{"id":"https://openalex.org/W4366392594","doi":"https://doi.org/10.3390/rs15082139","title":"CapERA: Captioning Events in Aerial Videos","display_name":"CapERA: Captioning Events in Aerial Videos","publication_year":2023,"publication_date":"2023-04-18","ids":{"openalex":"https://openalex.org/W4366392594","doi":"https://doi.org/10.3390/rs15082139"},"language":"en","primary_location":{"id":"doi:10.3390/rs15082139","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15082139","pdf_url":"https://www.mdpi.com/2072-4292/15/8/2139/pdf?version=1681887583","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/15/8/2139/pdf?version=1681887583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064445451","display_name":"Laila Bashmal","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Laila Bashmal","raw_affiliation_strings":["Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054237841","display_name":"Yakoub Bazi","orcid":"https://orcid.org/0000-0001-9287-0596"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Yakoub Bazi","raw_affiliation_strings":["Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071736181","display_name":"Mohamad Mahmoud Al Rahhal","orcid":"https://orcid.org/0000-0002-8105-9746"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohamad Mahmoud Al Rahhal","raw_affiliation_strings":["Applied Computer Science Department, College of Applied Computer Science, King Saud University, Riyadh 11543, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Applied Computer Science Department, College of Applied Computer Science, King Saud University, Riyadh 11543, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001185870","display_name":"Mansour Zuair","orcid":"https://orcid.org/0000-0003-2490-5739"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mansour Zuair","raw_affiliation_strings":["Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021389231","display_name":"Farid Melgani","orcid":"https://orcid.org/0000-0001-9745-3732"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Farid Melgani","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054237841"],"corresponding_institution_ids":["https://openalex.org/I28022161"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":1.2146,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80977394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"15","issue":"8","first_page":"2139","last_page":"2139"},"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":0.9975000023841858,"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":0.9957000017166138,"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":0.9759659767150879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8937707543373108},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7127653360366821},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6691642999649048},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6410138607025146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5793896913528442},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5284136533737183},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4196412265300751},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1969168484210968}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9759659767150879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8937707543373108},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7127653360366821},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6691642999649048},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6410138607025146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5793896913528442},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5284136533737183},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4196412265300751},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1969168484210968},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/rs15082139","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15082139","pdf_url":"https://www.mdpi.com/2072-4292/15/8/2139/pdf?version=1681887583","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e9af47099bf741cebe2c5b9f99ee938b","is_oa":true,"landing_page_url":"https://doaj.org/article/e9af47099bf741cebe2c5b9f99ee938b","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 15, Iss 8, p 2139 (2023)","raw_type":"article"},{"id":"pmh:oai:iris.unitn.it:11572/400700","is_oa":true,"landing_page_url":"https://www.mdpi.com/2072-4292/15/8/2139","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:mdpi.com:/2072-4292/15/8/2139/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/rs15082139","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing; Volume 15; Issue 8; Pages: 2139","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/rs15082139","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs15082139","pdf_url":"https://www.mdpi.com/2072-4292/15/8/2139/pdf?version=1681887583","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4366392594.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1539356909","https://openalex.org/W1956340063","https://openalex.org/W2108598243","https://openalex.org/W2133459682","https://openalex.org/W2602837914","https://openalex.org/W2792542990","https://openalex.org/W2794176907","https://openalex.org/W2962749812","https://openalex.org/W2962777203","https://openalex.org/W2969238677","https://openalex.org/W2984008963","https://openalex.org/W2996264288","https://openalex.org/W3003741573","https://openalex.org/W3005267631","https://openalex.org/W3028752951","https://openalex.org/W3144503735","https://openalex.org/W3159705445","https://openalex.org/W3196922338","https://openalex.org/W3210997334","https://openalex.org/W4211038108","https://openalex.org/W4283639897","https://openalex.org/W4290973251","https://openalex.org/W4312576773","https://openalex.org/W4312635102","https://openalex.org/W6682631176","https://openalex.org/W6800425103","https://openalex.org/W6808176243","https://openalex.org/W6841125288"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2275988210"],"abstract_inverted_index":{"In":[0,161],"this":[1],"paper,":[2],"we":[3,94,165],"introduce":[4],"the":[5,10,44,60,75,86,90,100,117,125,131,147,151,158,162,168,182,187,200,203,214,225],"CapERA":[6,101,228],"dataset,":[7,45],"which":[8],"upgrades":[9],"Event":[11],"Recognition":[12],"in":[13,88],"Aerial":[14],"Videos":[15],"(ERA)":[16],"dataset":[17,25,102],"to":[18,27,78,103,123,149,180,197],"aerial":[19,47,220],"video":[20,37,109,132,159,170,173,243],"captioning.":[21,110],"The":[22,111,127,206],"newly":[23],"proposed":[24,112],"aims":[26],"advance":[28],"visual\u2013language-understanding":[29],"tasks":[30],"for":[31,99,107,235],"UAV":[32,108,242],"videos":[33,48],"by":[34,135],"providing":[35],"each":[36],"with":[38,52,120,241],"diverse":[39],"textual":[40],"descriptions.":[41],"To":[42],"build":[43],"2864":[46],"are":[49,71],"manually":[50],"annotated":[51],"a":[53,96,140,172,192],"caption":[54],"that":[55,175,224],"includes":[56],"information":[57],"such":[58],"as":[59,82,84],"main":[61],"event,":[62],"object,":[63],"place,":[64],"action,":[65],"numbers,":[66],"and":[67,185],"time.":[68],"More":[69],"captions":[70,201,218],"automatically":[72],"generated":[73],"from":[74,157,202,219],"manual":[76],"annotation":[77],"take":[79],"into":[80],"account":[81],"much":[83],"possible":[85],"variation":[87],"describing":[89],"same":[91],"video.":[92,126],"Furthermore,":[93],"propose":[95],"captioning":[97],"model":[98,113],"provide":[104],"benchmark":[105],"results":[106,208],"is":[114,144,195],"based":[115],"on":[116,146],"encoder\u2013decoder":[118],"paradigm":[119],"two":[121],"configurations":[122],"encode":[124,167],"first":[128],"configuration":[129],"encodes":[130],"frames":[133],"independently":[134],"an":[136],"image":[137],"encoder.":[138],"Then,":[139],"temporal":[141,152],"attention":[142,179],"module":[143],"added":[145],"top":[148],"consider":[150],"dynamics":[153],"between":[154,186],"features":[155],"derived":[156],"frames.":[160,188],"second":[163],"configuration,":[164],"directly":[166],"input":[169],"using":[171],"encoder":[174],"employs":[176],"factorized":[177],"space\u2013time":[178],"capture":[181],"dependencies":[183],"within":[184],"For":[189],"generating":[190,217],"captions,":[191],"language":[193,238],"decoder":[194],"utilized":[196],"autoregressively":[198],"produce":[199],"visual":[204],"tokens.":[205],"experimental":[207],"under":[209],"different":[210],"evaluation":[211],"criteria":[212],"show":[213],"challenges":[215],"of":[216,227],"videos.":[221],"We":[222],"expect":[223],"introduction":[226],"will":[229],"open":[230],"interesting":[231],"new":[232],"research":[233],"avenues":[234],"integrating":[236],"natural":[237],"processing":[239],"(NLP)":[240],"understandings.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
