{"id":"https://openalex.org/W7202261149","doi":"https://doi.org/10.5281/zenodo.21898695","title":"DenseNet201, LSTM Image Captioning: An Attention Gap Analysis","display_name":"DenseNet201, LSTM Image Captioning: An Attention Gap Analysis","publication_year":2026,"publication_date":"2026-08-12","ids":{"openalex":"https://openalex.org/W7202261149","doi":"https://doi.org/10.5281/zenodo.21898695"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.21898695","doi":"https://doi.org/10.5281/zenodo.21898695","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21898695","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.21898695","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146275518","display_name":"Md. Sohan Biswas","orcid":"https://orcid.org/0009-0000-5888-373X","observed_orcids":["https://orcid.org/0009-0000-5888-373X"]},"institutions":[{"id":"https://openalex.org/I4210152629","display_name":"Eastern University","ror":"https://ror.org/05e2ncr14","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210152629"]},{"id":"https://openalex.org/I905180023","display_name":"Eastern University","ror":"https://ror.org/04txhk134","country_code":"US","type":"education","lineage":["https://openalex.org/I905180023"]}],"countries":["BD","US"],"is_corresponding":true,"raw_author_name":"Biswas, Md. Sohan","raw_affiliation_strings":["Eastern University"],"raw_orcid":"https://orcid.org/0009-0000-5888-373X","affiliations":[{"raw_affiliation_string":"Eastern University","institution_ids":["https://openalex.org/I4210152629","https://openalex.org/I905180023"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5146275518"],"corresponding_institution_ids":["https://openalex.org/I4210152629","https://openalex.org/I905180023"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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":0.9980000257492065},{"id":"https://openalex.org/keywords/densenet-201","display_name":"DenseNet201","score":0.9919999837875366},{"id":"https://openalex.org/keywords/lstm-decoder","display_name":"LSTM decoder","score":0.8100000023841858},{"id":"https://openalex.org/keywords/flickr8k","display_name":"Flickr8k","score":0.8259999752044678},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.6299999952316284},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.8669999837875366},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.6209999918937683}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9090999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350999712944031},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6284999847412109},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5799000263214111},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5281999707221985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5009999871253967},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.27219998836517334},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.26030001044273376}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.21898695","doi":"https://doi.org/10.5281/zenodo.21898695","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21898695","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"},{"id":"doi:10.5281/zenodo.21898696","doi":"https://doi.org/10.5281/zenodo.21898696","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21898696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.5281/zenodo.21898695","doi":"https://doi.org/10.5281/zenodo.21898695","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21898695","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7130844627","https://openalex.org/W4413431958","https://openalex.org/W7147505176","https://openalex.org/W2991914565","https://openalex.org/W3129050402","https://openalex.org/W3195083812","https://openalex.org/W6903701013","https://openalex.org/W2971597072","https://openalex.org/W4410566138","https://openalex.org/W3010982166"],"abstract_inverted_index":{"This":[0,89],"paper":[1,90,170],"documents":[2],"the":[3,26,33,92,103,109,118,178],"design,":[4],"implementation,":[5],"and":[6,19,38,48,59,107,124,134,162,187],"evaluation":[7,190],"of":[8,35,65,152],"an":[9,20],"image":[10],"captioning":[11,30],"system":[12],"built":[13],"on":[14,25,74],"a":[15,62,75,82,86,129,141,167,173],"DenseNet201":[16],"convolutional":[17],"encoder":[18,123],"LSTM-based":[21],"language":[22,40,49],"decoder,":[23],"trained":[24],"Flickr8k":[27,70],"dataset.":[28],"Image":[29],"sits":[31],"at":[32],"intersection":[34],"computer":[36],"vision":[37],"natural":[39],"processing,":[41],"requiring":[42],"joint":[43],"reasoning":[44],"over":[45],"visual":[46,120],"content":[47],"generation.":[50],"While":[51],"recent":[52],"literature":[53],"has":[54],"moved":[55],"decisively":[56],"toward":[57],"attention-based":[58],"transformer":[60,185],"decoders,":[61,186],"substantial":[63],"share":[64],"published":[66],"implementations":[67],"that":[68,96],"use":[69],"continue":[71],"to":[72],"rely":[73],"nonattention":[76],"CNN-LSTM":[77],"merge":[78],"architecture,":[79],"either":[80],"as":[81,85,166],"baseline":[83],"or":[84],"complete":[87],"system.":[88],"situates":[91],"present":[93],"implementation":[94,161],"within":[95],"literature,":[97],"reviews":[98],"closely":[99],"related":[100],"work":[101],"using":[102],"same":[104],"encoder-decoder":[105,198],"pattern,":[106],"identifies":[108],"specific":[110],"architectural":[111],"property":[112],"responsible":[113],"for":[114,176],"its":[115],"observed":[116],"limitations:":[117],"fixed-length":[119],"bottleneck":[121],"between":[122,132],"decoder.":[125],"Training":[126],"curves":[127],"show":[128],"widening":[130],"gap":[131],"training":[133,183],"validation":[135],"loss":[136],"consistent":[137],"with":[138,172],"overfitting":[139],"in":[140,150,159],"small-data,":[142],"non-attention":[143],"regime.":[144],"Qualitative":[145],"caption":[146],"outputs":[147],"are":[148,163],"reviewed":[149],"place":[151],"quantitative":[153],"metrics,":[154],"which":[155],"were":[156],"not":[157],"computed":[158],"this":[160],"noted":[164],"explicitly":[165],"limitation.":[168],"The":[169],"closes":[171],"literature-grounded":[174],"roadmap":[175],"extending":[177],"system:":[179],"attention":[180],"mechanisms,":[181],"larger":[182],"corpora,":[184],"standard":[188],"n-gram":[189],"metrics.Keyword:":[191],"image-captioning":[192],"deep-learning":[193],"computer-vision":[194],"nlp":[195],"densenet201":[196],"lstm":[197],"flickr8k":[199],"tensorflow":[200],"keras":[201],"cnn-lstm":[202],"attention-mechanism":[203],"transfer-learning":[204],"Source":[205],"Code:GitHub:":[206],"https://github.com/sohanbiswas-ds/Brain-Tumor-detection-using-transfer-learning-VGG-16-":[207],"Author:":[208],"Md.":[209],"Sohan":[210],"BiswasORCID:":[211],"0009-0000-5888-373X":[212]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-13T00:00:00"}