{"id":"https://openalex.org/W7131815793","doi":"https://doi.org/10.1109/tmm.2026.3668493","title":"SCL: Semantic Coherence Learning for Video Question Answering","display_name":"SCL: Semantic Coherence Learning for Video Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131815793","doi":"https://doi.org/10.1109/tmm.2026.3668493"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2026.3668493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668493","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/A5075764771","display_name":"Xize Wu","orcid":"https://orcid.org/0000-0001-6122-273X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xize Wu","raw_affiliation_strings":["LIST, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6122-273X","affiliations":[{"raw_affiliation_string":"LIST, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401173","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0003-4873-505X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9318-0084","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060062341","display_name":"Jiasong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiasong Wu","raw_affiliation_strings":["LIST, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7171-1318","affiliations":[{"raw_affiliation_string":"LIST, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127169291","display_name":"Lei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2993-7142","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127362638","display_name":"Heng Tao Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24427254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5821","last_page":"5834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9769999980926514,"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":0.9769999980926514,"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":0.006099999882280827,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002400000113993883,"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/semantics","display_name":"Semantics (computer science)","score":0.7042999863624573},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6942999958992004},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6499999761581421},{"id":"https://openalex.org/keywords/interrogative","display_name":"Interrogative","score":0.6208999752998352},{"id":"https://openalex.org/keywords/interrogative-word","display_name":"Interrogative word","score":0.34700000286102295},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.30090001225471497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8636000156402588},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7042999863624573},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6942999958992004},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6499999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6331999897956848},{"id":"https://openalex.org/C57098296","wikidata":"https://www.wikidata.org/wiki/Q12021746","display_name":"Interrogative","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6003999710083008},{"id":"https://openalex.org/C59650362","wikidata":"https://www.wikidata.org/wiki/Q2304610","display_name":"Interrogative word","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2026.3668493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668493","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"},{"id":"pmh:oai:HAL:hal-05682134v1","is_oa":false,"landing_page_url":"https://univ-rennes.hal.science/hal-05682134","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Multimedia, 2026, 14 (8), &#x27E8;10.1109/TMM.2026.3668493&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5015722513198853,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3171123205","display_name":null,"funder_award_id":"2023A1515140104","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G4047099904","display_name":null,"funder_award_id":"62306065","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5407837808","display_name":null,"funder_award_id":"62476055","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8445935974","display_name":null,"funder_award_id":"62171125","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/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"requires":[4],"clarifying":[5],"the":[6,17,24,35,67,83,97,157],"true":[7],"question":[8,39,143],"intent":[9],"and":[10,33,75,145,167,182],"understanding":[11],"dynamic":[12],"video":[13,46,154],"content":[14],"to":[15,42,94,123],"predict":[16],"answer.":[18],"However,":[19],"most":[20],"existing":[21],"methods":[22],"overlook":[23],"temporal":[25,106],"semantic":[26,79],"exploration":[27],"of":[28,38,45,71,102],"fine-grained":[29,68,98],"clues":[30,80],"across":[31,105],"frames,":[32],"neglect":[34],"interrogative":[36],"properties":[37],"text,":[40],"leading":[41],"suboptimal":[43],"grounding":[44],"frames.":[47,114],"To":[48],"address":[49],"these":[50],"limitations,":[51],"in":[52,138,149],"this":[53],"paper,":[54],"we":[55,87,116],"propose":[56,117],"a":[57,89,118],"novel":[58],"Semantic":[59],"Coherence":[60],"Learning":[61],"(SCL)":[62],"framework,":[63],"which":[64,133],"explicitly":[65],"models":[66],"spatio-temporal":[69,90],"coherence":[70],"critical":[72,103,136,147],"visual":[73],"regions":[74,104,112],"progressively":[76,124],"mines":[77,146],"multi-modal":[78,119,126],"aligned":[81],"with":[82,130,165],"reasoning":[84,92,121,131],"intent.":[85],"Specifically,":[86],"design":[88],"clue":[91,120],"module":[93,122],"adaptively":[95],"model":[96],"coherent":[99,127],"transition":[100],"semantics":[101,128,144],"frames":[107,137],"while":[108],"suppressing":[109],"irrelevant":[110],"noisy":[111],"within":[113],"Additionally,":[115],"mine":[125],"associated":[129],"intent,":[132],"iteratively":[134],"grounds":[135],"videos":[139],"based":[140,151],"on":[141,152,174],"refined":[142,153],"phrases":[148],"questions":[150],"semantics.":[155],"Finally,":[156],"answer":[158,163],"is":[159],"derived":[160],"through":[161],"an":[162],"decoder":[164],"intra":[166],"inter-sample":[168],"contrastive":[169],"strategies.":[170],"Extensive":[171],"experimental":[172,185],"results":[173],"six":[175],"widely":[176],"used":[177],"benchmarks":[178],"verify":[179],"our":[180],"effectiveness":[181],"superiority.":[183],"The":[184],"source":[186],"codes":[187],"are":[188],"available":[189],"at":[190],"https://github.com/XizeWu/SCL.":[191]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-02-28T00:00:00"}
