{"id":"https://openalex.org/W4226109438","doi":"https://doi.org/10.1109/tcsvt.2022.3169894","title":"Towards Knowledge-Aware Video Captioning via Transitive Visual Relationship Detection","display_name":"Towards Knowledge-Aware Video Captioning via Transitive Visual Relationship Detection","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4226109438","doi":"https://doi.org/10.1109/tcsvt.2022.3169894"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3169894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3169894","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5047021636","display_name":"Bofeng Wu","orcid":"https://orcid.org/0000-0002-4539-4854"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bofeng Wu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4539-4854","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009352936","display_name":"Guocheng Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guocheng Niu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1922-7283","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112673776","display_name":"Xinyan Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyan Xiao","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042342029","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0001-6478-9192"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["School of International Business, Zhejiang International Studies University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6478-9192","affiliations":[{"raw_affiliation_string":"School of International Business, Zhejiang International Studies University, Hangzhou, China","institution_ids":["https://openalex.org/I105126617"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100677198","display_name":"Hua Wu","orcid":"https://orcid.org/0000-0002-5687-7800"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047021636"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":4.7959,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96225657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"32","issue":"10","first_page":"6753","last_page":"6765"},"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":0.998199999332428,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9944000244140625,"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/interpretability","display_name":"Interpretability","score":0.8595667481422424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8377149105072021},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8048765063285828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6300180554389954},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5583608746528625},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5001466274261475},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4834921658039093},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45955929160118103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3780094087123871},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3429112136363983},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2701098322868347},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1268562376499176}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8595667481422424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377149105072021},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8048765063285828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6300180554389954},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5583608746528625},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5001466274261475},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4834921658039093},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45955929160118103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3780094087123871},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3429112136363983},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2701098322868347},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1268562376499176},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3169894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3169894","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4605825167","display_name":null,"funder_award_id":"U21B2040","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5182346650","display_name":null,"funder_award_id":"61972361","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6151690139","display_name":null,"funder_award_id":"62020106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6570941292","display_name":null,"funder_award_id":"62125201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":null,"funder_award_id":"61836002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2016089260","https://openalex.org/W2081580037","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2557264465","https://openalex.org/W2579549467","https://openalex.org/W2766375149","https://openalex.org/W2766520430","https://openalex.org/W2806331055","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2962737704","https://openalex.org/W2962990649","https://openalex.org/W2963101956","https://openalex.org/W2963184176","https://openalex.org/W2963536419","https://openalex.org/W2963971014","https://openalex.org/W2964350391","https://openalex.org/W2984862483","https://openalex.org/W2988753485","https://openalex.org/W2990964949","https://openalex.org/W2997248215","https://openalex.org/W3022778813","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3047922786","https://openalex.org/W3094751268","https://openalex.org/W3098682680","https://openalex.org/W3117181316","https://openalex.org/W3134875898","https://openalex.org/W3160891393","https://openalex.org/W4205510032","https://openalex.org/W6620707391","https://openalex.org/W6639432524","https://openalex.org/W6682631176","https://openalex.org/W6694395031","https://openalex.org/W6739901393","https://openalex.org/W6784761581"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2905433371","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Video":[0],"captioning":[1,64],"can":[2],"be":[3],"enhanced":[4],"by":[5,149],"incorporating":[6],"the":[7,18,33,46,52,89,92,103,107,114,117,120,131,137,146,153,175,196],"knowledge,":[8],"which":[9,86,129],"is":[10],"usually":[11],"represented":[12],"as":[13,187,189],"relationships":[14,68,193],"of":[15,91,191,200],"objects.":[16],"However,":[17],"previous":[19],"methods":[20],"construct":[21,96],"only":[22],"superficial":[23],"or":[24,39],"static":[25],"object":[26,67,147],"relationships,":[27],"and":[28,49,95,109,198],"often":[29],"introduce":[30],"noise":[31],"into":[32],"task":[34],"through":[35],"irrelevant":[36],"common":[37],"sense":[38],"fixed":[40],"syntax":[41],"templates.":[42],"These":[43],"problems":[44],"mitigate":[45],"model":[47],"interpretability":[48,199],"lead":[50],"to":[51,61,101,122,139,144,194],"undesirable":[53],"consequence.":[54],"To":[55],"overcome":[56],"these":[57],"limitations,":[58],"we":[59,76,87,112,156,182],"propose":[60],"enhance":[62],"video":[63],"with":[65],"deep-level":[66,132,150],"that":[69,174],"are":[70],"adaptively":[71],"explored":[72],"during":[73],"training.":[74],"Specifically,":[75],"present":[77,183],"a":[78,140],"Transitive":[79],"Visual":[80],"Relationship":[81],"Detection":[82],"(TVRD)":[83],"module":[84],"in":[85],"estimate":[88],"actions":[90,121],"visual":[93,192],"objects,":[94],"an":[97,125,159],"Object-Action":[98],"Graph":[99,127],"(OAG)":[100],"describe":[102],"shallow":[104],"relationship":[105],"between":[106,116],"objects":[108,118],"actions.":[110],"Then":[111],"bridge":[113],"gap":[115],"via":[119],"transitively":[123],"infer":[124],"Object-Object":[126],"(OOG)":[128],"reflects":[130],"relationship.":[133],"We":[134],"further":[135],"feed":[136],"OOG":[138],"graph":[141],"convolutional":[142],"network":[143],"refine":[145],"representation":[148],"relationships.":[151],"With":[152],"refined":[154],"representation,":[155],"capitalize":[157],"on":[158,167],"LSTM-based":[160],"decoder":[161],"for":[162],"caption":[163],"generation.":[164],"Experimental":[165],"results":[166],"two":[168],"benchmark":[169],"datasets:":[170],"MSVD,":[171],"MSR-VTT":[172],"demonstrate":[173,195],"proposed":[176],"method":[177],"achieves":[178],"state-of-the-art":[179],"performance.":[180],"Lastly,":[181],"comprehensive":[184],"ablation":[185],"studies":[186],"well":[188],"visualization":[190],"effectiveness":[197],"our":[201],"model.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}