{"id":"https://openalex.org/W4298557199","doi":"https://doi.org/10.1145/3549179.3549182","title":"A Machine-Learning Pipeline for Semantic-Aware and Contexts-Rich Video Description Method","display_name":"A Machine-Learning Pipeline for Semantic-Aware and Contexts-Rich Video Description Method","publication_year":2022,"publication_date":"2022-07-29","ids":{"openalex":"https://openalex.org/W4298557199","doi":"https://doi.org/10.1145/3549179.3549182"},"language":"en","primary_location":{"id":"doi:10.1145/3549179.3549182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3549179.3549182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 4th International Conference on Pattern Recognition and Intelligent Systems","raw_type":"proceedings-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/A5053649812","display_name":"Yichiet Aun","orcid":"https://orcid.org/0000-0001-5977-7912"},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Yichiet Aun","raw_affiliation_strings":["Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020388209","display_name":"Jasmina Yen Min Khaw","orcid":null},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jasmina Yen Min Khaw","raw_affiliation_strings":["Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001807132","display_name":"Ming-Lee Gan","orcid":"https://orcid.org/0000-0002-0993-1130"},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ming-Lee Gan","raw_affiliation_strings":["Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045138387","display_name":"Ley-Ter Tin","orcid":null},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ley-Ter Tin","raw_affiliation_strings":["Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia","institution_ids":["https://openalex.org/I931681460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053649812"],"corresponding_institution_ids":["https://openalex.org/I931681460"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09107343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9531000256538391,"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":0.9531000256538391,"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/computer-science","display_name":"Computer science","score":0.8348432779312134},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6935054063796997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306747555732727},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48846235871315},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3753233850002289},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17947113513946533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348432779312134},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6935054063796997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306747555732727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48846235871315},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3753233850002289},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17947113513946533}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3549179.3549182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3549179.3549182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 4th International Conference on Pattern Recognition and Intelligent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1905153633","https://openalex.org/W2123301721","https://openalex.org/W2125707784","https://openalex.org/W2471768434","https://openalex.org/W2603203130","https://openalex.org/W2619082050","https://openalex.org/W2896457183","https://openalex.org/W2949535701","https://openalex.org/W3024515685","https://openalex.org/W3104915307","https://openalex.org/W6659511560","https://openalex.org/W6680375555","https://openalex.org/W6737009557","https://openalex.org/W6740934225","https://openalex.org/W6750227808","https://openalex.org/W6987196544"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Video":[0],"description":[1,22],"(VD)":[2],"methods":[3,19],"use":[4,43],"machine":[5],"learning":[6,45],"to":[7,11,23,46,61,92,149,161,183,190,197],"automatically":[8],"generate":[9,198],"sentences":[10,87,116,219],"describe":[12,94],"video":[13,29,95,199],"contents.":[14],"Global-description":[15],"based":[16,193],"VD":[17,41,140],"(gVD)":[18],"generates":[20],"global":[21],"provide":[24],"the":[25,68,77,99,163,169,172,215],"big":[26],"picture":[27],"of":[28,79,165,217,226,231],"scenes":[30],"but":[31],"they":[32,107],"lack":[33],"finer":[34],"grain":[35,159],"entities":[36,100,160,173,187,192],"information.":[37],"Meanwhile,":[38],"modern":[39],"entity-based":[40],"(eVD)":[42],"deep":[44],"train":[47],"ML":[48,112,130,145,154],"models":[49,155],"like":[50],"object":[51],"model":[52,56],"(YOLOv3),":[53],"human":[54],"activity":[55],"(CNN),":[57],"location":[58],"tracking":[59],"(DeepSORT)":[60],"resolve":[62],"individual":[63],"entity":[64,180],"that":[65,88,117,201,211],"made":[66],"up":[67],"complete":[69],"sentences.":[70],"However,":[71],"existing":[72],"eVD":[73,85,103],"are":[74,104,108,118,175,202],"limited":[75],"in":[76,84,115,171,220],"types":[78],"supported":[80],"entities;":[81],"thus,":[82],"resulting":[83,114],"generating":[86],"contexts-deprived":[89],"and":[90,123,138,188,204,228],"incomplete":[91],"clearly":[93],"scenes.":[96],"In":[97,125],"addition,":[98],"resolved":[101,166],"by":[102],"isolated":[105],"since":[106],"inferred":[109],"from":[110],"different":[111],"models;":[113],"not":[119],"semantically":[120],"cohesive;":[121],"contextually":[122],"grammatically.":[124],"this":[126],"paper,":[127],"a":[128,136,144],"two-stages":[129],"pipeline":[131,146],"(teVD)":[132],"is":[133,147],"proposed":[134],"for":[135,156],"holistic":[137],"semantic-aware":[139],"sentence":[141],"generation.":[142],"Firstly,":[143],"designed":[148],"aggregate":[150],"several":[151],"high":[152],"performing":[153],"resolving":[157],"fine":[158],"improve":[162],"accuracy":[164],"entities.":[167],"Second,":[168],"components":[170],"set":[174],"\u2018stitched\u2019":[176],"together":[177],"using":[178],"an":[179],"trimming":[181],"method":[182],"(1)":[184],"remove":[185],"shadow":[186],"(2)":[189],"re-arrange":[191],"on":[194,233],"linguistic":[195],"rules":[196],"descriptions":[200],"context-aware":[203],"less":[205],"ambiguous.":[206],"The":[207],"experimental":[208],"results":[209],"showed":[210],"teVD":[212],"successfully":[213],"improved":[214],"quality":[216],"generated":[218],"short":[221],"videos;":[222],"achieving":[223],"BLEU":[224],"score":[225,230],"48.01":[227],"METEOR":[229],"32.80":[232],"MSVD":[234],"dataset.":[235]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}