{"id":"https://openalex.org/W4404562753","doi":"https://doi.org/10.1109/tcsvt.2024.3502736","title":"Action-Driven Semantic Representation and Aggregation for Video Captioning","display_name":"Action-Driven Semantic Representation and Aggregation for Video Captioning","publication_year":2024,"publication_date":"2024-11-20","ids":{"openalex":"https://openalex.org/W4404562753","doi":"https://doi.org/10.1109/tcsvt.2024.3502736"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3502736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3502736","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":"https://openalex.org/A5025707429","display_name":"Tingting Han","orcid":"https://orcid.org/0000-0002-2131-9200"},"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":true,"raw_author_name":"Tingting Han","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, Hangzhou, China","Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006218098","display_name":"Yaochen Xu","orcid":"https://orcid.org/0000-0002-5039-2781"},"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":"Yaochen Xu","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, Hangzhou, China","Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"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":"Jun Yu","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, Hangzhou, China","Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100581509","display_name":"Zhou Yu","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":"Zhou Yu","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, Hangzhou, China","Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051149140","display_name":"Sicheng Zhao","orcid":"https://orcid.org/0000-0001-5843-6411"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Zhao","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025707429"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":1.9599,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87982078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"4","first_page":"3383","last_page":"3395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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":0.9988999962806702,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9898999929428101,"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":0.9829000234603882,"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/closed-captioning","display_name":"Closed captioning","score":0.8750953674316406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.786536693572998},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5694893598556519},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5310870409011841},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47007256746292114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.462284117937088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44720354676246643},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38407596945762634},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32507243752479553},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23711761832237244},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11549010872840881}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8750953674316406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786536693572998},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5694893598556519},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5310870409011841},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47007256746292114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.462284117937088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44720354676246643},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38407596945762634},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32507243752479553},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23711761832237244},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11549010872840881},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3502736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3502736","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":[{"score":0.4699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1587013957","display_name":null,"funder_award_id":"LZ23F020007","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1690291968","display_name":null,"funder_award_id":"62422204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3034814294","display_name":null,"funder_award_id":"LDT23F02025F02","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3292571589","display_name":null,"funder_award_id":"62002091","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3410702520","display_name":null,"funder_award_id":"LZ23F020007","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G367674872","display_name":null,"funder_award_id":"LQ21F020014","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4033949287","display_name":null,"funder_award_id":"LDT23F02025F02","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G6290763762","display_name":null,"funder_award_id":"LR22F020001","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G6717691258","display_name":null,"funder_award_id":"LQ21F020014","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G7213623443","display_name":null,"funder_award_id":"LR22F020001","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7336325476","display_name":null,"funder_award_id":"62072147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2139501017","https://openalex.org/W2222512263","https://openalex.org/W2425121537","https://openalex.org/W2554906389","https://openalex.org/W2606982687","https://openalex.org/W2607119937","https://openalex.org/W2948358897","https://openalex.org/W2962681491","https://openalex.org/W2962934715","https://openalex.org/W2962990649","https://openalex.org/W2963454061","https://openalex.org/W2970641574","https://openalex.org/W2984862483","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3205021045","https://openalex.org/W3216659302","https://openalex.org/W3217340782","https://openalex.org/W4205510032","https://openalex.org/W4214692497","https://openalex.org/W4285118488","https://openalex.org/W4382464395","https://openalex.org/W4382469109","https://openalex.org/W4384161812","https://openalex.org/W4385245566","https://openalex.org/W4385805123","https://openalex.org/W4386057717","https://openalex.org/W4386122702","https://openalex.org/W4386453740","https://openalex.org/W4386902900","https://openalex.org/W4387247768","https://openalex.org/W4387969760","https://openalex.org/W4388189274","https://openalex.org/W6620707391","https://openalex.org/W6629393784","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6713349023","https://openalex.org/W6738967722","https://openalex.org/W6749210505","https://openalex.org/W6778485988","https://openalex.org/W6789747622","https://openalex.org/W6791353385","https://openalex.org/W6840578678","https://openalex.org/W6860172067"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Video":[0],"captioning,":[1],"a":[2,33,60,70,104,109,114],"challenging":[3],"task":[4],"that":[5,163],"entails":[6],"generating":[7],"natural":[8],"language":[9],"descriptions":[10],"of":[11,21,28,36,108,123],"visual":[12,67],"content,":[13,39],"often":[14],"fails":[15],"to":[16,31,134],"effectively":[17],"grasp":[18],"the":[19,26,37,86,121,141,159],"essence":[20],"action":[22,29,57,77,83],"semantics.":[23],"To":[24,95],"harness":[25],"power":[27],"detection":[30],"facilitate":[32],"deeper":[34],"understanding":[35],"video":[38,142],"we":[40,102],"propose":[41],"an":[42],"action-driven":[43],"method,":[44],"named":[45],"Hierarchical":[46],"Semantic":[47],"Representation":[48],"and":[49,92,100,113,128,143,156,158],"Aggregation":[50],"(HSRA)":[51],"network.":[52],"This":[53,118],"method":[54],"explicitly":[55],"exploits":[56],"clues":[58],"with":[59],"hierarchical":[61],"semantic":[62,98,105,110,115,138],"representation":[63],"module,":[64],"which":[65],"models":[66],"semantics":[68,84,124],"in":[69,137],"three-level":[71],"structure:":[72],"\u201cobject-action-event\u201d.":[73],"By":[74],"employing":[75],"learnable":[76],"queries,":[78],"our":[79,164],"approach":[80],"injects":[81],"extensive":[82,148],"into":[85],"model,":[87],"thereby":[88],"enabling":[89],"more":[90],"accurate":[91],"context-rich":[93],"captions.":[94,145],"further":[96],"enhance":[97],"alignment":[99,122],"understanding,":[101],"introduce":[103],"aggregation":[106],"composed":[107],"interaction":[111],"module":[112],"refinement":[116],"module.":[117],"component":[119],"facilitates":[120],"across":[125],"different":[126],"levels":[127],"emphasizes":[129],"key":[130],"information,":[131],"ultimately":[132],"leading":[133],"significant":[135],"improvements":[136],"consistency":[139],"between":[140],"generated":[144],"We":[146],"performed":[147],"evaluations":[149],"on":[150],"two":[151],"well-established":[152],"public":[153],"datasets,":[154],"MSVD":[155],"MSR-VTT,":[157],"findings":[160],"consistently":[161],"demonstrate":[162],"proposed":[165],"HSRA":[166],"network":[167],"outperforms":[168],"contemporary":[169],"state-of-the-art":[170],"methods.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
