{"id":"https://openalex.org/W4308234208","doi":"https://doi.org/10.1109/icip46576.2022.9897559","title":"Evaluation of Automatically Generated Video Captions Using Vision and Language Models","display_name":"Evaluation of Automatically Generated Video Captions Using Vision and Language Models","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308234208","doi":"https://doi.org/10.1109/icip46576.2022.9897559"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897559","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doras.dcu.ie/27890/1/ICIP.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068004697","display_name":"Luis Lebron","orcid":"https://orcid.org/0000-0002-3230-3589"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Luis Lebron","raw_affiliation_strings":["Dublin City University (DCU),Insight SFI Research Centre for Data Analytics","Insight SFI Research Centre for Data Analytics, Dublin City University (DCU)"],"affiliations":[{"raw_affiliation_string":"Dublin City University (DCU),Insight SFI Research Centre for Data Analytics","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight SFI Research Centre for Data Analytics, Dublin City University (DCU)","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020500064","display_name":"Yvette Graham","orcid":"https://orcid.org/0000-0001-6741-4855"},"institutions":[{"id":"https://openalex.org/I204442077","display_name":"Trinity College","ror":"https://ror.org/019dhar59","country_code":"CA","type":"education","lineage":["https://openalex.org/I204442077"]},{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["CA","IE"],"is_corresponding":false,"raw_author_name":"Yvette Graham","raw_affiliation_strings":["Trinity College Dublin,School of Computer Science and Statistics","School of Computer Science and Statistics, Trinity College Dublin"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin,School of Computer Science and Statistics","institution_ids":["https://openalex.org/I204442077","https://openalex.org/I205274468"]},{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106498523","display_name":"Noel E. O\u2019Connor","orcid":"https://orcid.org/0000-0002-4033-9135"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Noel E. O'Connor","raw_affiliation_strings":["Dublin City University (DCU),Insight SFI Research Centre for Data Analytics","Insight SFI Research Centre for Data Analytics, Dublin City University (DCU)"],"affiliations":[{"raw_affiliation_string":"Dublin City University (DCU),Insight SFI Research Centre for Data Analytics","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight SFI Research Centre for Data Analytics, Dublin City University (DCU)","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073924795","display_name":"Kevin McGuinness","orcid":"https://orcid.org/0000-0003-1336-6477"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kevin McGuinness","raw_affiliation_strings":["Dublin City University (DCU),Insight SFI Research Centre for Data Analytics","Insight SFI Research Centre for Data Analytics, Dublin City University (DCU)"],"affiliations":[{"raw_affiliation_string":"Dublin City University (DCU),Insight SFI Research Centre for Data Analytics","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight SFI Research Centre for Data Analytics, Dublin City University (DCU)","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068004697"],"corresponding_institution_ids":["https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":0.0599,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28604021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2416","last_page":"2420"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9970999956130981,"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":0.9909999966621399,"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":0.9195683002471924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8607997894287109},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6533865928649902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6500519514083862},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6001757383346558},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.542124330997467},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.491567462682724},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48456135392189026},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4811450242996216},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3931003510951996},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37531691789627075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3265179991722107}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9195683002471924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607997894287109},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6533865928649902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6500519514083862},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6001757383346558},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.542124330997467},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.491567462