{"id":"https://openalex.org/W4308236835","doi":"https://doi.org/10.1109/icip46576.2022.9897810","title":"CSTNET: Enhancing Global-To-Local Interactions for Image Captioning","display_name":"CSTNET: Enhancing Global-To-Local Interactions for Image Captioning","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236835","doi":"https://doi.org/10.1109/icip46576.2022.9897810"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897810","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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 IEEE International Conference on Image Processing (ICIP)","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/A5088751649","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0001-6252-1061"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Yang","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi'an,China","School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi'an,China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346965","display_name":"Ying Wang","orcid":"https://orcid.org/0000-0001-5172-4736"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi'an,China","School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi'an,China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078343966","display_name":"Haishun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haishun Chen","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi'an,China","School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi'an,China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100642867","display_name":"Jie Li","orcid":"https://orcid.org/0000-0001-7950-4233"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi'an,China","School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi'an,China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088751649"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10708684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"1861","last_page":"1865"},"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":0.9944999814033508,"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":0.9944999814033508,"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":0.9856981039047241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7965556383132935},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6492346525192261},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5776163339614868},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5426332354545593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5364969372749329},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.49498671293258667},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4558528661727905},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36550819873809814},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06528204679489136},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06107005476951599}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9856981039047241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965556383132935},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6492346525192261},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5776163339614868},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5426332354545593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5364969372749329},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.49498671293258667},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4558528661727905},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36550819873809814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06528204679489136},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06107005476951599},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897810","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.41999998688697815,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W2064675550","https://openalex.org/W2463955103","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2963084599","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3094502228","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3196091473","https://openalex.org/W4288329833","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6763643401","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"aims":[2],"to":[3,55],"generate":[4],"descriptions":[5],"of":[6,99],"images,":[7],"which":[8,70],"requires":[9],"capturing":[10],"complex":[11],"interactions":[12],"between":[13],"local":[14],"regions":[15],"and":[16,77],"global":[17,23,58,75],"context":[18,24,76],"within":[19],"image.":[20],"However,":[21],"effective":[22],"modeling":[25],"from":[26],"image":[27,100],"remains":[28],"a":[29,63],"challenging":[30],"research":[31],"topic.":[32],"Existing":[33],"approaches":[34],"incorporate":[35],"global-level":[36],"information":[37],"into":[38],"the":[39,73,80,86,91,97],"initialized":[40],"input":[41],"mainly":[42],"based":[43],"on":[44,85],"transformer":[45],"architecture.":[46],"Unlike":[47],"previous":[48],"methods":[49],"that":[50,90],"may":[51],"not":[52],"be":[53],"able":[54],"capture":[56],"rich":[57],"contextual":[59],"information,":[60],"we":[61],"propose":[62],"novel":[64],"method":[65],"named":[66],"Context-Sensitive":[67],"Transformer":[68],"(CSTNet),":[69],"can":[71,94],"discover":[72],"inherent":[74],"further":[78],"empower":[79],"global-to-local":[81],"interactions.":[82],"Experimental":[83],"results":[84],"MSCOCO":[87],"dataset":[88],"show":[89],"proposed":[92],"model":[93],"significantly":[95],"improve":[96],"performance":[98],"captioning.":[101]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}