{"id":"https://openalex.org/W4313306953","doi":"https://doi.org/10.1109/iccais56082.2022.9990458","title":"An Image Caption Model Based on the Scene Graph and Semantic Prior Network","display_name":"An Image Caption Model Based on the Scene Graph and Semantic Prior Network","publication_year":2022,"publication_date":"2022-11-21","ids":{"openalex":"https://openalex.org/W4313306953","doi":"https://doi.org/10.1109/iccais56082.2022.9990458"},"language":"en","primary_location":{"id":"doi:10.1109/iccais56082.2022.9990458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais56082.2022.9990458","pdf_url":null,"source":{"id":"https://openalex.org/S4363608617","display_name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100444142","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0001-9537-8767"},"institutions":[{"id":"https://openalex.org/I51622183","display_name":"Shaanxi University of Science and Technology","ror":"https://ror.org/034t3zs45","country_code":"CN","type":"education","lineage":["https://openalex.org/I51622183"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["Shaanxi University of Science and Technology,School of Electrical and Control Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shaanxi University of Science and Technology,School of Electrical and Control Engineering,Xi’an,China","institution_ids":["https://openalex.org/I51622183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016066447","display_name":"Nan Zhang","orcid":"https://orcid.org/0000-0002-6474-5031"},"institutions":[{"id":"https://openalex.org/I51622183","display_name":"Shaanxi University of Science and Technology","ror":"https://ror.org/034t3zs45","country_code":"CN","type":"education","lineage":["https://openalex.org/I51622183"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["Shaanxi University of Science and Technology,School of Electrical and Control Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shaanxi University of Science and Technology,School of Electrical and Control Engineering,Xi’an,China","institution_ids":["https://openalex.org/I51622183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641680","display_name":"Yaning Wang","orcid":"https://orcid.org/0000-0001-6258-8063"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaning Wang","raw_affiliation_strings":["Hangzhou Dianzi University,School of Automation,Hangzhou,China","School of Automation, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University,School of Automation,Hangzhou,China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"School of Automation, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102007824","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-6967-1668"},"institutions":[{"id":"https://openalex.org/I75920027","display_name":"Shaanxi University of Chinese Medicine","ror":"https://ror.org/021r98132","country_code":"CN","type":"education","lineage":["https://openalex.org/I75920027"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Di","raw_affiliation_strings":["Shaanxi University of Chinese Medicine,School of Basic Medical Science,Xianyang","School of Basic Medical Science, Shaanxi University of Chinese Medicine, Xianyang"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shaanxi University of Chinese Medicine,School of Basic Medical Science,Xianyang","institution_ids":["https://openalex.org/I75920027"]},{"raw_affiliation_string":"School of Basic Medical Science, Shaanxi University of Chinese Medicine, Xianyang","institution_ids":["https://openalex.org/I75920027"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0925,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42243549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"24","issue":null,"first_page":"60","last_page":"66"},"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":0.9977999925613403,"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":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.810045063495636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6600559949874878},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.6533401012420654},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5868826508522034},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5724070072174072},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5410735607147217},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5372021198272705},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5203192234039307},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.47618475556373596},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.454546183347702},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4200730621814728},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3789680302143097},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11266550421714783},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.08478718996047974},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.07744869589805603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810045063495636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6600559949874878},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6533401012420654},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5868826508522034},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5724070072174072},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5410735607147217},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5372021198272705},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5203192234039307},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.47618475556373596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.454546183347702},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4200730621814728},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3789680302143097},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11266550421714783},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.08478718996047974},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.07744869589805603},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccais56082.2022.9990458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais56082.2022.9990458","pdf_url":null,"source":{"id":"https://openalex.org/S4363608617","display_name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1969616664","https://openalex.org/W2302086703","https://openalex.org/W2549599535","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2912372357","https://openalex.org/W2913618459","https://openalex.org/W2946281912","https://openalex.org/W2952122856","https://openalex.org/W2955956881","https://openalex.org/W2963686907","https://openalex.org/W2992478697"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3123087812","https://openalex.org/W2379770539"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5,103],"image":[6,22,35,48,56,104],"caption":[7,23],"model":[8],"based":[9],"on":[10,29],"scene":[11,39,47,79],"graphs":[12],"and":[13,37],"semantic":[14,75,86],"priors":[15],"to":[16,68,73,89,101],"address":[17],"the":[18,33,38,46,51,59,62,70,91,99],"problem":[19],"of":[20],"traditional":[21],"models":[24],"that":[25],"are":[26,42,82,95],"overly":[27],"dependent":[28],"training":[30],"data.":[31],"First,":[32],"original":[34],"features":[36,41,49,81],"graph":[40,80],"fused":[43],"by":[44],"embedding":[45],"into":[50,98],"feature":[52],"space.":[53],"Second,":[54],"using":[55],"captions":[57],"from":[58],"existing":[60],"dataset,":[61],"sentence":[63],"reconstruction":[64],"task":[65],"is":[66],"used":[67],"train":[69],"memory":[71],"network":[72],"retain":[74],"prior":[76,87],"knowledge.":[77],"The":[78],"then":[83,96],"combined":[84],"with":[85],"information":[88],"reconstruct":[90],"new":[92],"features,":[93],"which":[94],"sent":[97],"Decoder":[100],"produce":[102],"caption.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}