{"id":"https://openalex.org/W4380077272","doi":"https://doi.org/10.1142/s1793351x23640031","title":"Hierarchical Time-Aware Summarization with an Adaptive Transformer for Video Captioning","display_name":"Hierarchical Time-Aware Summarization with an Adaptive Transformer for Video Captioning","publication_year":2023,"publication_date":"2023-06-10","ids":{"openalex":"https://openalex.org/W4380077272","doi":"https://doi.org/10.1142/s1793351x23640031"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x23640031","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x23640031","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","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/A5049366278","display_name":"Leonardo Vilela Cardoso","orcid":"https://orcid.org/0000-0003-0365-6403"},"institutions":[{"id":"https://openalex.org/I170935008","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica de Minas Gerais","ror":"https://ror.org/03j1rr444","country_code":"BR","type":"education","lineage":["https://openalex.org/I170935008"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Vilela Cardoso","raw_affiliation_strings":["Image and Multimedia Data Science Laboratory (IMSCIENCE), Pontifcia Universidade Catlica de Minas Gerais (PUC Minas), Av. Dom Jos\u00e9 Gaspar, 500 - Pr\u00e9dio 20, 30535-901, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Multimedia Data Science Laboratory (IMSCIENCE), Pontifcia Universidade Catlica de Minas Gerais (PUC Minas), Av. Dom Jos\u00e9 Gaspar, 500 - Pr\u00e9dio 20, 30535-901, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I170935008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070629635","display_name":"Silvio Jamil F. Guimar\u00e3es","orcid":"https://orcid.org/0000-0001-8522-2056"},"institutions":[{"id":"https://openalex.org/I170935008","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica de Minas Gerais","ror":"https://ror.org/03j1rr444","country_code":"BR","type":"education","lineage":["https://openalex.org/I170935008"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Silvio Jamil Ferzoli Guimar\u00e3es","raw_affiliation_strings":["Image and Multimedia Data Science Laboratory (IMSCIENCE), Pontifcia Universidade Catlica de Minas Gerais (PUC Minas), Av. Dom Jos\u00e9 Gaspar, 500 - Pr\u00e9dio 20, 30535-901, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Multimedia Data Science Laboratory (IMSCIENCE), Pontifcia Universidade Catlica de Minas Gerais (PUC Minas), Av. Dom Jos\u00e9 Gaspar, 500 - Pr\u00e9dio 20, 30535-901, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I170935008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035002611","display_name":"Zenilton K. G. Patroc\u00ednio","orcid":"https://orcid.org/0000-0003-0804-1790"},"institutions":[{"id":"https://openalex.org/I170935008","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica de Minas Gerais","ror":"https://ror.org/03j1rr444","country_code":"BR","type":"education","lineage":["https://openalex.org/I170935008"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Zenilton Kleber Gon\u00e7alves do Patroc\u00ednio J\u00fanior","raw_affiliation_strings":["Image and Multimedia Data Science Laboratory (IMSCIENCE), Pontifcia Universidade Catlica de Minas Gerais (PUC Minas), Av. Dom Jos\u00e9 Gaspar, 500 - Pr\u00e9dio 20, 30535-901, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Multimedia Data Science Laboratory (IMSCIENCE), Pontifcia Universidade Catlica de Minas Gerais (PUC Minas), Av. Dom Jos\u00e9 Gaspar, 500 - Pr\u00e9dio 20, 30535-901, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I170935008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4491,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62731762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"17","issue":"04","first_page":"569","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9987999796867371,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9933000206947327,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9912999868392944,"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/computer-science","display_name":"Computer science","score":0.888244092464447},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8329784870147705},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7212461233139038},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6696167588233948},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.5746423602104187},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5400128960609436},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.46196243166923523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4398857355117798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4385926425457001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34731918573379517},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12404096126556396},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1065070629119873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.888244092464447},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8329784870147705},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7212461233139038},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6696167588233948},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.5746423602104187},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5400128960609436},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.46196243166923523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4398857355117798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4385926425457001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34731918573379517},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12404096126556396},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1065070629119873},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793351x23640031","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x23640031","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1250581112","https://openalex.org/W2064675550","https://openalex.org/W2621212586","https://openalex.org/W3134665270","https://openalex.org/W3210314917","https://openalex.org/W4288083805","https://openalex.org/W4306393283","https://openalex.org/W4311424438"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3174042809","https://openalex.org/W2391800119","https://openalex.org/W2595239241","https://openalex.org/W2052919063","https://openalex.org/W2799181378","https://openalex.org/W2064074028","https://openalex.org/W3003711649","https://openalex.org/W2904173691","https://openalex.org/W4365517254"],"abstract_inverted_index":{"A":[0],"coherent":[1],"description":[2,172],"is":[3,36],"an":[4,70],"ultimate":[5],"goal":[6],"regarding":[7],"video":[8,35,117,160],"captioning":[9],"via":[10],"a":[11,31,34,63,76,99,132],"couple":[12],"of":[13,24,86,135,148],"sentences":[14,168],"because":[15],"it":[16,153],"might":[17],"also":[18,54],"affect":[19],"the":[20,25,39,80,84,106,109,116,121,139,146,158,163,166,171,175],"consistency":[21],"and":[22,48,124,169],"intelligibility":[23],"generated":[26,110,167],"results.":[27],"In":[28],"this":[29,149],"context,":[30],"paragraph":[32],"describing":[33],"affected":[37],"by":[38,138],"activities":[40],"used":[41],"to":[42,78,90,97,127],"both":[43],"produce":[44],"its":[45],"specific":[46],"narrative":[47],"provide":[49],"some":[50],"clues":[51],"that":[52,74,88,126],"can":[53],"assist":[55],"in":[56,120,165,174],"decreasing":[57,162],"textual":[58],"repetition.":[59],"This":[60,102],"work":[61],"proposes":[62],"model,":[64],"named":[65],"Hierarchical":[66],"time-aware":[67],"Summarization":[68],"with":[69,94],"Adaptive":[71],"Transformer":[72],"(HSAT),":[73],"uses":[75,125],"strategy":[77],"enhance":[79,98],"frame":[81],"selection":[82],"reducing":[83],"amount":[85],"information":[87],"needed":[89],"be":[91],"processed":[92],"along":[93],"attention":[95],"mechanisms":[96],"memory-augmented":[100],"transformer.":[101],"new":[103,150],"approach":[104,151],"increases":[105],"coherence":[107,156],"among":[108,157],"sentences,":[111],"assessing":[112],"data":[113],"importance":[114],"(about":[115],"segments)":[118],"contained":[119],"self-attention":[122],"results":[123,144],"improve":[128],"readability":[129],"using":[130],"only":[131],"small":[133],"fraction":[134],"time":[136],"spent":[137],"other":[140],"methods.":[141],"The":[142],"test":[143],"show":[145],"potential":[147],"as":[152],"provides":[154],"higher":[155],"various":[159],"segments,":[161],"repetition":[164],"improving":[170],"diversity":[173],"ActivityNet":[176],"Captions":[177],"dataset.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}