{"id":"https://openalex.org/W4364376005","doi":"https://doi.org/10.1007/s10462-023-10414-6","title":"Video description: A comprehensive survey of deep learning approaches","display_name":"Video description: A comprehensive survey of deep learning approaches","publication_year":2023,"publication_date":"2023-04-11","ids":{"openalex":"https://openalex.org/W4364376005","doi":"https://doi.org/10.1007/s10462-023-10414-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-023-10414-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-023-10414-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-023-10414-6.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10462-023-10414-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071678818","display_name":"Ghazala Rafiq","orcid":"https://orcid.org/0000-0002-1045-8715"},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ghazala Rafiq","raw_affiliation_strings":["Department of Information & Communication Engineering, Yeungnam University, \nGyeongsan-si, 38541, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information & Communication Engineering, Yeungnam University, \nGyeongsan-si, 38541, South Korea","institution_ids":["https://openalex.org/I55240360"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101952881","display_name":"Muhammad Rafiq","orcid":"https://orcid.org/0000-0001-6713-8766"},"institutions":[{"id":"https://openalex.org/I52010207","display_name":"Keimyung University","ror":"https://ror.org/00tjv0s33","country_code":"KR","type":"education","lineage":["https://openalex.org/I52010207"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Muhammad Rafiq","raw_affiliation_strings":["Department of Game & Mobile Engineering, Keimyung University, 1095 Dalgubeol-daero, Dalseo-gu, Daegu, 42601, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6713-8766","affiliations":[{"raw_affiliation_string":"Department of Game & Mobile Engineering, Keimyung University, 1095 Dalgubeol-daero, Dalseo-gu, Daegu, 42601, South Korea","institution_ids":["https://openalex.org/I52010207"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044080887","display_name":"Gyu Sang Choi","orcid":"https://orcid.org/0000-0002-0854-768X"},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Gyu Sang Choi","raw_affiliation_strings":["Department of Information & Communication Engineering, Yeungnam University, \nGyeongsan-si, 38541, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information & Communication Engineering, Yeungnam University, \nGyeongsan-si, 38541, South Korea","institution_ids":["https://openalex.org/I55240360"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044080887","https://openalex.org/A5101952881"],"corresponding_institution_ids":["https://openalex.org/I52010207","https://openalex.org/I55240360"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":28.3259,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.99581473,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"56","issue":"11","first_page":"13293","last_page":"13372"},"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":0.9983999729156494,"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":0.9944999814033508,"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":0.8988996744155884},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8523950576782227},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6402592062950134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6081993579864502},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5737485885620117},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.571241557598114},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46954450011253357},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41327041387557983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8988996744155884},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8523950576782227},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6402592062950134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6081993579864502},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5737485885620117},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.571241557598114},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46954450011253357},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41327041387557983},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10462-023-10414-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-023-10414-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-023-10414-6.