{"id":"https://openalex.org/W4372266864","doi":"https://doi.org/10.1109/icassp49357.2023.10094571","title":"Video Captioning via Relation-Aware Graph Learning","display_name":"Video Captioning via Relation-Aware Graph Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266864","doi":"https://doi.org/10.1109/icassp49357.2023.10094571"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/Video_Captioning_via_Relation-Aware_Graph_Learning/24733563","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043971208","display_name":"Yi Zheng","orcid":"https://orcid.org/0000-0002-8996-9840"},"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":"Yi Zheng","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","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":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076958401","display_name":"Qiujie Xie","orcid":"https://orcid.org/0000-0003-0396-9063"},"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":"Qiujie Xie","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China","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":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017732945","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-5918-8712"},"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":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, China","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":["Shanghai University of Finance and Economics,School of Information Management and Engineering,China","School of Information Management and Engineering, Shanghai University of Finance and Economics, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics,School of Information Management and Engineering,China","institution_ids":["https://openalex.org/I181679659"]},{"raw_affiliation_string":"School of Information Management and Engineering, Shanghai University of Finance and Economics, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048961502","display_name":"Shang Gao","orcid":"https://orcid.org/0000-0002-2176-6553"},"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":["Deakin University,School of Information Technology,Australia","School of Information Technology, Deakin University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University,School of Information Technology,Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"School of Information Technology, Deakin University, Australia","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9980999827384949,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8731042742729187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.796425461769104},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.7122355103492737},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.6621927618980408},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6254622340202332},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5671335458755493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5396222472190857},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5147566795349121},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3285016715526581},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3221389651298523},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.309976726770401},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20505547523498535},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19003507494926453}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8731042742729187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796425461769104},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7122355103492737},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.6621927618980408},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6254622340202332},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5671335458755493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5396222472190857},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5147566795349121},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3285016715526581},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3221389651298523},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.309976726770401},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20505547523498535},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19003507494926453},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/24733563","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Video_Captioning_via_Relation-Aware_Graph_Learning/24733563","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/24733563","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Video_Captioning_via_Relation-Aware_Graph_Learning/24733563","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1586939924","https://openalex.org/W1956340063","https://openalex.org/W2117539524","https://openalex.org/W2119717200","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2604314403","https://openalex.org/W2619947201","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2962907269","https://openalex.org/W2963084599","https://openalex.org/W2963514444","https://openalex.org/W2963524571","https://openalex.org/W2964015378","https://openalex.org/W2964350391","https://openalex.org/W2984862483","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3035392611","https://openalex.org/W3035404043","https://openalex.org/W3035763695","https://openalex.org/W3039060838","https://openalex.org/W3176425931","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6726873649","https://openalex.org/W6735632219","https://openalex.org/W6898505805","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4287661223","https://openalex.org/W4214591816","https://openalex.org/W4389471147","https://openalex.org/W4312650216","https://openalex.org/W4387129494","https://openalex.org/W3109142545","https://openalex.org/W4221155265","https://openalex.org/W4385571298","https://openalex.org/W2590022237","https://openalex.org/W4390195594"],"abstract_inverted_index":{"Recent":[0],"neural":[1],"models":[2,49],"for":[3,55,86,103],"video":[4,25],"captioning":[5],"usually":[6],"employed":[7],"an":[8],"encoder-decoder":[9],"framework.":[10,46,118],"However,":[11],"most":[12],"approaches":[13],"either":[14],"neglected":[15],"the":[16,29,66,87,104,114],"spatial":[17,51,67],"and":[18,52,101,128],"temporal":[19,53,77],"interactions":[20],"between":[21,69],"objects":[22,71,89],"in":[23,32,72,90],"a":[24,41,59,73,76],"or":[26],"implicitly":[27],"modelled":[28],"interactions,":[30],"resulting":[31],"less":[33],"desired":[34],"performance.":[35],"In":[36,57],"this":[37],"paper,":[38],"we":[39],"propose":[40],"novel":[42],"relation-aware":[43,60],"graph":[44,61,78],"learning":[45],"It":[47,119],"explicitly":[48],"both":[50,95],"relations":[54,68,98],"objects.":[56],"particular,":[58],"is":[62,80],"designed":[63,81],"to":[64,82],"depict":[65],"different":[70],"scene.":[74],"Parallelly,":[75],"network":[79],"perform":[83],"relational":[84],"reasoning":[85],"same":[88],"adjacent":[91],"frames.":[92],"Features":[93],"of":[94,97,116],"types":[96],"are":[99],"learned":[100],"fused":[102],"follow-up":[105],"language":[106],"decoder.":[107],"Experiments":[108],"on":[109,126],"two":[110],"bench-mark":[111],"datasets":[112],"show":[113],"effectiveness":[115],"our":[117],"achieves":[120],"state-of-the-art":[121],"performance":[122],"with":[123],"CIDEr":[124],"scores":[125],"MSVD":[127],"MSR-VTT.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
