{"id":"https://openalex.org/W4403599514","doi":"https://doi.org/10.1109/picet60765.2024.10716063","title":"A Survey on Image Captioning Using Encoder-Decoder Based Deep Learning Models","display_name":"A Survey on Image Captioning Using Encoder-Decoder Based Deep Learning Models","publication_year":2024,"publication_date":"2024-05-03","ids":{"openalex":"https://openalex.org/W4403599514","doi":"https://doi.org/10.1109/picet60765.2024.10716063"},"language":"en","primary_location":{"id":"doi:10.1109/picet60765.2024.10716063","doi":"https://doi.org/10.1109/picet60765.2024.10716063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/picet60765.2024.10716063","pdf_url":null,"source":{"id":"https://openalex.org/S7407096418","display_name":"Parul International Conference on Engineering and Technology (PICET)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Parul International Conference on Engineering and Technology (PICET)","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/A5114345444","display_name":"Chauhan Harshil Narendrabhai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9694494","display_name":"Parul University","ror":"https://ror.org/024v3fg07","country_code":"IN","type":"education","lineage":["https://openalex.org/I9694494"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chauhan Harshil Narendrabhai","raw_affiliation_strings":["Computer Science and Engineering, Parul University,Vadodara-Gujarat,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Parul University,Vadodara-Gujarat,India","institution_ids":["https://openalex.org/I9694494"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015030022","display_name":"Chintan Bhupeshbhai Thacker","orcid":"https://orcid.org/0000-0002-2794-0030","observed_orcids":["https://orcid.org/0000-0002-2794-0030"]},"institutions":[{"id":"https://openalex.org/I9694494","display_name":"Parul University","ror":"https://ror.org/024v3fg07","country_code":"IN","type":"education","lineage":["https://openalex.org/I9694494"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chintan Bhupeshbhai Thacker","raw_affiliation_strings":["Computer Science and Engineering, Parul University,Vadodara-Gujarat,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Parul University,Vadodara-Gujarat,India","institution_ids":["https://openalex.org/I9694494"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9694494"],"apc_list":null,"apc_paid":null,"fwci":0.1401,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36534242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.9200000166893005},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.7099999785423279},{"id":"https://openalex.org/keywords/multimodal-deep-learning","display_name":"multimodal deep learning","score":0.5849999785423279}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.977205753326416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803188562393188},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6744470000267029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574036180973053},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5662747621536255},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5379524827003479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4610876441001892},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3880707621574402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3724343180656433},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/picet60765.2024.10716063","doi":"https://doi.org/10.1109/picet60765.2024.10716063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/picet60765.2024.10716063","pdf_url":null,"source":{"id":"https://openalex.org/S7407096418","display_name":"Parul International Conference on Engineering and Technology (PICET)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Parul International Conference on Engineering and Technology (PICET)","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":29,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1773149199","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2119775030","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2626778328","https://openalex.org/W2803259101","https://openalex.org/W2896348597","https://openalex.org/W2943885184","https://openalex.org/W2946349183","https://openalex.org/W2963770624","https://openalex.org/W2977970283","https://openalex.org/W3000154564","https://openalex.org/W3180663799","https://openalex.org/W4206617771","https://openalex.org/W4213189167","https://openalex.org/W4235388301","https://openalex.org/W4292595909","https://openalex.org/W4312219151","https://openalex.org/W4319594886","https://openalex.org/W4320016076","https://openalex.org/W4362566211","https://openalex.org/W4366492328","https://openalex.org/W4382240730","https://openalex.org/W4385214962","https://openalex.org/W4386607626"],"related_works":["https://openalex.org/W3169528989","https://openalex.org/W4415623671","https://openalex.org/W4399485860","https://openalex.org/W4412167519","https://openalex.org/W4414261787","https://openalex.org/W7218288199","https://openalex.org/W2961944450","https://openalex.org/W4386162736","https://openalex.org/W2896348597","https://openalex.org/W4289654392"],"abstract_inverted_index":{"The":[0],"intersection":[1],"of":[2,19,25,79,94],"computer":[3],"vision":[4],"and":[5,22,43,115],"natural":[6,47],"language":[7],"processing":[8],"has":[9],"seen":[10],"remarkable":[11],"progress,":[12],"particularly":[13],"in":[14,46,84],"deep":[15,57,99],"learning":[16,58],"techniques.":[17],"One":[18],"the":[20,61,116],"captivating":[21],"burgeoning":[23],"areas":[24],"research":[26],"stemming":[27],"from":[28,41,55,107],"this":[29],"advancement":[30],"is":[31],"image":[32,70,95,112],"caption":[33,71,96],"generation,":[34],"which":[35],"aims":[36],"to":[37,60,121],"automatically":[38],"extract":[39],"content":[40,105],"images":[42],"describe":[44],"it":[45],"language.":[48],"Image":[49],"captioning":[50,113],"techniques":[51,73],"have":[52,74],"evolved":[53],"significantly":[54],"classical":[56],"approaches":[59],"most":[62],"advanced":[63],"methods":[64],"available":[65,111],"today.":[66],"Presently,":[67],"Encoder-Decoder":[68],"based":[69],"generation":[72,97],"achieved":[75],"a":[76,91],"state-of-the-art":[77,123],"level":[78],"performance,":[80],"nearing":[81],"human-level":[82],"abilities":[83],"describing":[85],"visual":[86],"content.":[87],"This":[88],"paper":[89],"provides":[90],"comprehensive":[92],"overview":[93],"using":[98],"learning,":[100],"covering":[101],"various":[102],"methodologies":[103],"for":[104],"extraction":[106],"images,":[108],"challenges":[109],"encountered,":[110],"datasets,":[114],"diverse":[117],"evaluation":[118],"metrics":[119],"employed":[120],"assess":[122],"performance.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2024-10-22T00:00:00"}