{"id":"https://openalex.org/W4306952682","doi":"https://doi.org/10.1145/3538641.3561491","title":"End-to-end image captioning based on reduced feature maps of deep learners pre-trained for object detection","display_name":"End-to-end image captioning based on reduced feature maps of deep learners pre-trained for object detection","publication_year":2022,"publication_date":"2022-10-03","ids":{"openalex":"https://openalex.org/W4306952682","doi":"https://doi.org/10.1145/3538641.3561491"},"language":"en","primary_location":{"id":"doi:10.1145/3538641.3561491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3538641.3561491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Research in Adaptive and Convergent Systems","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/A5108641878","display_name":"Yan Lyu","orcid":null},"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":["The University of Aizu, Aizu-Wakamatsu, Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Aizu, Aizu-Wakamatsu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","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":["The University of Aizu, Aizu-Wakamatsu, Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Aizu, Aizu-Wakamatsu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119272033","display_name":"Yong Liu","orcid":"https://orcid.org/0009-0007-7205-2909"},"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":["The University of Aizu, Aizu-Wakamatsu, Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Aizu, Aizu-Wakamatsu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108641878"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.1019,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39714401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"76"},"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":0.9929999709129333,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9230162501335144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8469864130020142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7039294242858887},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6989902257919312},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6881375908851624},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6214848160743713},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6131702661514282},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5268437266349792},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5109085440635681},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5017077922821045},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4808505177497864},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.47801148891448975},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4600626528263092},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4527469277381897},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4482387602329254},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42194581031799316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3912133276462555},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33626997470855713},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.059167444705963135}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9230162501335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8469864130020142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7039294242858887},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6989902257919312},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6881375908851624},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6214848160743713},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6131702661514282},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5268437266349792},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5109085440635681},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5017077922821045},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4808505177497864},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.47801148891448975},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4600626528263092},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4527469277381897},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4482387602329254},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42194581031799316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3912133276462555},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33626997470855713},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.059167444705963135},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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:10.1145/3538641.3561491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3538641.3561491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W2097117768","https://openalex.org/W2185175083","https://openalex.org/W2560920409","https://openalex.org/W2753000712","https://openalex.org/W2896348597","https://openalex.org/W2945222541","https://openalex.org/W2945563815","https://openalex.org/W2963037989","https://openalex.org/W2964018924","https://openalex.org/W2997200074","https://openalex.org/W3174377922"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2275988210","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Image":[0],"caption":[1,43],"generation":[2,44,86],"is":[3,64,75,94],"a":[4,8,13],"task":[5],"to":[6,66,77,87],"generate":[7],"descriptive":[9],"sentence":[10],"automatically":[11],"for":[12,82],"given":[14],"image":[15,18,42],"which":[16],"combines":[17],"process":[19,23,31],"and":[20,36,57],"natural":[21,83],"language":[22,84],"together.":[24],"Most":[25],"existing":[26,98],"approaches":[27],"divided":[28],"the":[29,48,53,58,73,79,89],"whole":[30],"into":[32,69],"two":[33],"parts,":[34],"encoding":[35],"decoding.":[37],"Our":[38],"research":[39],"proposed":[40,92],"an":[41],"method":[45,93],"based":[46],"on":[47],"most":[49],"popular":[50],"architecture":[51],"with":[52,96],"YOLO":[54],"as":[55,60],"encoder":[56,63],"LSTM":[59],"decoder.":[61],"The":[62,91],"used":[65,76],"encode":[67],"images":[68],"feature":[70,80],"vectors":[71],"while":[72],"decoder":[74],"decode":[78],"maps":[81],"sentences":[85],"describe":[88],"images.":[90],"compared":[95],"other":[97],"methods.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}