{"id":"https://openalex.org/W7081919759","doi":"https://doi.org/10.1109/tcsvt.2025.3609441","title":"Spatial\u2013Temporal Clue Reasoning Chain for Long Video Question Answering","display_name":"Spatial\u2013Temporal Clue Reasoning Chain for Long Video Question Answering","publication_year":2025,"publication_date":"2025-09-12","ids":{"openalex":"https://openalex.org/W7081919759","doi":"https://doi.org/10.1109/tcsvt.2025.3609441"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3609441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3609441","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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":null,"display_name":"Haibo Gong","orcid":"https://orcid.org/0009-0009-0830-765X"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Gong","raw_affiliation_strings":["School of Automation, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-0830-765X","affiliations":[{"raw_affiliation_string":"School of Automation, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenggang Yan","orcid":"https://orcid.org/0000-0003-1204-0512"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":["School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1204-0512","affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiehua Zhang","orcid":"https://orcid.org/0000-0003-0790-9279"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiehua Zhang","raw_affiliation_strings":["School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0003-0790-9279","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yaoqi Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoqi Sun","raw_affiliation_strings":["School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhan Gao","orcid":"https://orcid.org/0000-0002-7777-3613"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Gao","raw_affiliation_strings":["School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7777-3613","affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":null,"display_name":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8437-4824","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2699,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87484582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"3","first_page":"2757","last_page":"2770"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6599000096321106,"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"}},"topics":[{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6599000096321106,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.026000000536441803,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.019200000911951065,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7856000065803528},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7217000126838684},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5486999750137329},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.49399998784065247},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.39169999957084656},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3546999990940094},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3407000005245209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220000267028809},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7856000065803528},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7217000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914999842643738},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3255000114440918},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3609441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3609441","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4536128632","display_name":null,"funder_award_id":"62322211","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2337252826","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2954199749","https://openalex.org/W2964220823","https://openalex.org/W2998166190","https://openalex.org/W3006871679","https://openalex.org/W3107580728","https://openalex.org/W3111278072","https://openalex.org/W3136792391","https://openalex.org/W3167092180","https://openalex.org/W3168640669","https://openalex.org/W3175961224","https://openalex.org/W3189890868","https://openalex.org/W3196930868","https://openalex.org/W3203711169","https://openalex.org/W3205572000","https://openalex.org/W4200631219","https://openalex.org/W4206982465","https://openalex.org/W4292692470","https://openalex.org/W4312246181","https://openalex.org/W4313071966","https://openalex.org/W4377235294","https://openalex.org/W4383112678","https://openalex.org/W4385681696","https://openalex.org/W4386071468","https://openalex.org/W4386076661","https://openalex.org/W4386902900","https://openalex.org/W4390872862","https://openalex.org/W4402667906","https://openalex.org/W4402703123","https://openalex.org/W4402727520","https://openalex.org/W4402727798","https://openalex.org/W4402753952","https://openalex.org/W4403182266","https://openalex.org/W4404035255","https://openalex.org/W4404469286","https://openalex.org/W4404782980","https://openalex.org/W4405232240","https://openalex.org/W7133189103"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"Video":[1],"Question":[2],"Answering":[3],"(VideoQA)":[4],"methods":[5],"face":[6],"tremendous":[7],"challenges":[8],"when":[9],"dealing":[10],"with":[11,113],"longer":[12],"videos.":[13],"On":[14,43],"the":[15,30,40,44,47,53,66,85,124,133,143,147,154,160,169],"one":[16],"hand,":[17,46],"long":[18],"videos":[19],"contain":[20],"rich":[21],"and":[22,83,100,130,146,157],"diverse":[23],"information":[24],"at":[25],"different":[26],"spatial-temporal":[27,54,73],"scales,":[28],"requiring":[29],"VideoQA":[31,166],"model":[32,48],"to":[33,50,77,116,152],"mine":[34],"multi-granularity":[35,80,149],"visual":[36,81,94,128,150],"clues":[37,82,95,129,151],"conditioned":[38],"on":[39,164],"specific":[41],"question.":[42],"other":[45],"needs":[49],"effectively":[51,78],"reason":[52,79],"relationships":[55],"of":[56,126,135,171],"complex":[57,88],"events":[58],"that":[59],"span":[60],"large":[61],"temporal":[62],"intervals.":[63],"To":[64],"address":[65],"above":[67],"challenges,":[68],"we":[69,91,107,138],"propose":[70,108],"a":[71,103],"novel":[72],"clue":[74,111],"reasoning":[75],"chain":[76],"predict":[84,159],"answer":[86],"in":[87,102],"events.":[89],"Specifically,":[90],"extracts":[92],"question-related":[93,127],"from":[96],"video":[97],"clips,":[98],"frames":[99],"regions":[101],"\u201cstep-by-step\"":[104],"manner.":[105],"Further,":[106],"an":[109],"asynchronous":[110],"selector":[112],"self-excitation":[114],"loss":[115],"perform":[117],"more":[118],"effective":[119],"selections":[120],"by":[121],"(1)":[122],"facilitating":[123],"identification":[125],"(2)":[131],"enhancing":[132],"diversity":[134],"selections.":[136],"Next,":[137],"introduce":[139],"cross-modal":[140],"fusion":[141],"between":[142],"question":[144],"semantics":[145],"selected":[148],"learn":[153],"detailed":[155],"interactions":[156],"then":[158],"answer.":[161],"Extensive":[162],"experiments":[163],"multiple":[165],"datasets":[167],"demonstrate":[168],"effectiveness":[170],"our":[172],"method.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
