{"id":"https://openalex.org/W4388430346","doi":"https://doi.org/10.1109/tmm.2023.3330070","title":"GPT-Based Knowledge Guiding Network for Commonsense Video Captioning","display_name":"GPT-Based Knowledge Guiding Network for Commonsense Video Captioning","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4388430346","doi":"https://doi.org/10.1109/tmm.2023.3330070"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3330070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3330070","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5005487402","display_name":"Mengqi Yuan","orcid":"https://orcid.org/0000-0001-9183-3267"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Yuan","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China","College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9183-3267","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084003247","display_name":"Gengyun Jia","orcid":"https://orcid.org/0000-0002-0513-138X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gengyun Jia","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China","College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0513-138X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":1.0636,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79686932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"5147","last_page":"5158"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9768000245094299,"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":0.9493110179901123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8916248679161072},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.736763596534729},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.640259861946106},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5924112200737},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.5563433170318604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4825519919395447},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4704887866973877},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4298710823059082},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42359796166419983},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.278290718793869},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19008103013038635}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9493110179901123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8916248679161072},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.736763596534729},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.640259861946106},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5924112200737},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.5563433170318604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4825519919395447},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4704887866973877},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4298710823059082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42359796166419983},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.278290718793869},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19008103013038635},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3330070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3330070","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3275790314","display_name":null,"funder_award_id":"NY222115","funder_id":"https://openalex.org/F4320323268","funder_display_name":"Nanjing University of Posts and Telecommunications"},{"id":"https://openalex.org/G4317995357","display_name":null,"funder_award_id":"61936005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7576569306","display_name":null,"funder_award_id":"62306150","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"},{"id":"https://openalex.org/F4320323268","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2608022654","https://openalex.org/W2739107216","https://openalex.org/W2798405286","https://openalex.org/W2895845501","https://openalex.org/W2896457183","https://openalex.org/W2938759099","https://openalex.org/W2947312908","https://openalex.org/W2963293463","https://openalex.org/W2963351113","https://openalex.org/W2963524571","https://openalex.org/W2964137974","https://openalex.org/W2979936813","https://openalex.org/W2981165461","https://openalex.org/W3013612439","https://openalex.org/W3034188691","https://openalex.org/W3034464851","https://openalex.org/W3036900224","https://openalex.org/W3082226086","https://openalex.org/W3101767943","https://openalex.org/W3134875898","https://openalex.org/W3153565615","https://openalex.org/W3163971663","https://openalex.org/W3167008019","https://openalex.org/W3174257385","https://openalex.org/W3174441232","https://openalex.org/W3175431949","https://openalex.org/W3190457301","https://openalex.org/W3199693760","https://openalex.org/W3201200828","https://openalex.org/W3205021045","https://openalex.org/W3206634578","https://openalex.org/W3207005999","https://openalex.org/W3207493267","https://openalex.org/W3209229003","https://openalex.org/W3209772048","https://openalex.org/W3216180229","https://openalex.org/W4211103897","https://openalex.org/W4214692497","https://openalex.org/W4214844714","https://openalex.org/W4220848440","https://openalex.org/W4226143692","https://openalex.org/W4226321975","https://openalex.org/W4312463400","https://openalex.org/W4312793544","https://openalex.org/W4385245566","https://openalex.org/W4386065596","https://openalex.org/W6631190155","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6729831399","https://openalex.org/W6785062888","https://openalex.org/W6838989559","https://openalex.org/W6839015040","https://openalex.org/W6849257913"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W2196562041","https://openalex.org/W4385488510","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"Video-based":[0],"commonsense":[1,14,28,136],"captioning":[2,59],"aims":[3],"to":[4,24,36,77,86,91,100,118],"generate":[5,27],"captions":[6],"for":[7,148],"the":[8,16,38,53,106,111,115,123,155,163],"video":[9,22,58,107,142],"content":[10,108],"while":[11],"providing":[12],"multiple":[13],"about":[15],"underlying":[17],"event.":[18],"Existing":[19],"methods":[20],"utilize":[21],"features":[23,127,143],"explore":[25],"and":[26,45,81,97,102,138],"containing":[29],"latent":[30],"semantics.":[31],"However,":[32],"this":[33,62],"process":[34],"needs":[35],"overcome":[37],"complex":[39],"semantic":[40,133,150],"gap":[41],"between":[42],"visible":[43],"videos":[44],"invisible":[46],"commonsense,":[47],"which":[48,74],"is":[49],"not":[50],"supported":[51],"by":[52,122],"limited":[54],"knowledge":[55,80,137],"in":[56,128,144],"existing":[57],"datasets.":[60],"To":[61],"end,":[63],"we":[64,94],"propose":[65],"a":[66,83,145],"novel":[67],"GPT-based":[68],"Two-stage":[69],"Knowledge":[70],"Guiding":[71],"Network":[72],"(TKG-Net),":[73],"uses":[75],"GPT":[76,99],"augment":[78,92],"datasets":[79],"introduces":[82],"cross-attention":[84,146],"mechanism":[85,147],"fuse":[87],"multimodal":[88,149],"knowledge.":[89],"Specifically,":[90],"knowledge,":[93],"set":[95],"prompts":[96],"finetune":[98],"imagine":[101],"reason":[103],"based":[104],"on":[105,154,167],"description":[109],"at":[110],"first":[112],"stage.":[113],"At":[114],"second":[116],"stage,":[117],"prevent":[119],"over-reasoning":[120],"caused":[121],"loss":[124],"of":[125,135],"visual":[126],"GPT,":[129],"TKG-Net":[130],"extracts":[131],"high-level":[132],"representations":[134],"fuses":[139],"them":[140],"with":[141],"interaction.":[151],"Our":[152],"experiments":[153],"large-scale":[156],"Video-to-Commonsense":[157],"dataset":[158],"manifest":[159],"significant":[160],"improvements":[161],"over":[162],"previous":[164],"state-of-the-art":[165],"approach":[166],"all":[168],"metrics.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}