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10462-023-10414-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-023-10414-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-023-10414-6.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G1989376136","display_name":null,"funder_award_id":"NRF-2019R1A2C1006159","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G284234960","display_name":null,"funder_award_id":"NRF-2021R1A6A1A03039493","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7875769530","display_name":null,"funder_award_id":"NRF-2021R1A6A1A03039493","funder_id":"https://openalex.org/F4320321380","funder_display_name":"Yeungnam University"},{"id":"https://openalex.org/G960464093","display_name":null,"funder_award_id":"2021R1A6A1A03039493.","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321380","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4364376005.pdf","grobid_xml":"https://content.openalex.org/works/W4364376005.grobid-xml"},"referenced_works_count":144,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1571576241","https://openalex.org/W1573040851","https://openalex.org/W1601567445","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1995820507","https://openalex.org/W2016053056","https://openalex.org/W2016589492","https://openalex.org/W2065883680","https://openalex.org/W2078861931","https://openalex.org/W2084376682","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2110933980","https://openalex.org/W2124386111","https://openalex.org/W2128856065","https://openalex.org/W2133512280","https://openalex.org/W2139501017","https://openalex.org/W2145339207","https://openalex.org/W2155893237","https://openalex.org/W2157331557","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2296073425","https://openalex.org/W2302086703","https://openalex.org/W2425121537","https://openalex.org/W2508429489","https://openalex.org/W2523993696","https://openalex.org/W2526417872","https://openalex.org/W2556388456","https://openalex.org/W2564590796","https://openalex.org/W2575842049","https://openalex.org/W2584992898","https://openalex.org/W2607151106","https://openalex.org/W2621571501","https://openalex.org/W2737030113","https://openalex.org/W2739107216","https://openalex.org/W2740388348","https://openalex.org/W2751392123","https://openalex.org/W2766375149","https://openalex.org/W2774556334","https://openalex.org/W2787326684","https://openalex.org/W2788713610","https://openalex.org/W2788738262","https://openalex.org/W2790776232","https://openalex.org/W2803620531","https://openalex.org/W2807834696","https://openalex.org/W2883429621","https://openalex.org/W2884675507","https://openalex.org/W2887097088","https://openalex.org/W2888137286","https://openalex.org/W2891939431","https://openalex.org/W2895845501","https://openalex.org/W2905145027","https://openalex.org/W2914306086","https://openalex.org/W2941825186","https://openalex.org/W2948358897","https://openalex.org/W2950579554","https://openalex.org/W2953461088","https://openalex.org/W2962681491","https://openalex.org/W2962762462","https://openalex.org/W2962861647","https://openalex.org/W2962907269","https://openalex.org/W2962937869","https://openalex.org/W2962994439","https://openalex.org/W2963084599","https://openalex.org/W2963088785","https://openalex.org/W2963115613","https://openalex.org/W2963177403","https://openalex.org/W2963290083","https://openalex.org/W2963351113","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2963971014","https://openalex.org/W2964101993","https://openalex.org/W2964110616","https://openalex.org/W2964232540","https://openalex.org/W2964532449","https://openalex.org/W2965432789","https://openalex.org/W2968101724","https://openalex.org/W2971075730","https://openalex.org/W2979936813","https://openalex.org/W2981851019","https://openalex.org/W2984862483","https://openalex.org/W2988753485","https://openalex.org/W2989322838","https://openalex.org/W2990423554","https://openalex.org/W3000154564","https://openalex.org/W3009192917","https://openalex.org/W3010779223","https://openalex.org/W3013601028","https://openalex.org/W3034221024","https://openalex.org/W3034464851","https://openalex.org/W3034815696","https://openalex.org/W3035237998","https://openalex.org/W3035284526","https://openalex.org/W3035365026","https://openalex.org/W3038017128","https://openalex.org/W3039060838","https://openalex.org/W3100255860","https://openalex.org/W3101767943","https://openalex.org/W3104862079","https://openalex.org/W3105232955","https://openalex.org/W3119