{"id":"https://openalex.org/W4416251165","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227251","title":"Deep Learning Based Captioning of Toys in a Smart Monitoring System","display_name":"Deep Learning Based Captioning of Toys in a Smart Monitoring System","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251165","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227251"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/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":true,"raw_author_name":"Kritika Jindal","raw_affiliation_strings":["Vellore Institute of Technology,School of Computer Science and Engineering,Chennai,India"],"affiliations":[{"raw_affiliation_string":"Vellore Institute of Technology,School of Computer Science and Engineering,Chennai,India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","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":["Vellore Institute of Technology,School of Computer Science and Engineering,Chennai,India"],"affiliations":[{"raw_affiliation_string":"Vellore Institute of Technology,School of Computer Science and Engineering,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":["Vellore Institute of Technology,School of Computer Science and Engineering,Chennai,India"],"affiliations":[{"raw_affiliation_string":"Vellore Institute of Technology,School of Computer Science and Engineering,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 Krishna Singh","raw_affiliation_strings":["University of Essex,School of Computer Science and Electronics Engineering,Colchester,UK"],"affiliations":[{"raw_affiliation_string":"University of Essex,School of Computer Science and Electronics Engineering,Colchester,UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066659045","display_name":"Rahmat Ullah","orcid":"https://orcid.org/0000-0001-5162-5164"},"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":"Rahmat Ullah","raw_affiliation_strings":["University of Essex,School of Computer Science and Electronics Engineering,Colchester,UK"],"affiliations":[{"raw_affiliation_string":"University of Essex,School of Computer Science and Electronics Engineering,Colchester,UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101956512","display_name":"Mujeeb Ur Rehman","orcid":"https://orcid.org/0000-0002-8154-6560"},"institutions":[{"id":"https://openalex.org/I66943878","display_name":"De Montfort University","ror":"https://ror.org/0312pnr83","country_code":"GB","type":"education","lineage":["https://openalex.org/I66943878"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mujeeb Ur Rehman","raw_affiliation_strings":["De Montfort University,School of Computer Science and Informatics, Institute of Artificial Intelligence,Leicester,UK"],"affiliations":[{"raw_affiliation_string":"De Montfort University,School of Computer Science and Informatics, Institute of Artificial Intelligence,Leicester,UK","institution_ids":["https://openalex.org/I66943878"]}]},{"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":["Vellore Institute of Technology,School of Computer Science and Engineering,Chennai,India"],"affiliations":[{"raw_affiliation_string":"Vellore Institute of Technology,School of Computer Science and Engineering,Chennai,India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113333607"],"corresponding_institution_ids":["https://openalex.org/I876193797"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34735323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9240999817848206,"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":0.9240999817848206,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.013299999758601189,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0038999998942017555,"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":0.9919999837875366},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7347999811172485},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7059999704360962},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5648000240325928},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5637000203132629},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4625999927520752}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9919999837875366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198000192642212},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7347999811172485},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7059999704360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6740999817848206},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5648000240325928},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36340001225471497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.essex.ac.uk:42194","is_oa":false,"landing_page_url":null,"pdf_url":null,"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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2302086703","https://openalex.org/W2941328520","https://openalex.org/W3033100359","https://openalex.org/W3033783894","https://openalex.org/W3095598260","https://openalex.org/W3134450428","https://openalex.org/W3206937028","https://openalex.org/W4308235787","https://openalex.org/W4312688202","https://openalex.org/W4321260695","https://openalex.org/W4386919726","https://openalex.org/W4391129684","https://openalex.org/W4392063026"],"related_works":[],"abstract_inverted_index":{"The":[0,140,185],"domain":[1],"of":[2,22,41,48,61,85,105,199],"image":[3,62,149],"captioning":[4,63,150],"has":[5],"attracted":[6],"increased":[7],"interest":[8],"in":[9,15,72,101],"recent":[10],"times":[11],"due":[12],"to":[13,53,57,94,132,152,158,165,180],"advancements":[14],"computer":[16],"vision":[17],"technology":[18],"and":[19,31,44,98,126,170,192],"the":[20,39,59,73,90,137,148,176,195,202],"incorporation":[21],"deep":[23,55],"learning":[24,56],"models,":[25],"specifically":[26],"convolutional":[27],"neural":[28,33],"networks":[29,34],"(CNNs)":[30],"recurrent":[32],"(RNNs).":[35],"These":[36,128],"developments":[37],"empower":[38],"creation":[40],"more":[42,173],"precise":[43],"contextually":[45],"comprehensive":[46,103],"descriptions":[47],"images.":[49],"This":[50],"research":[51,74],"aims":[52],"adapt":[54],"address":[58],"challenge":[60],"particularly":[64],"for":[65],"toys.":[66,86],"A":[67],"new":[68],"dataset":[69,96],"is":[70],"curated":[71],"by":[75],"sourcing":[76],"copyright":[77],"free":[78],"images":[79,91,106],"from":[80],"websites":[81],"featuring":[82],"diverse":[83],"categories":[84],"Through":[87],"augmentation":[88],"techniques,":[89],"are":[92],"enhanced":[93],"promote":[95],"generalization":[97],"robustness,":[99],"culminating":[100],"a":[102,172],"collection":[104],"spanning":[107],"distinct":[108],"classes,":[109],"each":[110],"meticulously":[111],"annotated":[112],"with":[113,189],"manually":[114],"crafted":[115],"captions.":[116],"Feature":[117],"extraction":[118],"was":[119,144,156,187],"performed":[120],"using":[121,182],"pre-trained":[122],"VGG16,":[123],"DenseNet201,":[124],"ResNet50,":[125],"ResNet101.":[127],"models":[129],"were":[130,178],"fine-tuned":[131],"achieve":[133],"optimal":[134],"performance":[135],"on":[136],"collected":[138],"dataset.":[139],"language":[141],"model":[142],"utilized":[143],"LSTM.":[145],"For":[146],"extending":[147],"methodology":[151],"video":[153,162],"captioning,":[154],"YOLO":[155],"implemented":[157],"detect":[159],"objects":[160],"within":[161],"frames.":[163],"Additionally,":[164],"assist":[166],"visually":[167],"impaired":[168],"children":[169],"create":[171],"inclusive":[174],"environment,":[175],"captions":[177],"translated":[179],"audio":[181],"Google":[183],"Text-to-Speech.":[184],"approach":[186],"evaluated":[188],"BLEU":[190],"score":[191,198],"ResNet101+LSTM":[193],"yielded":[194],"highest":[196],"BLEU-1":[197],"0.975825":[200],"outperforming":[201],"other":[203],"proposed":[204],"approaches.":[205]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-11-14T00:00:00"}