{"id":"https://openalex.org/W4415124578","doi":"https://doi.org/10.1109/icmlt65785.2025.11193326","title":"Multi Head Attention-based Visual Content Analysis","display_name":"Multi Head Attention-based Visual Content Analysis","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4415124578","doi":"https://doi.org/10.1109/icmlt65785.2025.11193326"},"language":"en","primary_location":{"id":"doi:10.1109/icmlt65785.2025.11193326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlt65785.2025.11193326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5023412948","display_name":"M J Raghavendra","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghavendra M J","raw_affiliation_strings":["PES University,Department of ECE,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of ECE,Bangalore,India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111631300","display_name":"Surya Ramesh","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Surya Ramesh","raw_affiliation_strings":["PES University,Department of ECE,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of ECE,Bangalore,India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119975417","display_name":"Sriraj Ghali","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriraj Ghali","raw_affiliation_strings":["PES University,Department of ECE,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of ECE,Bangalore,India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tejas Rajesh","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tejas Rajesh","raw_affiliation_strings":["PES University,Department of ECE,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of ECE,Bangalore,India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026136357","display_name":"B Krupa","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"B Niranjana Krupa","raw_affiliation_strings":["PES University,Department of ECE,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University,Department of ECE,Bangalore,India","institution_ids":["https://openalex.org/I196608512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196608512"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30468932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9045000076293945,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9045000076293945,"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":0.9835000038146973},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.642799973487854},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5676000118255615},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4438999891281128},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4058000147342682},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.391400009393692},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3887999951839447}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9835000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7178000211715698},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.642799973487854},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5242000222206116},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3887999951839447},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlt65785.2025.11193326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlt65785.2025.11193326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1905882502","https://openalex.org/W2066134726","https://openalex.org/W2101105183","https://openalex.org/W2143177362","https://openalex.org/W2220981600","https://openalex.org/W3003478339","https://openalex.org/W3094526033","https://openalex.org/W3118655135","https://openalex.org/W3154766321","https://openalex.org/W3192652975","https://openalex.org/W3194346615","https://openalex.org/W4226397058","https://openalex.org/W4226411404","https://openalex.org/W4285814624","https://openalex.org/W4296197540","https://openalex.org/W4385245566","https://openalex.org/W4388046514","https://openalex.org/W4389724702","https://openalex.org/W4390873420","https://openalex.org/W4392210003","https://openalex.org/W4396983120","https://openalex.org/W4400233252","https://openalex.org/W4400490386","https://openalex.org/W4401803531"],"related_works":[],"abstract_inverted_index":{"The":[0,95,112],"purpose":[1],"of":[2,13,53,119],"image":[3,16,60,70],"captioning":[4,17,36,61],"(IC)":[5],"is":[6,31,67],"to":[7,38,42,45,87,92],"provide":[8,46],"an":[9,59],"accurate":[10],"textual":[11,51],"description":[12],"images.":[14,55],"Traditional":[15],"models":[18,37],"are":[19,75,85,98],"based":[20,104],"on":[21,105,121],"advanced":[22],"signal":[23],"processing":[24],"and":[25,80],"convolutional":[26],"neural":[27],"networks.":[28],"However,":[29],"there":[30],"a":[32,88,101,116],"demand":[33],"for":[34],"the":[35,43,54,78,122],"pay":[39],"higher":[40],"attention":[41],"images":[44],"richer,":[47],"or":[48],"more":[49],"dense,":[50],"descriptions":[52],"In":[56],"this":[57],"paper,":[58],"model":[62],"with":[63],"Multi-Head":[64],"Attention":[65],"(MHA)":[66],"proposed.":[68],"Here,":[69],"features":[71,84],"extracted":[72],"using":[73,77,100],"EfficientNetB0":[74],"enhanced":[76],"Squeeze":[79],"Excitation":[81],"network.":[82],"Further,":[83],"applied":[86],"modified":[89],"transformer-based":[90],"encoder-decoder":[91],"generate":[93],"captions.":[94,111],"obtained":[96],"captions":[97],"refined":[99],"refinement":[102],"network":[103],"T5-architecture,":[106],"thus":[107],"providing":[108],"grammatically":[109],"correct":[110],"proposed":[113],"approach":[114],"achieves":[115],"BLEU-4":[117],"score":[118],"24.83":[120],"Flickr8K":[123],"dataset.":[124]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-14T00:00:00"}
