{"id":"https://openalex.org/W4399658433","doi":"https://doi.org/10.1145/3641584.3641586","title":"A Multi-stage Feature Enhancement Network with Second-Attention for Image Captioning","display_name":"A Multi-stage Feature Enhancement Network with Second-Attention for Image Captioning","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4399658433","doi":"https://doi.org/10.1145/3641584.3641586"},"language":"en","primary_location":{"id":"doi:10.1145/3641584.3641586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641584.3641586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","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/A5038725235","display_name":"Xiaobao Yang","orcid":"https://orcid.org/0000-0003-1515-8663"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobao Yang","raw_affiliation_strings":["School of Computer Science, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0003-1515-8663","affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103159618","display_name":"Yang Yang","orcid":"https://orcid.org/0009-0006-0540-4938"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["School of Computer Science, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0006-0540-4938","affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017194230","display_name":"Junsheng Wu","orcid":"https://orcid.org/0000-0003-3974-5838"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsheng Wu","raw_affiliation_strings":["School of Software, Northwestern Polytechnical University, China"],"raw_orcid":"https://orcid.org/0000-0003-3974-5838","affiliations":[{"raw_affiliation_string":"School of Software, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068927949","display_name":"Sugang Ma","orcid":"https://orcid.org/0000-0002-8588-8111"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sugang Ma","raw_affiliation_strings":["School of Computer Science, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-8588-8111","affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053618028","display_name":"Zhiqiang Hou","orcid":"https://orcid.org/0000-0002-8059-5395"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Hou","raw_affiliation_strings":["School of Computer Science, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-8059-5395","affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018039306","display_name":"Bohui Song","orcid":"https://orcid.org/0009-0005-9893-2838"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohui Song","raw_affiliation_strings":["School of Computer Science, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0005-9893-2838","affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9958999752998352,"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":0.9556668996810913},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7315765023231506},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722102165222168},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6742019653320312},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5774720907211304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5117061138153076},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4506707787513733},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3988465368747711},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3741404414176941},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33389997482299805},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05271938443183899},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0499233603477478}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9556668996810913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7315765023231506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722102165222168},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6742019653320312},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5774720907211304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5117061138153076},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4506707787513733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3988465368747711},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3741404414176941},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33389997482299805},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05271938443183899},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0499233603477478},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641584.3641586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641584.3641586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W2481240925","https://openalex.org/W2565639579","https://openalex.org/W2575842049","https://openalex.org/W2769836096","https://openalex.org/W2883502031","https://openalex.org/W2896457183","https://openalex.org/W2914304175","https://openalex.org/W2996732257","https://openalex.org/W3008612785","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3107475078","https://openalex.org/W3124149278","https://openalex.org/W3129415623","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3159583533","https://openalex.org/W3177525997","https://openalex.org/W4214708455","https://openalex.org/W4220697067","https://openalex.org/W4221148504","https://openalex.org/W4231608398","https://openalex.org/W4251598823","https://openalex.org/W4282968790","https://openalex.org/W4285531802","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W4386059972","https://openalex.org/W6639657675","https://openalex.org/W6739901393","https://openalex.org/W6756667841","https://openalex.org/W6761628794","https://openalex.org/W6762655340","https://openalex.org/W6771429369","https://openalex.org/W6775772702","https://openalex.org/W6781533629","https://openalex.org/W6789705400","https://openalex.org/W6809596087"],"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/W2949522393"],"abstract_inverted_index":{"In":[0],"the":[1,35,42,48,66,72,75,106,121,135,146],"past":[2],"few":[3],"years,":[4],"self-attention":[5,38],"in":[6,12,31,90,154],"Transformer":[7],"has":[8],"been":[9],"widely":[10],"used":[11],"natural":[13],"language":[14],"processing":[15],"(NLP)":[16],"and":[17,71,104,111,118],"computer":[18],"vision":[19],"(CV)":[20],"due":[21,64],"to":[22,26,65,108,114,133,137],"its":[23],"excellent":[24],"ability":[25,136],"capture":[27],"global":[28,67],"information,":[29],"especially":[30],"image":[32,50,95],"captioning,":[33],"where":[34],"use":[36],"of":[37,44,69,77,123],"can":[39,99],"significantly":[40],"improve":[41,134],"representation":[43],"visual":[45,139],"information.":[46,140],"However,":[47],"obtained":[49],"feature":[51,83],"from":[52,56],"Transformer-based":[53],"models":[54],"suffers":[55],"two":[57],"main":[58],"problems,":[59],"one":[60],"is":[61,74],"information":[62,79,103,117],"redundancy":[63],"aggregation":[68],"self-attention,":[70],"other":[73],"lack":[76],"semantic":[78,116],"caused":[80],"by":[81,93,161,165],"single-scale":[82],"extraction.":[84],"Therefore,":[85],"we":[86,125,150],"first":[87],"propose":[88],"second-attention":[89,98],"this":[91],"paper,":[92],"redistributing":[94],"attention":[96,107],"weights,":[97],"effectively":[100],"remove":[101],"irrelevant":[102],"enhance":[105,120],"essential":[109],"objects":[110],"relations.":[112],"Meanwhile,":[113],"enrich":[115],"further":[119],"role":[122],"second-attention,":[124],"design":[126],"a":[127],"Multi-stage":[128],"Feature":[129],"Enhancement":[130],"(MFE)":[131],"network":[132],"represent":[138],"After":[141],"conducting":[142],"extensive":[143],"experiments":[144],"on":[145],"MS":[147],"COCO":[148],"dataset,":[149],"achieve":[151],"significant":[152],"improvements":[153],"all":[155],"popular":[156],"benchmarks,":[157],"particularly":[158],"BLEU4":[159],"increased":[160,164],"1.6%,":[162],"CIDEr":[163],"3.4%.":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
