{"id":"https://openalex.org/W3192261211","doi":"https://doi.org/10.1145/3474085.3475519","title":"Discriminative Latent Semantic Graph for Video Captioning","display_name":"Discriminative Latent Semantic Graph for Video Captioning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3192261211","doi":"https://doi.org/10.1145/3474085.3475519","mag":"3192261211"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475519","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.03662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Bai","raw_affiliation_strings":["Newcastle University, Newcastle upon Tyne, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University, Newcastle upon Tyne, United Kingdom","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junyan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junyan Wang","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Long","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Long","raw_affiliation_strings":["Durham University, Durham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University, Durham, United Kingdom","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bingzhang Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingzhang Hu","raw_affiliation_strings":["Hefei CAS Dihuge Automation Co., LTD, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei CAS Dihuge Automation Co., LTD, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Song","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Maurice Pagnucco","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Maurice Pagnucco","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yu Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Guan","raw_affiliation_strings":["Newcastle University, Newcastle upon Tyne, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University, Newcastle upon Tyne, United Kingdom","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1006,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9193229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3556","last_page":"3564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9980000257492065,"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":0.9937000274658203,"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":0.7258999943733215},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7226999998092651},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.59170001745224},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5109999775886536},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4693000018596649},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4645000100135803},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3691999912261963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381999731063843},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7258999943733215},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7226999998092651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6571000218391418},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5996000170707703},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.34769999980926514},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30979999899864197},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475519","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.03662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.03662","pdf_url":"https://arxiv.org/pdf/2108.03662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.03662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.03662","pdf_url":"https://arxiv.org/pdf/2108.03662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3000430873","display_name":null,"funder_award_id":"MR/S003916/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G3688699135","display_name":null,"funder_award_id":"EP/M020576/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7197601580","display_name":null,"funder_award_id":"MR/S003916/2","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1596841185","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2745461083","https://openalex.org/W2887712318","https://openalex.org/W2948358897","https://openalex.org/W2962681491","https://openalex.org/W2962914678","https://openalex.org/W2962968835","https://openalex.org/W2963524571","https://openalex.org/W2963811641","https://openalex.org/W2963971014","https://openalex.org/W2981750519","https://openalex.org/W2996984511","https://openalex.org/W3035303837","https://openalex.org/W3035365026","https://openalex.org/W3069154721","https://openalex.org/W3095422700"],"related_works":[],"abstract_inverted_index":{"Video":[0],"captioning":[1],"aims":[2],"to":[3,38,46,87,106],"automatically":[4],"generate":[5,39],"natural":[6],"language":[7],"sentences":[8],"that":[9,70,111],"can":[10,71,115],"describe":[11],"the":[12,28],"visual":[13,90],"contents":[14],"of":[15],"a":[16,52,66],"given":[17],"video.":[18],"Existing":[19],"generative":[20],"models":[21],"like":[22],"encoder-decoder":[23],"frameworks":[24],"cannot":[25],"explicitly":[26],"explore":[27],"object-level":[29],"interactions":[30],"and":[31,126,140],"frame-level":[32],"information":[33,74],"from":[34],"complex":[35],"spatio-temporal":[36,73],"data":[37],"semantic-rich":[40],"captions.":[41],"Our":[42,119,142],"main":[43],"contribution":[44],"is":[45,85,104,144],"identify":[47],"three":[48],"key":[49,112],"problems":[50],"in":[51],"joint":[53],"framework":[54],"for":[55,138],"future":[56],"video":[57],"summarization":[58],"tasks.":[59],"1)":[60],"Enhanced":[61],"Object":[62],"Proposal:":[63],"we":[64],"propose":[65],"novel":[67,100],"Conditional":[68],"Graph":[69],"fuse":[72],"into":[75],"latent":[76],"object":[77],"proposal.":[78],"2)":[79],"Visual":[80],"Knowledge:":[81],"Latent":[82],"Proposal":[83],"Aggregation":[84],"proposed":[86,105],"dynamically":[88],"extract":[89],"words":[91],"with":[92],"higher":[93],"semantic":[94,113],"levels.":[95],"3)":[96],"Sentence":[97],"Validation:":[98],"A":[99],"Discriminative":[101],"Language":[102],"Validator":[103],"verify":[107],"generated":[108],"captions":[109],"so":[110],"concepts":[114],"be":[116],"effectively":[117],"preserved.":[118],"experiments":[120],"on":[121,134],"two":[122],"public":[123],"datasets":[124],"(MVSD":[125],"MSR-VTT)":[127],"manifest":[128],"significant":[129],"improvements":[130],"over":[131],"state-of-the-art":[132],"approaches":[133],"all":[135],"metrics,":[136],"especially":[137],"BLEU-4":[139],"CIDEr.":[141],"code":[143],"available":[145],"at":[146],"https://github.com/baiyang4/D-LSG-Video-Caption.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2021-08-16T00:00:00"}