{"id":"https://openalex.org/W4308234126","doi":"https://doi.org/10.1109/icip46576.2022.9897766","title":"VLCAP: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","display_name":"VLCAP: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308234126","doi":"https://doi.org/10.1109/icip46576.2022.9897766"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897766","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089288624","display_name":"Kashu Yamazaki","orcid":"https://orcid.org/0000-0001-6569-6860"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kashu Yamazaki","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA,72701"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA,72701","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059418368","display_name":"Sang Truong","orcid":"https://orcid.org/0000-0001-8069-9410"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sang Truong","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA,72701"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA,72701","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052144407","display_name":"Viet-Khoa Vo-Ho","orcid":"https://orcid.org/0000-0003-0277-7094"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khoa Vo","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA,72701"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA,72701","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110305534","display_name":"Michael T. Kidd","orcid":null},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Kidd","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA,72701"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA,72701","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030170704","display_name":"Chase Rainwater","orcid":"https://orcid.org/0009-0008-6899-0932"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chase Rainwater","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA,72701"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA,72701","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056226189","display_name":"Khoa Luu","orcid":"https://orcid.org/0000-0003-2104-0901"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khoa Luu","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA,72701"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA,72701","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023725893","display_name":"Ngan Le","orcid":"https://orcid.org/0000-0003-2571-0511"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ngan Le","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA,72701"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA,72701","institution_ids":["https://openalex.org/I78715868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5089288624"],"corresponding_institution_ids":["https://openalex.org/I78715868"],"apc_list":null,"apc_paid":null,"fwci":1.3793,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87459005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3656","last_page":"3661"},"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":0.9994000196456909,"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":0.9937000274658203,"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":0.8326255083084106},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7964394092559814},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.7872223258018494},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6669604182243347},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6211410760879517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6134516000747681},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5942316651344299},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5081560611724854},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4210960865020752},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4195794463157654},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3507421016693115},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13686108589172363},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07980605959892273}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8326255083084106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964394092559814},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.7872223258018494},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6669604182243347},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6211410760879517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6134516000747681},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5942316651344299},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5081560611724854},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4210960865020752},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4195794463157654},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3507421016693115},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13686108589172363},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07980605959892273},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897766","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1899504021","https://openalex.org/W1956340063","https://openalex.org/W1983364832","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2342662179","https://openalex.org/W2604178507","https://openalex.org/W2883910824","https://openalex.org/W2963351113","https://openalex.org/W2963524571","https://openalex.org/W2963811641","https://openalex.org/W2963916161","https://openalex.org/W2964110616","https://openalex.org/W2968101724","https://openalex.org/W2990503944","https://openalex.org/W3035237998","https://openalex.org/W3036900224","https://openalex.org/W3090449556","https://openalex.org/W3091069321","https://openalex.org/W3108655343","https://openalex.org/W3210264524","https://openalex.org/W3216280672","https://openalex.org/W4214663214","https://openalex.org/W4214926101","https://openalex.org/W6631636882","https://openalex.org/W6638545294","https://openalex.org/W6682631176","https://openalex.org/W6682864246","https://openalex.org/W6739901393","https://openalex.org/W6747866816","https://openalex.org/W6754278344","https://openalex.org/W6784333009","https://openalex.org/W6784761581","https://openalex.org/W6791353385","https://openalex.org/W6803283611","https://openalex.org/W6803913677"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2993670781","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,74],"leverage":[4],"the":[5,43],"human":[6,57],"perceiving":[7],"process,":[8],"that":[9,99],"involves":[10],"vision":[11,35],"and":[12,46,58,66,89,95,109],"language":[13,48],"interaction,":[14],"to":[15,37,50,76],"generate":[16],"a":[17,82],"coherent":[18],"paragraph":[19],"description":[20,54],"of":[21,30,42,55],"untrimmed":[22],"videos.":[23],"We":[24],"propose":[25,75],"vision-language":[26],"(VL)":[27],"features":[28],"consisting":[29],"two":[31],"modalities,":[32],"i.e.,":[33],"(i)":[34],"modality":[36,49],"capture":[38],"global":[39],"visual":[40,65],"content":[41],"entire":[44],"scene":[45,52],"(ii)":[47],"extract":[51],"elements":[53,68],"both":[56,107],"non-human":[59],"objects":[60],"(e.g.":[61,69],"animals,":[62],"vehicles,":[63],"etc),":[64],"non-visual":[67],"relations,":[70],"activities,":[71],"etc).":[72],"Furthermore,":[73],"train":[77],"our":[78,100],"proposed":[79],"VLCap":[80,101],"under":[81],"contrastive":[83],"learning":[84],"VL":[85],"loss.":[86],"The":[87],"experiments":[88],"ablation":[90],"studies":[91],"on":[92,106],"ActivityNet":[93],"Captions":[94],"YouCookII":[96],"datasets":[97],"show":[98],"outperforms":[102],"existing":[103],"SOTA":[104],"methods":[105],"accuracy":[108],"diversity":[110],"metrics.":[111],"Source":[112],"code:":[113],"https://github.com/UARK-AICV/VLCAP":[114]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}