777426","https://openalex.org/W3120164061","https://openalex.org/W3140854437","https://openalex.org/W3160463872","https://openalex.org/W3160891393","https://openalex.org/W3166366124","https://openalex.org/W3167939936","https://openalex.org/W3174257385","https://openalex.org/W3176425931","https://openalex.org/W3176514808","https://openalex.org/W3176689360","https://openalex.org/W3178322352","https://openalex.org/W3182910454","https://openalex.org/W3196336622","https://openalex.org/W3198619403","https://openalex.org/W3209229003","https://openalex.org/W4200621741","https://openalex.org/W4210668396","https://openalex.org/W4213019189","https://openalex.org/W4214612132","https://openalex.org/W4214663214","https://openalex.org/W4220848440","https://openalex.org/W4221167937","https://openalex.org/W4225608741","https://openalex.org/W4230718924","https://openalex.org/W4283585459","https://openalex.org/W4285503503","https://openalex.org/W4288083805","https://openalex.org/W4312463400","https://openalex.org/W4312522167","https://openalex.org/W4312956563","https://openalex.org/W6600042225","https://openalex.org/W6600679772","https://openalex.org/W6600688380","https://openalex.org/W6600828087","https://openalex.org/W6601695987","https://openalex.org/W6629651325","https://openalex.org/W6704017408","https://openalex.org/W6729204602"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W4317547544","https://openalex.org/W4313395829"],"abstract_inverted_index":{"Abstract":[0],"Video":[1],"description":[2,43],"refers":[3],"to":[4,49,66,84,89,124],"understanding":[5,12],"visual":[6],"content":[7],"and":[8,26,34,63,112,149,158,168,222,228],"transforming":[9],"that":[10,75],"acquired":[11],"into":[13],"automatic":[14,85],"textual":[15],"narration.":[16],"It":[17,185],"bridges":[18],"the":[19,60,104,138,189,198],"key":[20],"AI":[21],"fields":[22],"of":[23,59,100,183,200,203],"computer":[24],"vision":[25],"natural":[27],"language":[28],"processing":[29,219],"in":[30,217],"conjunction":[31],"with":[32,120,177,197],"real-time":[33],"practical":[35],"applications.":[36],"Deep":[37],"learning-based":[38],"approaches":[39,83],"employed":[40,64,136],"for":[41,69,162,192,214,220,225],"video":[42,70,218],"have":[44],"demonstrated":[45],"enhanced":[46],"results":[47],"compared":[48],"conventional":[50],"approaches.":[51],"The":[52,152],"current":[53],"literature":[54],"lacks":[55],"a":[56,97,127,156,180],"thorough":[57],"interpretation":[58],"recently":[61],"developed":[62],"sequence":[65,67,90],"techniques":[68],"description.":[71],"This":[72,115],"paper":[73],"fills":[74],"gap":[76],"by":[77,146],"focusing":[78],"mainly":[79],"on":[80,126,171,179],"deep":[81],"learning-enabled":[82],"caption":[86],"generation.":[87],"Sequence":[88],"models":[91],"follow":[92],"an":[93,110,121,211],"Encoder\u2013Decoder":[94,139],"architecture":[95,161],"employing":[96],"specific":[98,128],"composition":[99],"CNN,":[101],"RNN,":[102],"or":[103,107,224],"variants":[105],"LSTM":[106],"GRU":[108],"as":[109],"encoder":[111],"decoder":[113],"block.":[114],"standard-architecture":[116],"can":[117,141,186,232],"be":[118],"fused":[119],"attention":[122],"mechanism":[123,154],"focus":[125],"distinctiveness,":[129],"achieving":[130],"high":[131],"quality":[132],"results.":[133],"Reinforcement":[134],"learning":[135],"within":[137],"structure":[140],"progressively":[142],"deliver":[143],"state-of-the-art":[144],"captions":[145],"following":[147],"exploration":[148],"exploitation":[150],"strategies.":[151],"transformer":[153],"is":[155,209],"modern":[157],"efficient":[159],"transductive":[160],"robust":[163],"output.":[164],"Free":[165],"from":[166,236],"recurrence,":[167],"solely":[169],"based":[170],"self-attention,":[172],"it":[173],"allows":[174],"parallelization":[175],"along":[176],"training":[178],"massive":[181],"amount":[182],"data.":[184],"fully":[187],"utilize":[188],"available":[190],"GPUs":[191],"most":[193],"NLP":[194],"tasks.":[195],"Recently,":[196],"emergence":[199],"several":[201],"versions":[202],"transformers,":[204],"long":[205],"term":[206],"dependency":[207],"handling":[208],"not":[210],"issue":[212],"anymore":[213],"researchers":[215],"engaged":[216],"summarization":[221],"description,":[223],"autonomous-vehicle,":[226],"surveillance,":[227],"instructional":[229],"purposes.":[230],"They":[231],"get":[233],"auspicious":[234],"directions":[235],"this":[237],"research.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":8}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}