{"id":"https://openalex.org/W4416251481","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228308","title":"Dual-level Concept-aware Network for Video Captioning with Augmented Semantics","display_name":"Dual-level Concept-aware Network for Video Captioning with Augmented Semantics","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251481","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228308"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228308","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":"conference-paper","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/A5059069914","display_name":"Siming Lu","orcid":"https://orcid.org/0000-0003-4041-1309"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijia Lu","raw_affiliation_strings":["Shanghai University,Schoool of Computer Engineering and Science,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Schoool of Computer Engineering and Science,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035821066","display_name":"Yinsai Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinsai Guo","raw_affiliation_strings":["Shanghai University,Schoool of Computer Engineering and Science,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Schoool of Computer Engineering and Science,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027933789","display_name":"Xue Chen","orcid":"https://orcid.org/0000-0001-5219-8176"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Chen","raw_affiliation_strings":["Shanghai University,Schoool of Computer Engineering and Science,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Schoool of Computer Engineering and Science,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100516312","display_name":"Liyan Ma","orcid":"https://orcid.org/0000-0001-8377-0163"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyan Ma","raw_affiliation_strings":["Shanghai University,Schoool of Computer Engineering and Science,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Schoool of Computer Engineering and Science,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9914000034332275,"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":0.9914000034332275,"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":0.00139999995008111,"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":0.0007999999797903001,"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":0.8720999956130981},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.772599995136261},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5001999735832214},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37529999017715454},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36390000581741333},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.34220001101493835}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8720999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8454999923706055},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.772599995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5616999864578247},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5001999735832214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4936000108718872},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228308","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1586939924","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2139501017","https://openalex.org/W2152984213","https://openalex.org/W2255466643","https://openalex.org/W2302086703","https://openalex.org/W2425121537","https://openalex.org/W2561529111","https://openalex.org/W2752191396","https://openalex.org/W2905145027","https://openalex.org/W2950579554","https://openalex.org/W2962934715","https://openalex.org/W2962990649","https://openalex.org/W2963552819","https://openalex.org/W2964065937","https://openalex.org/W2964241990","https://openalex.org/W2970641574","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3093309253","https://openalex.org/W3096609285","https://openalex.org/W3174295900","https://openalex.org/W3193767255","https://openalex.org/W3202799979","https://openalex.org/W3207042189","https://openalex.org/W3209229003","https://openalex.org/W3216659302","https://openalex.org/W3217340782","https://openalex.org/W4220790454","https://openalex.org/W4226109438","https://openalex.org/W4312340363","https://openalex.org/W4313131769","https://openalex.org/W4372266864","https://openalex.org/W4377235499","https://openalex.org/W4379516350","https://openalex.org/W4383682687","https://openalex.org/W4384161812","https://openalex.org/W4386057717","https://openalex.org/W4386122702","https://openalex.org/W4386234463","https://openalex.org/W4390075233","https://openalex.org/W4401413733","https://openalex.org/W4403439692"],"related_works":[],"abstract_inverted_index":{"Video":[0],"captioning":[1],"aims":[2],"to":[3,23,96,113,124,176,192],"generate":[4,193],"natural":[5],"language":[6],"descriptions":[7],"of":[8,36,49,80],"events":[9],"in":[10,58,99,163],"a":[11,67],"video.":[12],"While":[13,116],"several":[14],"methods":[15],"have":[16],"made":[17],"efforts":[18],"by":[19,103,131],"utilizing":[20],"detection":[21],"modules":[22,154],"obtain":[24],"principal":[25],"concepts":[26,98,175],"like":[27],"objects":[28],"and":[29,44,136,170,185,196],"then":[30],"capitalize":[31],"on":[32,183],"their":[33],"semantics.":[34,179],"Most":[35],"them":[37,138],"lack":[38],"prior":[39,110],"semantic":[40,53,106,141,166],"information":[41,107,167],"about":[42,168],"scenes":[43,101,169],"ignore":[45],"the":[46,89,117,140],"structural":[47],"semantics":[48,83],"concept":[50,126,171],"combinations,":[51],"causing":[52],"deviation":[54],"when":[55,173],"generating":[56],"captions":[57],"different":[59],"scenes.":[60],"To":[61],"address":[62],"these":[63],"problems,":[64],"we":[65],"propose":[66],"method":[68,189],"called":[69],"Dual-level":[70],"Concept-aware":[71],"Network":[72],"(DCN)":[73],"for":[74],"video":[75,114],"captioning,":[76],"which":[77],"is":[78,94,122,190],"capable":[79],"mining":[81],"comprehensive":[82],"via":[84],"two":[85],"concept-aware":[86,153],"modules.":[87],"Specifically,":[88],"Concept":[90,118],"Detection":[91],"Module":[92,120],"(CDM)":[93],"designed":[95],"detect":[97],"diverse":[100],"precisely":[102],"exploiting":[104],"scene":[105],"from":[108,149],"external":[109],"knowledge":[111],"according":[112],"content.":[115],"Alignment":[119],"(CAM)":[121],"constructed":[123],"represent":[125],"combinations":[127,172],"at":[128],"multiple":[129],"granularities":[130],"fusing":[132],"visual":[133],"features":[134],"hierarchically":[135],"mapping":[137],"into":[139],"space.":[142],"With":[143],"pseudo":[144],"concept-related":[145],"supervision":[146],"signals":[147],"extracted":[148],"ground-truth":[150],"texts,":[151],"both":[152],"get":[155],"fully":[156],"optimized":[157],"explicitly.":[158],"Hence":[159],"they":[160],"do":[161],"well":[162],"obtaining":[164],"useful":[165],"identifying":[174],"augment":[177],"caption":[178],"Given":[180],"competitive":[181],"results":[182],"MSVD":[184],"MSR-VTT":[186],"datasets,":[187],"our":[188],"demonstrated":[191],"more":[194],"accurate":[195],"plausible":[197],"captions.":[198]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-14T00:00:00"}