{"id":"https://openalex.org/W4206922148","doi":"https://doi.org/10.1109/icdm51629.2021.00201","title":"Joint Scence Network and Attention-Guided for Image Captioning","display_name":"Joint Scence Network and Attention-Guided for Image Captioning","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4206922148","doi":"https://doi.org/10.1109/icdm51629.2021.00201"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm51629.2021.00201","pdf_url":null,"source":{"id":"https://openalex.org/S4363608061","display_name":"2021 IEEE International Conference on Data Mining (ICDM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5069672411","display_name":"Dongming Zhou","orcid":"https://orcid.org/0000-0003-0139-9415"},"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":"Dongming 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":"middle","author":{"id":"https://openalex.org/A5101516308","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0002-7422-7297"},"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":"Jing Yang","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":"last","author":{"id":"https://openalex.org/A5102180180","display_name":"Yanping Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanping Tang","raw_affiliation_strings":["School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.194,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.531814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":72,"max":76},"biblio":{"volume":null,"issue":null,"first_page":"1535","last_page":"1540"},"is_retracted":false,"is_paratext":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":0.9961,"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":0.9836,"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":0.991447}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.991447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.58003336},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5482545},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5356599},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5292886},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.51888925},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48099124},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.474844},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4436435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37165272},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3474104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33298892},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10466617},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm51629.2021.00201","pdf_url":null,"source":{"id":"https://openalex.org/S4363608061","display_name":"2021 IEEE International Conference on Data Mining (ICDM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.69,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":null}],"datasets":[],"versions":[],"referenced_works_count":36,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2550553598","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2885013662","https://openalex.org/W2888039742","https://openalex.org/W2935791917","https://openalex.org/W2944965479","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2979739834","https://openalex.org/W2982553922","https://openalex.org/W2985051484","https://openalex.org/W2996421194","https://openalex.org/W2997026866","https://openalex.org/W2997226123","https://openalex.org/W2997591391","https://openalex.org/W3003478339","https://openalex.org/W3024534448","https://openalex.org/W3028688913","https://openalex.org/W3034984754","https://openalex.org/W3035323998","https://openalex.org/W3038571929","https://openalex.org/W3047875366","https://openalex.org/W3080813890","https://openalex.org/W3093309253","https://openalex.org/W3105136412","https://openalex.org/W3106925514","https://openalex.org/W3125154076","https://openalex.org/W3126207269","https://openalex.org/W3127216151","https://openalex.org/W3128826581","https://openalex.org/W3129050402","https://openalex.org/W3130531605","https://openalex.org/W3134428106","https://openalex.org/W3134991666"],"related_works":["https://openalex.org/W4388893791","https://openalex.org/W4290852288","https://openalex.org/W4283207562","https://openalex.org/W4210416330","https://openalex.org/W3217195652","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W2330246314"],"abstract_inverted_index":{"Image":[0],"captioning":[1,12,29,34,46],"is":[2,14,49,66,110],"an":[3,62],"interesting":[4],"and":[5,31,55,99,127,147],"challenging":[6],"task.":[7],"The":[8,151],"previously":[9],"established":[10],"image":[11,45,79,83],"approach":[13],"based":[15,50],"mainly":[16],"on":[17,51,144],"the":[18,32,69,76,94,114,117,122,130,133,138,142,145,156],"encoder-decoder":[19],"architecture,":[20],"but":[21],"it":[22],"suffers":[23],"from":[24,116],"problems":[25],"such":[26],"as":[27],"inaccurate":[28],"information,":[30],"generated":[33,123],"sentences":[35],"are":[36],"not":[37],"sufficiently":[38],"rich.":[39],"This":[40],"paper":[41],"proposes":[42],"a":[43,52,56,88,106],"novel":[44],"model":[47,101,143,158],"that":[48,155],"self-attention":[53,64],"network":[54,65,109],"scene":[57,118],"graph":[58,107],"relationship":[59],"network.":[60],"First,":[61],"improved":[63],"added":[67],"to":[68,74,92,112,120,128],"extraction":[70],"of":[71,78,96,132,141],"visual":[72,89,97],"features":[73,98],"evaluate":[75],"effectiveness":[77],"global":[80],"information":[81,119],"for":[82,102],"generation.":[84,104],"Then,":[85],"we":[86],"design":[87],"intensity":[90],"parameter":[91],"coordinate":[93],"strategies":[95],"language":[100],"word":[103],"Finally,":[105],"convolutional":[108],"designed":[111],"extract":[113],"relationships":[115],"render":[121],"caption":[124],"more":[125],"exciting":[126],"increase":[129],"accuracy":[131],"fine-grained":[134],"captioning.":[135],"We":[136],"demonstrated":[137],"satisfactory":[139],"performance":[140],"MS-COCO":[146],"Flickr":[148],"30K":[149],"datasets.":[150],"experimental":[152],"results":[153],"demonstrate":[154],"proposed":[157],"realizes":[159],"state-of-the-art":[160],"performance.":[161]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4206922148","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2024-12-06T22:33:41.866153","created_date":"2022-01-26"}