{"id":"https://openalex.org/W4376852373","doi":"https://doi.org/10.1145/3573942.3574052","title":"Image Captioning Method Based on Layer Feature Attention","display_name":"Image Captioning Method Based on Layer Feature Attention","publication_year":2022,"publication_date":"2022-09-23","ids":{"openalex":"https://openalex.org/W4376852373","doi":"https://doi.org/10.1145/3573942.3574052"},"language":"en","primary_location":{"id":"doi:10.1145/3573942.3574052","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573942.3574052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","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/A5085618437","display_name":"Qiujuan Tong","orcid":"https://orcid.org/0000-0001-8231-8562"},"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":true,"raw_author_name":"Qiujuan Tong","raw_affiliation_strings":["School of Science, Xi'an University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"School of Science, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009586987","display_name":"Chan He","orcid":"https://orcid.org/0000-0003-3071-7494"},"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":"Chan He","raw_affiliation_strings":["School of Telecommunication and Information Engineering, Xi'an University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"School of Telecommunication and Information Engineering, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102731450","display_name":"Jiaqi Li","orcid":"https://orcid.org/0000-0002-8015-8291"},"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":"Jiaqi Li","raw_affiliation_strings":["School of Science, Xi'an University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"School of Science, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018619395","display_name":"Yifan Li","orcid":"https://orcid.org/0000-0001-5957-7339"},"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":"Yifan Li","raw_affiliation_strings":["School of Science, Xi'an University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"School of Science, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085618437"],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17190033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"488"},"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":0.9894999861717224,"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":0.9768999814987183,"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":0.891149640083313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8374460935592651},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7018629312515259},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6184055805206299},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5306863784790039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5153840780258179},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4545508921146393},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.45163118839263916},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41673964262008667},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.41357338428497314},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3628752827644348},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3287573456764221}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.891149640083313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374460935592651},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7018629312515259},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6184055805206299},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5306863784790039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5153840780258179},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4545508921146393},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.45163118839263916},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41673964262008667},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.41357338428497314},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3628752827644348},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3287573456764221},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573942.3574052","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573942.3574052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","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":18,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2517227754","https://openalex.org/W2595813107","https://openalex.org/W2800782462","https://openalex.org/W2893539175","https://openalex.org/W2964018924","https://openalex.org/W2968660381","https://openalex.org/W3034655362","https://openalex.org/W3167939936","https://openalex.org/W3170494780","https://openalex.org/W3176470992","https://openalex.org/W3178322352","https://openalex.org/W4234552385","https://openalex.org/W4236965008","https://openalex.org/W6600210776","https://openalex.org/W6601700763","https://openalex.org/W6603713569","https://openalex.org/W6606404423"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"The":[0],"high-level":[1,26],"features":[2,12,27,114,128,141,149],"of":[3,33,40,56,66,82,101,115,129,142,154],"images":[4],"are":[5],"often":[6],"used":[7],"to":[8,45,52,126,150],"represent":[9],"the":[10,14,25,37,54,63,71,76,98,104,112,116,124,127,137,140,146,152,155],"scene":[11],"in":[13,75],"image":[15,77,86],"captioning":[16,87],"task,":[17],"because":[18],"they":[19],"contain":[20],"rich":[21,72],"semantic":[22,73,148],"information,":[23,35],"but":[24],"can":[28,122],"only":[29],"express":[30],"a":[31],"feature":[32,92,106],"global":[34],"and":[36,59,78,134,145],"local":[38],"information":[39,74],"small":[41,57,83],"objects":[42],"is":[43,94,109],"easy":[44],"be":[46],"ignored,":[47],"which":[48],"makes":[49],"it":[50],"difficult":[51],"generate":[53],"description":[55,64,81],"objects,":[58,84],"thus":[60],"cannot":[61],"meet":[62],"requirements":[65],"finer":[67],"granularity.":[68],"To":[69],"describe":[70],"retain":[79],"more":[80],"an":[85],"method":[88],"based":[89],"on":[90],"layer":[91,105,121,131,144],"attention":[93,107,125],"proposed.":[95],"Combined":[96],"with":[97],"existing":[99],"structure":[100],"Transformer":[102],"decoder,":[103],"module":[108],"designed.":[110],"Using":[111],"multi-layer":[113],"image,":[117],"each":[118,130,143],"decoder":[119],"stack":[120],"determine":[123],"when":[132],"decoding,":[133],"dynamically":[135],"learn":[136],"similarity":[138],"between":[139],"sequence":[147],"improve":[151],"quality":[153],"statement.":[156]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}