{"id":"https://openalex.org/W4401567443","doi":"https://doi.org/10.1109/access.2024.3443422","title":"Image and Video Captioning for Apparels Using Deep Learning","display_name":"Image and Video Captioning for Apparels Using Deep Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401567443","doi":"https://doi.org/10.1109/access.2024.3443422"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3443422","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3443422","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3443422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011938860","display_name":"Govind Agarwal","orcid":"https://orcid.org/0009-0008-4673-8090"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Govind Agarwal","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"raw_orcid":"https://orcid.org/0009-0008-4673-8090","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113333607","display_name":"Kritika Jindal","orcid":"https://orcid.org/0009-0001-1889-3316"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kritika Jindal","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"raw_orcid":"https://orcid.org/0009-0001-1889-3316","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007173988","display_name":"Abishi Chowdhury","orcid":"https://orcid.org/0000-0002-7991-7385"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abishi Chowdhury","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0002-7991-7385","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091495389","display_name":"Vishal Krishna Singh","orcid":"https://orcid.org/0000-0002-5438-579X"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vishal K. Singh","raw_affiliation_strings":["School of Computer Science and Electronics Engineering, University of Essex, Colchester Campus, Colchester, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5438-579X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronics Engineering, University of Essex, Colchester Campus, Colchester, U.K","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089476535","display_name":"Amrit Pal","orcid":"https://orcid.org/0000-0002-0555-9087"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amrit Pal","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0002-0555-9087","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.2227,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78699177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"113138","last_page":"113150"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9973999857902527,"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":0.991599977016449,"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":0.9202589988708496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433843612670898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5494307279586792},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4647720456123352},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46042442321777344},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3873607814311981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3568337559700012}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9202589988708496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433843612670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5494307279586792},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4647720456123352},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46042442321777344},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3873607814311981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3568337559700012}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2024.3443422","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3443422","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:repository.essex.ac.uk:39072","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ACCESS.2024.3443422","pdf_url":"https://repository.essex.ac.uk/39072/1/Image%20and%20Video%20Captioning%20for%20Apparels%20Using%20Deep%20Learning.pdf","source":{"id":"https://openalex.org/S4306401236","display_name":"Open Access at Essex (University of Essex)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I110002522","host_organization_name":"University of Essex","host_organization_lineage":["https://openalex.org/I110002522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:5675cc0189a140c3af9782435cb2e74c","is_oa":true,"landing_page_url":"https://doaj.org/article/5675cc0189a140c3af9782435cb2e74c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 113138-113150 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3443422","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3443422","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2962139653","https://openalex.org/W2990158537","https://openalex.org/W3095598260","https://openalex.org/W3124787982","https://openalex.org/W3134899271","https://openalex.org/W3173318157","https://openalex.org/W3173462351","https://openalex.org/W3214277435","https://openalex.org/W4220746441","https://openalex.org/W4308235787","https://openalex.org/W4320919514","https://openalex.org/W4362700943","https://openalex.org/W4378983079","https://openalex.org/W4388082674","https://openalex.org/W4388991679","https://openalex.org/W4389542638","https://openalex.org/W6797292187"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","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/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"In":[0,18,144],"the":[1,21,31,61,80,121,126,160,179,186,196],"rapidly":[2],"evolving":[3],"world":[4],"of":[5,20,23,33,63,71,82,169,193],"apparel,":[6,27],"writing":[7],"clear":[8],"and":[9,39,54,90,103,110,132,141,165],"interesting":[10],"product":[11],"descriptions":[12,25],"is":[13,149,176],"crucial":[14],"to":[15,43,47,52,134,162],"attract":[16],"customers.":[17],"light":[19],"importance":[22],"automated":[24],"for":[26,36,106,151,159,195],"this":[28],"work":[29],"explores":[30],"field":[32],"image":[34],"captioning":[35,45],"apparel":[37,57],"photos":[38,109,131],"expands":[40],"its":[41],"use":[42,81],"include":[44],"videos":[46,112,133],"enable":[48],"visually":[49],"impaired":[50],"people":[51],"access":[53],"understand":[55],"dynamic":[56],"content.":[58],"To":[59],"address":[60],"issue":[62],"diversity":[64],"in":[65],"datasets,":[66],"we":[67],"curated":[68],"a":[69,146,190],"collection":[70],"images":[72],"that":[73,113,137],"were":[74],"divided":[75],"into":[76],"26":[77],"classifications.":[78],"With":[79],"Convolutional":[83],"Neural":[84],"Network":[85],"(CNN)":[86],"architectures":[87],"like":[88],"ConvNeXtLarge":[89],"Long":[91],"Short-Term":[92],"Memory":[93],"(LSTM)":[94],"architectures,":[95],"our":[96],"suggested":[97,174],"system":[98],"can":[99],"automatically":[100],"provide":[101],"accurate":[102],"captivating":[104],"captions":[105,136],"both":[107,139],"still":[108],"moving":[111],"feature":[114],"clothing.":[115],"The":[116,173],"LSTM":[117],"network":[118],"smoothly":[119],"blends":[120],"visual":[122],"data":[123],"extracted":[124],"by":[125],"CNN":[127],"component":[128],"from":[129],"clothing":[130,170],"produce":[135],"are":[138],"semantically":[140],"linguistically":[142],"accurate.":[143],"addition,":[145],"YOLO":[147],"model":[148,161],"included":[150],"real-time":[152],"object":[153],"detection,":[154],"which":[155],"makes":[156],"it":[157],"possible":[158],"precisely":[163],"identify":[164],"track":[166],"several":[167],"articles":[168],"at":[171],"once.":[172],"architecture":[175],"evaluated":[177],"using":[178],"BLEU":[180],"score":[181,192],"performance":[182],"metric;":[183],"research":[184],"on":[185],"selected":[187],"dataset":[188],"yielded":[189],"BLEU-1":[191],"0.983":[194],"ConvNeXtLarge-based":[197],"model.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
