{"id":"https://openalex.org/W4293518823","doi":"https://doi.org/10.1109/icme52920.2022.9859690","title":"Semantic-Driven Saliency-Context Separation for Video Captioning","display_name":"Semantic-Driven Saliency-Context Separation for Video Captioning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518823","doi":"https://doi.org/10.1109/icme52920.2022.9859690"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859690","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Semantic-Driven_Saliency-Context_Separation_for_Video_Captioning/21132253","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065760141","display_name":"Heming Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heming Jing","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860531","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-6648-953X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626035","display_name":"Rui-Wei Zhao","orcid":"https://orcid.org/0000-0002-8498-5761"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui-Wei Zhao","raw_affiliation_strings":["Fudan University,Academy for Engineering and Technology","Academy for Engineering and Technology, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering and Technology","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375722","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0001-7561-0143"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["School of Information Management and Engineering, Shanghai Key Laboratory of Financial Information Technology, Shanghai University of Finance and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Management and Engineering, Shanghai Key Laboratory of Financial Information Technology, Shanghai University of Finance and Economics","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019288783","display_name":"Xuequan Lu","orcid":"https://orcid.org/0000-0003-0959-408X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuequan Lu","raw_affiliation_strings":["School of Information Technology, Deakin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008929449","display_name":"Shang Gao","orcid":"https://orcid.org/0000-0002-2947-7780"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shang Gao","raw_affiliation_strings":["School of Information Technology, Deakin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"06"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9991000294685364,"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":0.9385948181152344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8679908514022827},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7102220058441162},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6317482590675354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5314380526542664},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5220213532447815},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5052528977394104},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4793001711368561},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.44296732544898987},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43645691871643066},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4315486252307892},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1824120581150055}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9385948181152344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8679908514022827},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7102220058441162},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6317482590675354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314380526542664},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5220213532447815},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5052528977394104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4793001711368561},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.44296732544898987},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43645691871643066},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4315486252307892},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1824120581150055},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icme52920.2022.9859690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859690","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30176286","is_oa":false,"landing_page_url":"http://doi.org/10.1109/icme52920.2022.9859690","pdf_url":null,"source":{"id":"https://openalex.org/S4306402457","display_name":"Deakin Research Online (Deakin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:figshare.com:article/21132253","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Semantic-Driven_Saliency-Context_Separation_for_Video_Captioning/21132253","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/21132253","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Semantic-Driven_Saliency-Context_Separation_for_Video_Captioning/21132253","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2547875792","https://openalex.org/W2962990649","https://openalex.org/W2963524571","https://openalex.org/W2964199361","https://openalex.org/W2964241990","https://openalex.org/W2964350391","https://openalex.org/W2981411942","https://openalex.org/W2984862483","https://openalex.org/W3003478339","https://openalex.org/W3034221024","https://openalex.org/W3035404043","https://openalex.org/W3039060838","https://openalex.org/W3045491988","https://openalex.org/W3165961049","https://openalex.org/W3176425931","https://openalex.org/W4214692497","https://openalex.org/W6684090549","https://openalex.org/W6729448088","https://openalex.org/W6754546032","https://openalex.org/W6766991472","https://openalex.org/W6780578196","https://openalex.org/W6789747622","https://openalex.org/W6795360041"],"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":[1,39,82],"aims":[2],"at":[3],"generating":[4],"a":[5,10,29,65,79],"natural":[6],"language":[7],"de-scription":[8],"for":[9],"given":[11],"video":[12,30,81],"clip":[13],"including":[14],"not":[15,45],"only":[16],"salient":[17],"sce-narios":[18],"but":[19],"also":[20],"contextual":[21],"scenarios.":[22],"The":[23,41],"former":[24],"reveal":[25],"the":[26,34,69,74,105,118,139,145],"highlight":[27],"of":[28,36,68,141],"and":[31,48,58,94,111,120,126,136],"are":[32,44],"usually":[33],"focus":[35],"most":[37],"existing":[38],"methods.":[40,149],"latter,":[42],"however,":[43],"well":[46],"ex-plored":[47],"even":[49],"ignored":[50],"easily,":[51],"though":[52],"they":[53],"may":[54],"provide":[55],"cer-tain":[56],"detailed":[57,125],"latent":[59],"information":[60,107],"that":[61],"can":[62],"help":[63],"with":[64,147],"better":[66],"understanding":[67],"video.":[70],"To":[71],"effectively":[72],"exploit":[73],"infor-mation":[75],"contained":[76],"in":[77],"both,":[78],"novel":[80],"network":[83],"is":[84],"proposed.":[85],"It":[86],"has":[87],"two":[88,131],"key":[89],"modules:":[90],"Cross-Modality":[91],"Selection":[92],"(CMS)":[93],"Saliency-Context":[95],"Adaptive":[96],"Decoder":[97],"(SCAD).":[98],"Specifically,":[99],"CMS":[100],"mainly":[101],"focuses":[102],"on":[103,130],"utilizing":[104],"semantic":[106],"to":[108,122],"distinguish":[109],"saliency":[110,119],"context.":[112],"Meanwhile,":[113],"SCAD":[114],"adaptively":[115],"identifies":[116],"both":[117],"context":[121],"generate":[123],"more":[124],"precise":[127],"captions.":[128],"Experiments":[129],"benchmark":[132],"datasets,":[133],"i.e.,":[134],"MSVD":[135],"MSR-VTT,":[137],"demon-strate":[138],"effectiveness":[140],"our":[142],"model":[143],"through":[144],"comparison":[146],"state-of-the-art":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}