{"id":"https://openalex.org/W3162682897","doi":"https://doi.org/10.1109/iccmc51019.2021.9418347","title":"Image Captioning with Attention Based Model","display_name":"Image Captioning with Attention Based Model","publication_year":2021,"publication_date":"2021-04-08","ids":{"openalex":"https://openalex.org/W3162682897","doi":"https://doi.org/10.1109/iccmc51019.2021.9418347","mag":"3162682897"},"language":"en","primary_location":{"id":"doi:10.1109/iccmc51019.2021.9418347","doi":"https://doi.org/10.1109/iccmc51019.2021.9418347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccmc51019.2021.9418347","pdf_url":null,"source":{"id":"https://openalex.org/S4363607858","display_name":"International Conference on Computing Methodologies and Communication (ICCMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2021 5th International Conference on Computing Methodologies and Communication (ICCMC)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5048532397","display_name":"Sai Siddarth YV","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sai Siddarth YV","raw_affiliation_strings":["Information Technology, National Institute Of Technology Karnataka, Surathkal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology, National Institute Of Technology Karnataka, Surathkal, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028400166","display_name":"Yogesh Choubey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yogesh Choubey","raw_affiliation_strings":["Information Technology, National Institute Of Technology Karnataka, Surathkal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology, National Institute Of Technology Karnataka, Surathkal, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037889655","display_name":"Dinesh Naik","orcid":"https://orcid.org/0000-0002-8989-6282","observed_orcids":["https://orcid.org/0000-0002-8989-6282"]},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dinesh Naik","raw_affiliation_strings":["Information Technology, National Institute Of Technology Karnataka, Surathkal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology, National Institute Of Technology Karnataka, Surathkal, India","institution_ids":["https://openalex.org/I11880225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I11880225"],"apc_list":null,"apc_paid":null,"fwci":0.2311,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51220104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1051","last_page":"1055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.00039999998989515007,"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":9.999999747378752e-05,"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/image-captioning","display_name":"image captioning","score":1.0},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.9570000171661377},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.8140000104904175},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.6949999928474426},{"id":"https://openalex.org/keywords/image-description-generation","display_name":"image description generation","score":0.5649999976158142},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"natural language generation","score":0.4620000123977661},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9395692348480225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543648719787598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6847546100616455},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6110295653343201},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5876891613006592},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5723708271980286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5545647144317627},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5514487028121948},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5134957432746887},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4763217866420746},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46360835433006287},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.41778984665870667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3459731340408325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3303515911102295},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccmc51019.2021.9418347","doi":"https://doi.org/10.1109/iccmc51019.2021.9418347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccmc51019.2021.9418347","pdf_url":null,"source":{"id":"https://openalex.org/S4363607858","display_name":"International Conference on Computing Methodologies and Communication (ICCMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2021 5th International Conference on Computing Methodologies and Communication (ICCMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W77717277","https://openalex.org/W1590229582","https://openalex.org/W1836465849","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1902237438","https://openalex.org/W1987835821","https://openalex.org/W2141125852","https://openalex.org/W2253806798","https://openalex.org/W2402268235","https://openalex.org/W2580662672","https://openalex.org/W2768401321","https://openalex.org/W2890531016","https://openalex.org/W2949117887","https://openalex.org/W2951912364","https://openalex.org/W3010872046","https://openalex.org/W6635199058","https://openalex.org/W6775068190"],"related_works":["https://openalex.org/W1895577753","https://openalex.org/W2941328520","https://openalex.org/W3006628257","https://openalex.org/W3119789064","https://openalex.org/W6912673241","https://openalex.org/W4404384645","https://openalex.org/W2302086703","https://openalex.org/W4246918423","https://openalex.org/W7100911661","https://openalex.org/W2463955103"],"abstract_inverted_index":{"Defining":[0],"the":[1,25,35,52,60,63,67,70,77,82,90],"content":[2],"of":[3,69,76],"an":[4],"image":[5,53,91],"automatically":[6],"in":[7,38],"Artificial":[8],"Intelligence":[9],"is":[10,31,86],"basically":[11],"a":[12,28,46],"rudimentary":[13],"problem":[14],"that":[15,50],"connects":[16],"computer":[17,42],"vision":[18,43],"and":[19,41,81],"NLP":[20],"(Natural":[21],"Language":[22],"Processing).":[23],"In":[24],"proposed":[26],"work,":[27],"generative":[29],"model":[30,65],"presented":[32],"by":[33,96],"combining":[34],"recent":[36],"developments":[37],"machine":[39],"learning":[40],"based":[44],"on":[45,89,99],"deep":[47],"recurrent":[48],"architecture":[49],"describes":[51],"using":[54],"natural":[55],"language":[56,83],"phrases.":[57],"By":[58],"integrating":[59],"training":[61],"picture,":[62],"trained":[64],"maximizes":[66],"likelihood":[68],"target":[71],"description":[72],"sentence.":[73],"The":[74],"efficiency":[75],"model,":[78],"its":[79],"accuracy":[80],"it":[84],"learns":[85],"only":[87],"dependent":[88],"descriptions,":[92],"which":[93],"was":[94],"demonstrated":[95],"experiments":[97],"performed":[98],"several":[100],"datasets.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-05-24T00:00:00"}