{"id":"https://openalex.org/W4316660194","doi":"https://doi.org/10.1109/vcip56404.2022.10008904","title":"Dual-stream Self-attention Network for Image Captioning","display_name":"Dual-stream Self-attention Network for Image Captioning","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W4316660194","doi":"https://doi.org/10.1109/vcip56404.2022.10008904"},"language":"en","primary_location":{"id":"doi:10.1109/vcip56404.2022.10008904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip56404.2022.10008904","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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 Visual Communications and Image Processing (VCIP)","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/A5103081907","display_name":"Boyang Wan","orcid":"https://orcid.org/0000-0001-8889-0287"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Boyang Wan","raw_affiliation_strings":["Jiangxi University of Finance and Economics,NanChang,China","Jiangxi University of Finance and Economics, NanChang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,NanChang,China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"Jiangxi University of Finance and Economics, NanChang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030344445","display_name":"Wenhui Jiang","orcid":"https://orcid.org/0000-0002-4144-6725"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Jiang","raw_affiliation_strings":["Jiangxi University of Finance and Economics,NanChang,China","Jiangxi University of Finance and Economics, NanChang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,NanChang,China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"Jiangxi University of Finance and Economics, NanChang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063013411","display_name":"Yuming Fang","orcid":"https://orcid.org/0000-0002-6946-3586"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Fang","raw_affiliation_strings":["Jiangxi University of Finance and Economics,NanChang,China","Jiangxi University of Finance and Economics, NanChang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,NanChang,China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"Jiangxi University of Finance and Economics, NanChang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037182288","display_name":"Wenying Wen","orcid":"https://orcid.org/0000-0002-3098-4640"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenying Wen","raw_affiliation_strings":["Jiangxi University of Finance and Economics,NanChang,China","Jiangxi University of Finance and Economics, NanChang, China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,NanChang,China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"Jiangxi University of Finance and Economics, NanChang, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101605853","display_name":"Hantao Liu","orcid":"https://orcid.org/0000-0003-4544-3481"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hantao Liu","raw_affiliation_strings":["Cardiff University,Cardiff,United Kingdom","Cardiff University, Cardiff, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Cardiff University,Cardiff,United Kingdom","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103081907"],"corresponding_institution_ids":["https://openalex.org/I59649739"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46249822,"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":"5"},"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":0.9968000054359436,"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":0.994700014591217,"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":0.9720817804336548},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8407339453697205},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6151275634765625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5840072631835938},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5499800443649292},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5326356887817383},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.527645468711853},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5225374698638916},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5062578916549683},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4756065011024475},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4563177227973938},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3774718940258026},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35937535762786865},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3545297384262085}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9720817804336548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8407339453697205},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6151275634765625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5840072631835938},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5499800443649292},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5326356887817383},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.527645468711853},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5225374698638916},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5062578916549683},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4756065011024475},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4563177227973938},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3774718940258026},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35937535762786865},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3545297384262085},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/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/vcip56404.2022.10008904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip56404.2022.10008904","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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 Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G8303285193","display_name":null,"funder_award_id":"62161013,62132006,61901197,62162029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2185175083","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2752782242","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2955058313","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963925437","https://openalex.org/W2965846473","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3038571929","https://openalex.org/W3129436779","https://openalex.org/W3138516171","https://openalex.org/W3167939936","https://openalex.org/W3185141858","https://openalex.org/W3204380095","https://openalex.org/W3212386989","https://openalex.org/W3216130706","https://openalex.org/W4214666412","https://openalex.org/W4224920290","https://openalex.org/W4226200183","https://openalex.org/W4285265382","https://openalex.org/W4288329833","https://openalex.org/W4289752563","https://openalex.org/W4312881242","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6674330103","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6763643401","https://openalex.org/W6790667107","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Self-attention":[0],"based":[1,90],"encoder-decoder":[2],"models":[3,15],"achieve":[4],"dominant":[5],"performance":[6,52],"in":[7,53,60],"image":[8,13],"captioning.":[9],"However,":[10],"most":[11],"existing":[12],"captioning":[14,62],"(ICMs)":[16],"only":[17],"focus":[18],"on":[19,133,156,162],"modeling":[20],"the":[21,61,66,81,98,124,134,146],"relation":[22],"between":[23],"spatial":[24,99],"tokens,":[25],"while":[26],"channel-wise":[27,106],"attention":[28],"is":[29],"neglected":[30],"for":[31],"getting":[32],"visual":[33,40,45,95,107],"representation.":[34],"Considering":[35],"that":[36,92],"different":[37,44],"channels":[38],"of":[39,55,126],"representation":[41],"usually":[42],"denote":[43],"objects,":[46],"it":[47],"may":[48],"lead":[49],"to":[50,79,104],"poor":[51],"terms":[54],"object":[56],"and":[57,100,110,140,144,158],"attribute":[58],"words":[59],"sentences":[63],"generated":[64],"by":[65],"ICMs.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,85,112,129],"propose":[72,86],"a":[73,87,114],"novel":[74],"dual-stream":[75],"self-attention":[76,89,116],"module":[77,91],"(DSM)":[78],"alleviate":[80],"above":[82],"issue.":[83],"Specifically,":[84],"parallel":[88],"simultaneously":[93],"encodes":[94],"information":[96],"from":[97],"channel":[101],"dimensions.":[102],"Besides,":[103],"obtain":[105],"features":[108],"effectively":[109],"efficiently,":[111],"introduce":[113],"group":[115],"block":[117],"with":[118],"linear":[119],"computational":[120],"complexity.":[121],"To":[122],"validate":[123],"effectiveness":[125],"our":[127],"model,":[128],"conduct":[130],"extensive":[131],"experiments":[132],"standard":[135],"IC":[136],"benchmarks":[137],"including":[138],"MSCOCO":[139,157],"Flickr30k.":[141,163],"Without":[142],"bells":[143],"whistles,":[145],"proposed":[147],"model":[148],"performs":[149],"new":[150],"SOTAs":[151],"containing":[152],"135.4":[153],"CIDEr":[154,160],"score":[155,161],"70.8":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}