682724},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48456135392189026},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4811450242996216},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3931003510951996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37531691789627075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3265179991722107},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip46576.2022.9897559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897559","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:doras.dcu.ie:27890","is_oa":true,"landing_page_url":"http://doras.dcu.ie/27890/","pdf_url":"http://doras.dcu.ie/27890/1/ICIP.pdf","source":{"id":"https://openalex.org/S4306401511","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"  Lebron Casas, Luis ORCID: 0000-0002-3230-3589 &lt;https://orcid.org/0000-0002-3230-3589&gt;, Graham, Yvette, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 &lt;https://orcid.org/0000-0002-4033-9135&gt; and McGuinness, Kevin ORCID: 0000-0003-1336-6477 &lt;https://orcid.org/0000-0003-1336-6477&gt;  (2022) Evaluation of automatically generated video captions using vision and language models.  In: IEEE International Conference on Image Processing (ICIP), 16-19 Oct 2022, Bordeaux, France.  ISBN 978-1-6654-9620-9     ","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:doras.dcu.ie:27890","is_oa":true,"landing_page_url":"http://doras.dcu.ie/27890/","pdf_url":"http://doras.dcu.ie/27890/1/ICIP.pdf","source":{"id":"https://openalex.org/S4306401511","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"  Lebron Casas, Luis ORCID: 0000-0002-3230-3589 &lt;https://orcid.org/0000-0002-3230-3589&gt;, Graham, Yvette, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 &lt;https://orcid.org/0000-0002-4033-9135&gt; and McGuinness, Kevin ORCID: 0000-0003-1336-6477 &lt;https://orcid.org/0000-0003-1336-6477&gt;  (2022) Evaluation of automatically generated video captions using vision and language models.  In: IEEE International Conference on Image Processing (ICIP), 16-19 Oct 2022, Bordeaux, France.  ISBN 978-1-6654-9620-9     ","raw_type":"Conference or Workshop Item"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320321056","display_name":"Irish Research Council","ror":"https://ror.org/051xex213"},{"id":"https://openalex.org/F4320331354","display_name":"Insight SFI Research Centre for Data Analytics","ror":null},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4308234208.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1773149199","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W1967320885","https://openalex.org/W2150593711","https://openalex.org/W2154652894","https://openalex.org/W2226480163","https://openalex.org/W2506483933","https://openalex.org/W2600463316","https://openalex.org/W2896457183","https://openalex.org/W2936695845","https://openalex.org/W2964042428","https://openalex.org/W2970858040","https://openalex.org/W3090449556","https://openalex.org/W3153469116","https://openalex.org/W3166396011","https://openalex.org/W3205071530","https://openalex.org/W4234731922","https://openalex.org/W4286897344","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6688953515","https://openalex.org/W6755207826","https://openalex.org/W6761205521","https://openalex.org/W6791353385","https://openalex.org/W6809579393","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4388002133","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Vision":[0],"and":[1,46,82,135],"language":[2],"models":[3,51,68],"are":[4],"easily":[5],"transferred":[6],"to":[7,16,31,85,97,102,132],"other":[8],"tasks.":[9],"In":[10,61],"particular,":[11],"they":[12],"have":[13],"been":[14],"demonstrated":[15],"work":[17],"well":[18],"in":[19,116],"the":[20,35,44,47,75,104,117,123,129,137],"evaluation":[21,81,138],"of":[22,58,77],"automatic":[23],"image":[24,45],"captioning.":[25],"This":[26],"has":[27],"made":[28],"it":[29],"possible":[30],"evaluate":[32],"systems":[33],"without":[34],"need":[36],"for":[37,69],"references":[38],"or":[39],"additional":[40],"information":[41],"apart":[42],"from":[43,88],"caption.":[48],"However,":[49],"these":[50,67],"do":[52],"not":[53],"provide":[54],"a":[55,99],"straightforward":[56],"way":[57],"evaluating":[59],"videos.":[60],"this":[62],"paper,":[63],"we":[64,126],"propose":[65,127],"using":[66,94],"video":[70],"captioning":[71],"evaluation.":[72],"We":[73],"explore":[74],"use":[76],"both":[78],"single":[79],"image-based":[80],"different":[83],"methods":[84,96],"include":[86],"data":[87],"multiple":[89],"frames.":[90],"Experiments":[91],"demonstrate":[92],"that":[93],"clustering":[95],"select":[98],"few":[100],"frames":[101],"compute":[103],"final":[105],"score":[106],"gives":[107],"an":[108],"excellent":[109],"correlation":[110],"with":[111],"human":[112,118,130],"judgment.":[113],"The":[114],"bias":[115],"annotations":[119],"can":[120],"also":[121],"influence":[122],"metric,":[124],"so":[125],"filtering":[128],"assessments":[131],"discard":[133],"outliers":[134],"improve":[136],"process.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
