{"id":"https://openalex.org/W2978125519","doi":"https://doi.org/10.1109/ijcnn.2019.8852118","title":"Image Captioning Based On Sentence-Level And Word-Level Attention","display_name":"Image Captioning Based On Sentence-Level And Word-Level Attention","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978125519","doi":"https://doi.org/10.1109/ijcnn.2019.8852118","mag":"2978125519"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5009693444","display_name":"Haiyang Wei","orcid":"https://orcid.org/0000-0002-0145-9353"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haiyang Wei","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":"https://orcid.org/0000-0002-5313-6134"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Li","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016469515","display_name":"Canlong Zhang","orcid":"https://orcid.org/0000-0003-4375-1405"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Canlong Zhang","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102719463","display_name":"Tao Zhou","orcid":"https://orcid.org/0000-0002-1220-5068"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhou","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102106766","display_name":"Quan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Quan","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009693444"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.6073,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.72655102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9890999794006348,"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":0.9807000160217285,"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":0.9856239557266235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8532981872558594},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7120200395584106},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6922873854637146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6282562017440796},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.597683310508728},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5642074942588806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47224730253219604},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4600526988506317},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43248164653778076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3951713442802429},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.065325528383255}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9856239557266235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8532981872558594},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7120200395584106},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6922873854637146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6282562017440796},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.597683310508728},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5642074942588806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47224730253219604},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4600526988506317},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43248164653778076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3951713442802429},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.065325528383255},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1811254738","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2119717200","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2176263492","https://openalex.org/W2220981600","https://openalex.org/W2267186426","https://openalex.org/W2302086703","https://openalex.org/W2407521645","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2564898401","https://openalex.org/W2575842049","https://openalex.org/W2607151106","https://openalex.org/W2737766105","https://openalex.org/W2798858969","https://openalex.org/W2804078698","https://openalex.org/W2949376505","https://openalex.org/W2950800384","https://openalex.org/W2962706528","https://openalex.org/W2963084599","https://openalex.org/W2963248296","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2964268978","https://openalex.org/W2964308564","https://openalex.org/W3103022576","https://openalex.org/W4295253143","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6685322675","https://openalex.org/W6714138976","https://openalex.org/W6727862155","https://openalex.org/W6739901393","https://openalex.org/W6740863234","https://openalex.org/W6751097180","https://openalex.org/W6752378368","https://openalex.org/W6763509872","https://openalex.org/W6898505805"],"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/W2949522393","https://openalex.org/W3217195652"],"abstract_inverted_index":{"Existing":[0],"attention":[1,10,14,18,49,62,70],"models":[2],"of":[3,87,110],"image":[4,22,31,39,139],"captioning":[5,32,140],"typically":[6],"extract":[7,47],"only":[8],"word-level":[9,69],"information.":[11],"i.e.,":[12],"the":[13,21,25,84,88,107,111],"mechanism":[15,45],"extracts":[16],"local":[17],"information":[19,50,71,94],"from":[20,55],"to":[23,37,72,90,102,105],"generate":[24,129],"current":[26],"word.":[27],"We":[28,78],"propose":[29,59],"an":[30],"approach":[33,127],"based":[34],"on":[35,118,142],"self-attention":[36,44],"utilize":[38],"features":[40],"more":[41,130],"effectively.":[42],"The":[43,64,121],"can":[46,128],"sentence-level":[48,67],"with":[51],"richer":[52,133],"visual":[53],"representation":[54],"images.":[56],"Furthermore,":[57],"we":[58,98,114],"a":[60],"double":[61],"model.":[63,112],"model":[65,89,117],"combines":[66],"and":[68,81,93,97,132,135],"better":[73],"simulate":[74],"human":[75],"perception":[76],"system.":[77],"implement":[79],"supervision":[80],"optimization":[82],"in":[83],"intermediate":[85],"stage":[86],"solve":[91],"over-fitting":[92],"interference":[95],"problems,":[96],"apply":[99],"reinforcement":[100],"learning":[101],"two-stage":[103],"training":[104],"optimize":[106],"evaluation":[108,144],"metrics":[109],"Finally,":[113],"evaluate":[115],"our":[116,126],"MSCOCO":[119],"dataset.":[120],"experimental":[122],"results":[123],"show":[124],"that":[125],"accurate":[131],"captions,":[134],"outperforms":[136],"many":[137],"state-of-the-art":[138],"approaches":[141],"various":[143],"metrics.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}