{"id":"https://openalex.org/W4225294377","doi":"https://doi.org/10.1109/icassp43922.2022.9746714","title":"Exploring Dual Stream Global Information For Image Captioning","display_name":"Exploring Dual Stream Global Information For Image Captioning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225294377","doi":"https://doi.org/10.1109/icassp43922.2022.9746714"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746714","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5060117326","display_name":"Tiantao Xian","orcid":"https://orcid.org/0000-0002-1092-9732"},"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":"Tiantao Xian","raw_affiliation_strings":["Guangxi Normal University,Guangxi Key Lab of Multi-Source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-Source Information Mining and Security,Guilin,China,541004","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 Normal University,Guangxi Key Lab of Multi-Source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-Source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371624","display_name":"Tianyu Chen","orcid":"https://orcid.org/0000-0002-5101-7561"},"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":"Tianyu Chen","raw_affiliation_strings":["Guangxi Normal University,Guangxi Key Lab of Multi-Source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-Source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053794277","display_name":"Huifang Ma","orcid":"https://orcid.org/0000-0002-5104-8982"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifang Ma","raw_affiliation_strings":["Northwest Normal University,College of Computer Science and Engineering,Lanzhou,China,730070"],"affiliations":[{"raw_affiliation_string":"Northwest Normal University,College of Computer Science and Engineering,Lanzhou,China,730070","institution_ids":["https://openalex.org/I68986083"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060117326"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.06,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22971624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"35","issue":null,"first_page":"4458","last_page":"4462"},"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":0.9976000189781189,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9872000217437744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8924524784088135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8040511608123779},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6239848136901855},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6157307028770447},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5536935925483704},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43487000465393066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4298633337020874},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41512760519981384},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36945393681526184},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34915274381637573},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13004621863365173}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8924524784088135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040511608123779},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6239848136901855},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6157307028770447},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5536935925483704},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43487000465393066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4298633337020874},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41512760519981384},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36945393681526184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34915274381637573},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13004621863365173},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746714","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2990818246","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3080813890","https://openalex.org/W3096407995","https://openalex.org/W3162954998","https://openalex.org/W3175824375","https://openalex.org/W4288329833","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6763643401","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2795359650","https://openalex.org/W4320858200","https://openalex.org/W3008515501","https://openalex.org/W2923366293","https://openalex.org/W2547835662","https://openalex.org/W4365441642","https://openalex.org/W2788710361","https://openalex.org/W2963421891","https://openalex.org/W2988894263","https://openalex.org/W2965432789"],"abstract_inverted_index":{"In":[0,25,55,74],"recent":[1],"years,":[2],"image":[3,125],"caption":[4],"methods":[5],"based":[6],"on":[7,122],"the":[8,20,40,43,52,109,123],"encoder-decoder":[9],"framework":[10],"have":[11],"made":[12],"promising":[13],"achievements,":[14],"but":[15],"most":[16],"of":[17,22,51],"them":[18],"lack":[19],"exploitation":[21],"global":[23,28,45,72,88,111],"information.":[24,73],"general,":[26],"visual":[27,53,69,80,90],"information":[29,46,112],"can":[30],"provide":[31],"more":[32],"fine-grain":[33],"details":[34],"for":[35],"recognizing":[36],"small":[37],"objects.":[38],"On":[39],"other":[41],"hand,":[42],"textual":[44,71,110],"provides":[47],"a":[48,87,93],"coarse":[49],"understanding":[50],"scene.":[54],"this":[56],"paper,":[57],"we":[58,77,101,118],"propose":[59],"Dual":[60],"Global":[61,95,103],"Enhanced":[62,96,104],"Transformer":[63],"(DGET)":[64],"to":[65,85,107],"explicitly":[66],"utilize":[67,108],"both":[68],"and":[70,128],"encoding":[75],"stages,":[76],"complement":[78],"two":[79],"features":[81],"with":[82],"different":[83],"properties":[84],"obtain":[86],"enhanced":[89],"representation":[91],"by":[92],"novel":[94],"Encoder":[97],"(GEE).":[98],"During":[99],"decoding,":[100],"proposed":[102],"Decoder":[105],"(GED)":[106],"explicitly.":[113],"To":[114],"validate":[115],"our":[116],"model,":[117],"conduct":[119],"extensive":[120],"experiments":[121],"COCO":[124],"captioning":[126],"dataset":[127],"achieve":[129],"superior":[130],"performance":[131],"over":[132],"many":[133],"state-of-the-art":[134],"methods.":[135]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}