,133,182,198,229],"memorizing":[45],"integrating":[47],"multi-frame":[48,113],"temporal":[49,81,115,173,191,213,235,273,301],"cues":[50],"associated":[51,242],"with":[52,96,171],"questions.":[54],"While":[55],"significant":[56,246],"performance":[57,123,170],"improvements":[58,73],"have":[59],"recently":[60],"been":[61],"witnessed":[62],"on":[63,124,152,162,256],"public":[64],"benchmarks,":[65,155],"this":[67,86,100],"work,":[68],"we":[69,88,102,147,194,224,260],"rethink":[70],"whether":[71],"these":[72],"truly":[74],"stem":[75],"from":[76,217],"better":[77],"understanding":[78],"context":[82],"expected.":[84],"To":[85],"end,":[87],"accomplish":[89],"strong":[91],"single-frame":[92,134,145,219,280],"baseline":[93],"model":[94],"trained":[95],"knowledge":[97],"distillation.":[98],"With":[99],"model,":[101],"surprisingly":[103],"find":[104,225,261],"that":[105,196,262],"visiting":[106],"only":[107,183],"one":[108,163],"single":[109],"frame,":[110],"without":[111],"incorporating":[112],"information,":[116],"sufficient":[118],"achieve":[120,168],"state-of-the-art":[121],"(SOTA)":[122],"multiple":[125,153],"mainstream":[126],"benchmarks.":[127],"This":[128],"finding":[129],"reveals":[130],"prevalence":[132],"bias":[135,281,298],"current":[137],"benchmarks":[138,200,210],"first":[141],"time.":[142],"Around":[143],"bias,":[146],"conduct":[148],"an":[149],"in-depth":[150],"analysis":[151,255,287],"popular":[154],"demonstrate":[157],"that:":[158],"(i)":[159],"merely":[160],"relying":[161],"frame":[164],"able":[166,188],"comparable":[169],"SOTA":[172],"models;":[175],"(ii)":[176],"simply":[177],"ensembling":[178],"prediction":[180],"scores":[181],"3":[184],"separate":[185],"frames":[186],"surpass":[190],"SOTAs.":[192],"Furthermore,":[193],"observe":[195],"most":[197],"are":[201],"biased":[202],"towards":[203,295],"central":[204],"segments,":[205],"even":[207],"latest":[209],"tailored":[211],"reasoning":[214,258],"still":[215],"suffer":[216],"severe":[218],"bias.":[220],"In":[221],"case":[222],"study,":[223],"two":[226],"key":[227],"properties":[228],"low-bias":[230],"instances:":[231],"emphasizes":[234],"dependency":[236],"contextual":[238],"understanding,":[239],"content":[244],"presents":[245],"variability":[247],"scenes,":[249],"actions":[250],"or":[251],"interactions.":[252],"Through":[253],"further":[254],"compositional":[257],"datasets,":[259],"constructing":[263],"explicit":[264],"object/event":[265],"interactions":[266],"upon":[267],"videos":[268],"fill":[270],"well-designed":[272],"templates":[275],"can":[276],"effectively":[277],"reduce":[278],"during":[282],"annotation.":[283],"We":[284],"hope":[285],"our":[286],"helps":[288],"facilitate":[289],"future":[290],"efforts":[291],"field":[294],"mitigating":[296],"static":[297],"highlighting":[300],"reasoning.":[302]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}