{"id":"https://openalex.org/W3128848149","doi":"https://doi.org/10.1109/aiccsa50499.2020.9316518","title":"Graph Self-Attention Network for Image Captioning","display_name":"Graph Self-Attention Network for Image Captioning","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3128848149","doi":"https://doi.org/10.1109/aiccsa50499.2020.9316518","mag":"3128848149"},"language":"en","primary_location":{"id":"doi:10.1109/aiccsa50499.2020.9316518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa50499.2020.9316518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/ACS 17th International Conference on Computer Systems and Applications (AICCSA)","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/A5010770511","display_name":"Qitong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qitong Zheng","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339106","display_name":"Yu\u2010Ping Wang","orcid":"https://orcid.org/0000-0001-9340-5864"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010770511"],"corresponding_institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0977,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43945352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9987999796867371,"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":0.9929999709129333,"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":0.8984494805335999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7987486124038696},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5742241144180298},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5374268889427185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5198110342025757},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48552870750427246},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.48220908641815186},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.4781152606010437},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44376495480537415},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.440903902053833},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4380882978439331},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43008846044540405},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4113858938217163},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3444180488586426},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33169281482696533},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32879477739334106},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07725435495376587}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8984494805335999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987486124038696},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5742241144180298},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5374268889427185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5198110342025757},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48552870750427246},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.48220908641815186},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.4781152606010437},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44376495480537415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.440903902053833},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4380882978439331},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43008846044540405},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4113858938217163},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3444180488586426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33169281482696533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32879477739334106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07725435495376587},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa50499.2020.9316518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa50499.2020.9316518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/ACS 17th International Conference on Computer Systems and Applications (AICCSA)","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":52,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W1987835821","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2149172860","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2560645892","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2807873315","https://openalex.org/W2809343047","https://openalex.org/W2890531016","https://openalex.org/W2890855364","https://openalex.org/W2896140001","https://openalex.org/W2911267749","https://openalex.org/W2945623882","https://openalex.org/W2952402334","https://openalex.org/W2962946486","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963403868","https://openalex.org/W2963858333","https://openalex.org/W2964121744","https://openalex.org/W2964189376","https://openalex.org/W2964253311","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6682086108","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6745537798","https://openalex.org/W6754498612"],"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/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3217195652"],"abstract_inverted_index":{"Most":[0],"state-of-the-art":[1],"methods":[2],"for":[3,67],"image":[4,68,132],"captioning":[5],"highly":[6],"depend":[7],"on":[8,12,26,159],"an":[9],"attention":[10,22,55,178],"mechanism":[11],"the":[13,17,37,41,45,80,86,95,99,103,115,123,126,131,160,164,185],"object":[14,82,104],"regions":[15,83,105],"within":[16],"encoder-decoder":[18],"framework.":[19],"Generally,":[20],"existing":[21],"models":[23],"are":[24,106,140,154],"based":[25],"simple":[27],"addition":[28],"or":[29],"multiplication":[30],"operations":[31],"and":[32,44,65,98,117,130,137,170,187],"may":[33],"not":[34,141],"fully":[35],"discover":[36],"complex":[38],"relationships":[39,124],"between":[40,125],"visual":[42,100,145],"features":[43,101],"target":[46,128],"words.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"a":[53,72],"novel":[54],"model,":[56],"named":[57],"graph":[58,63],"self-attention":[59,66,149],"(GSA),":[60],"that":[61,139,151,176],"incorporates":[62],"networks":[64],"captioning.":[69],"GSA":[70,120,147,165],"constructs":[71],"star-graph":[73],"model":[74,166],"to":[75,79,144,156,174,179],"dynamically":[76],"assign":[77],"weights":[78],"detected":[81],"when":[84],"generating":[85],"words":[87,153],"step-by-step.":[88],"The":[89,182],"central":[90],"node":[91],"is":[92,167],"represented":[93],"by":[94],"semantic":[96,161],"feature":[97],"of":[102,189],"used":[107],"as":[108],"edge":[109,118],"nodes.":[110],"Through":[111],"propagating":[112],"messages":[113],"among":[114],"center":[116],"nodes,":[119],"explicitly":[121],"captures":[122],"current":[127],"word":[129],"features.":[133,181],"To":[134],"generate":[135],"conjunctions":[136],"attributives":[138],"directly":[142],"related":[143],"information,":[146],"introduces":[148],"so":[150],"such":[152],"allowed":[155],"focus":[157],"more":[158],"information.":[162],"Moreover,":[163],"also":[168],"generic":[169],"can":[171],"be":[172],"applied":[173],"tasks":[175],"require":[177],"multiple":[180],"experiments":[183],"show":[184],"effectiveness":[186],"potentiality":[188],"our":[190],"proposed":[191],"GSA.":[192]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}