{"id":"https://openalex.org/W4393183787","doi":"https://doi.org/10.1145/3634814.3634842","title":"Performance and Cost Balancing in Vision Transformer-Based Image Captioning","display_name":"Performance and Cost Balancing in Vision Transformer-Based Image Captioning","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4393183787","doi":"https://doi.org/10.1145/3634814.3634842"},"language":"en","primary_location":{"id":"doi:10.1145/3634814.3634842","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3634814.3634842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 4th Asia Service Sciences and Software Engineering Conference","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/A5022256954","display_name":"Y. F. Lyu","orcid":"https://orcid.org/0000-0001-7329-2225"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yan Lyu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7329-2225","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103166030","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0002-6839-4769"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4663-6739","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069452869","display_name":"Qiangfu Zhao","orcid":"https://orcid.org/0000-0003-3101-749X"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Qiangfu Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3101-749X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022256954"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20817781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.998199999332428,"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/T11439","display_name":"Video Analysis and Summarization","score":0.995199978351593,"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":0.9164811372756958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750220537185669},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6026433706283569},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.488104909658432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46576690673828125},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4206409752368927},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1632750928401947},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13202440738677979},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07306569814682007}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9164811372756958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750220537185669},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6026433706283569},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.488104909658432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46576690673828125},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4206409752368927},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1632750928401947},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13202440738677979},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07306569814682007}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3634814.3634842","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3634814.3634842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 4th Asia Service Sciences and Software Engineering Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1981276685","https://openalex.org/W2194775991","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2885013662","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2963084599","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3106925514","https://openalex.org/W3171007011","https://openalex.org/W4223525433","https://openalex.org/W4282968790","https://openalex.org/W4312810944","https://openalex.org/W4313131769","https://openalex.org/W4313156423","https://openalex.org/W4386071687","https://openalex.org/W6600018615","https://openalex.org/W6600168044","https://openalex.org/W6600175266","https://openalex.org/W6600228633","https://openalex.org/W6600424091","https://openalex.org/W6600547436","https://openalex.org/W6600828087","https://openalex.org/W6601939488","https://openalex.org/W6605755270","https://openalex.org/W6702248584","https://openalex.org/W6743198006"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4323777661","https://openalex.org/W4388184981","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Image":[0],"captioning":[1,67],"connects":[2],"computer":[3],"vision":[4],"and":[5,24,93,102,120,131],"natural":[6],"language":[7],"processing.":[8],"Many":[9],"deep":[10],"learning":[11],"models":[12,48],"have":[13],"been":[14,32],"proposed":[15],"for":[16,41,64],"solving":[17,65],"this":[18],"problem,":[19],"such":[20],"as":[21],"Transformer-based,":[22],"CLIP-based":[23],"Diffusion-based":[25],"models.":[26],"However,":[27],"the":[28,35,71,85,125],"primary":[29],"focus":[30],"has":[31],"on":[33,53],"increasing":[34],"accuracy":[36],"of":[37,73,79],"generating":[38],"human-like":[39],"descriptions":[40],"given":[42],"images,":[43],"leading":[44],"to":[45,111,127],"expensive":[46],"SOTA":[47],"that":[49,96],"cannot":[50],"be":[51],"implemented":[52],"computation-limited":[54],"devices.":[55],"For":[56],"better":[57,136],"performance,":[58],"we":[59,107],"propose":[60],"a":[61,80],"ViT-LSTM":[62],"model":[63,77,82,126],"image":[66],"tasks":[68],"by":[69],"addressing":[70],"challenge":[72],"long-range":[74],"dependencies.":[75],"Our":[76],"consists":[78],"ViT":[81],"pre-trained":[83],"using":[84],"ImageNet":[86],"21k":[87],"dataset,":[88],"which":[89],"captures":[90],"global":[91,103],"context,":[92],"an":[94],"LSTM":[95],"generates":[97],"captions":[98],"reflecting":[99],"both":[100],"local":[101,121,129],"visual":[104],"cues.":[105],"Additionally,":[106],"use":[108],"convolutional":[109],"layers":[110],"reduce":[112],"feature":[113],"map":[114],"dimensionality":[115],"while":[116],"preserving":[117],"spatial":[118],"relationships":[119,132],"patterns.":[122],"This":[123],"allows":[124],"understand":[128],"details":[130],"between":[133],"regions,":[134],"achieving":[135],"performance":[137],"with":[138],"less":[139],"computational":[140],"cost.":[141]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}