{"id":"https://openalex.org/W7163019282","doi":"https://doi.org/10.1109/access.2026.3698553","title":"Task-Driven Dual-Path Keyframe Selection: Enhancing Multimodal Video Understanding","display_name":"Task-Driven Dual-Path Keyframe Selection: Enhancing Multimodal Video Understanding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7163019282","doi":"https://doi.org/10.1109/access.2026.3698553"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3698553","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3698553","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3698553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yurong Wang","raw_affiliation_strings":["School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China"],"raw_orcid":"https://orcid.org/0009-0004-7131-6173","affiliations":[{"raw_affiliation_string":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137553253","display_name":"Chengwei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwei Yang","raw_affiliation_strings":["School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137535983","display_name":"Tianhao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]},{"id":"https://openalex.org/I4210112270","display_name":"Qingdao Academy of Intelligent Industries","ror":"https://ror.org/02a0rnh86","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112270"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Wu","raw_affiliation_strings":["School of Intelligent Electrical Engineering and New Energy, Qingdao Hengxing University of Science and Technology, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Electrical Engineering and New Energy, Qingdao Hengxing University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I143413998","https://openalex.org/I4210112270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035652160","display_name":"\u82cf\u5fb7\u4ea8","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123920","display_name":"Silla University","ror":"https://ror.org/02w3gk008","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210123920"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Deheng Su","raw_affiliation_strings":["School of Mechanical Engineering, Silla University, Sasang-gu, Busan, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Silla University, Sasang-gu, Busan, Republic of Korea","institution_ids":["https://openalex.org/I4210123920"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137519149","display_name":"Fengjun Zhang","orcid":"https://orcid.org/0000-0001-5850-1922"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengjun Zhang","raw_affiliation_strings":["School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China"],"raw_orcid":"https://orcid.org/0000-0001-5850-1922","affiliations":[{"raw_affiliation_string":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China","institution_ids":["https://openalex.org/I4210096899"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68392232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"83838","last_page":"83851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.7261999845504761,"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/T11439","display_name":"Video Analysis and Summarization","score":0.7261999845504761,"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":0.040800001472234726,"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":0.037700001150369644,"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/visualization","display_name":"Visualization","score":0.36230000853538513},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.32899999618530273},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.25769999623298645},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.22779999673366547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828999757766724},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38510000705718994},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3531000018119812},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.22779999673366547}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3698553","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3698553","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:20deb0b4297c49228ad030b51137374c","is_oa":true,"landing_page_url":"https://doaj.org/article/20deb0b4297c49228ad030b51137374c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 83838-83851 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3698553","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3698553","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3595648496","display_name":null,"funder_award_id":"62404085","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"require":[5],"highly":[6],"representative":[7,74],"visual":[8],"inputs":[9],"for":[10],"efficient":[11],"video":[12],"understanding.":[13],"However,":[14],"existing":[15],"keyframe":[16,144],"selection":[17,145],"methods":[18],"often":[19],"struggle":[20],"to":[21,111],"simultaneously":[22],"capture":[23],"dynamic":[24,86],"actions,":[25],"ensure":[26],"comprehensive":[27],"semantic":[28,119,147],"coverage,":[29],"and":[30,99,124,152,167],"align":[31],"seamlessly":[32],"with":[33],"downstream":[34,149],"tasks.":[35],"To":[36,81],"overcome":[37],"these":[38,83],"limitations,":[39],"we":[40],"propose":[41],"the":[42,95,117,125,159,162],"Task-Adaptive":[43],"Keyframe":[44],"Selection":[45],"Framework":[46],"(TAKSF).":[47],"TAKSF":[48,138],"employs":[49],"a":[50,54,68,85,103],"decoupled":[51],"dual-path":[52,164],"architecture:":[53],"Visual":[55],"Saliency":[56],"Branch":[57,71],"(VSB)":[58],"isolates":[59],"critical":[60],"action":[61],"frames":[62,76],"by":[63,115],"analyzing":[64],"inter-frame":[65],"dynamics,":[66],"while":[67],"Semantic":[69,105],"Clustering":[70],"(SCB)":[72],"extracts":[73],"scene":[75],"via":[77],"deep":[78],"feature":[79],"clustering.":[80],"synergize":[82],"paths,":[84],"fusion":[87],"mechanism":[88,166],"adaptively":[89],"integrates":[90],"their":[91],"outputs":[92],"based":[93],"on":[94,132],"video's":[96],"motion":[97],"intensity":[98],"content":[100],"complexity.":[101],"Furthermore,":[102],"Task-driven":[104],"Matching":[106],"(TSM)":[107],"module":[108],"is":[109],"introduced":[110],"optimize":[112],"task":[113,127,150],"relevance":[114],"computing":[116],"cross-modal":[118],"similarity":[120],"between":[121],"candidate":[122],"keyframes":[123],"specific":[126],"text.":[128],"Extensive":[129],"experiments":[130],"conducted":[131],"six":[133],"public":[134],"benchmarks":[135],"demonstrate":[136],"that":[137],"significantly":[139],"outperforms":[140],"state-of-the-art":[141],"approaches":[142],"in":[143],"quality,":[146],"fidelity,":[148],"adaptability,":[151],"computational":[153],"efficiency.":[154],"These":[155],"results":[156],"strongly":[157],"validate":[158],"efficacy":[160],"of":[161],"proposed":[163],"collaborative":[165],"task-driven":[168],"alignment":[169],"strategy.":[170]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-06-02T00:00:00"}