{"id":"https://openalex.org/W4416251491","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228107","title":"Dual-Strategy Knowledge-Semantics Guided Network for Video Captioning","display_name":"Dual-Strategy Knowledge-Semantics Guided Network for Video Captioning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251491","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228107"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5101659494","display_name":"Yi Qian","orcid":"https://orcid.org/0000-0001-8696-4924"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingtian Qian","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047648083","display_name":"Bin Fang","orcid":"https://orcid.org/0000-0002-9788-4388"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Fang","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101659494"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34501986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9865000247955322,"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":0.9865000247955322,"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":0.0024999999441206455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0017999999690800905,"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":0.694599986076355},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6486999988555908},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6118000149726868},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.550599992275238},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5325000286102295},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4747999906539917},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4307999908924103},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41839998960494995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8697999715805054},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.694599986076355},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6486999988555908},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365999937057495},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4307999908924103},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2139501017","https://openalex.org/W2220981600","https://openalex.org/W2425121537","https://openalex.org/W2556388456","https://openalex.org/W2948358897","https://openalex.org/W2962990649","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W3019301826","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3176425931","https://openalex.org/W3176689360","https://openalex.org/W3205021045","https://openalex.org/W3216659302","https://openalex.org/W4220790454","https://openalex.org/W4312535570","https://openalex.org/W4312610896","https://openalex.org/W4382464395","https://openalex.org/W4385245566","https://openalex.org/W4385484578","https://openalex.org/W4385484816","https://openalex.org/W4385805123","https://openalex.org/W4386057717","https://openalex.org/W4386122702","https://openalex.org/W4386234463","https://openalex.org/W4387934928"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,37,58,79],"propose":[4],"a":[5,39,60,81],"dual-strategy":[6],"knowledge-semantics":[7],"guided":[8],"network":[9,66,85],"(DS-KSGN)":[10],"for":[11],"video":[12,105],"captioning,":[13],"which":[14],"leverages":[15],"two":[16],"parallel":[17,42],"decoders":[18,43],"to":[19,31,72,86],"process":[20],"multimodal":[21,70,91,99],"features":[22],"and":[23,50,97],"fully":[24],"exploit":[25],"knowledge":[26],"information":[27],"at":[28],"different":[29],"levels":[30],"generate":[32],"more":[33],"accurate":[34],"captions.":[35],"Firstly,":[36],"design":[38],"set":[40],"of":[41,90,117],"that":[44,67],"balance":[45],"the":[46,54,69,88,115,118],"contributions":[47],"from":[48],"knowledge-rich":[49],"semantics-rich":[51],"streams":[52],"in":[53,104],"generation":[55],"task.":[56],"Secondly,":[57],"develop":[59],"simple":[61],"yet":[62],"effective":[63],"semantic":[64,76],"extraction":[65],"guides":[68],"stream":[71],"focus":[73],"on":[74,110],"critical":[75],"information.":[77],"Finally,":[78],"construct":[80],"multi-scale":[82],"deep":[83],"fusion":[84],"enhance":[87],"representation":[89],"features.":[92],"This":[93],"method":[94],"effectively":[95],"integrates":[96],"refines":[98],"features,":[100],"demonstrating":[101],"its":[102],"potential":[103],"captioning.":[106],"Extensive":[107],"experiments":[108],"conducted":[109],"several":[111],"widely-used":[112],"datasets":[113],"validate":[114],"effectiveness":[116],"proposed":[119],"method.":[120]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}