{"id":"https://openalex.org/W7125814428","doi":"https://doi.org/10.1145/3779153.3779163","title":"Image Captioning Method Based on a CNN-Transformer Hybrid Architecture with Attention Mechanism","display_name":"Image Captioning Method Based on a CNN-Transformer Hybrid Architecture with Attention Mechanism","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W7125814428","doi":"https://doi.org/10.1145/3779153.3779163"},"language":null,"primary_location":{"id":"doi:10.1145/3779153.3779163","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779153.3779163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","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/A5123985621","display_name":"Xin He","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin He","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0005-8740-9777","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123917116","display_name":"Yang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xu","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0008-8258-1908","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123967984","display_name":"Jiajie Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajie Xie","raw_affiliation_strings":["School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0007-0380-2999","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5123985621"],"corresponding_institution_ids":["https://openalex.org/I145581781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66904678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9641000032424927,"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":0.9641000032424927,"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.004399999976158142,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0034000000450760126,"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":0.9294999837875366},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5058000087738037},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4697999954223633},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.40720000863075256},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.40149998664855957},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39739999175071716},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39730000495910645},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3856000006198883},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.36970001459121704}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9294999837875366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6201000213623047},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3856000006198883},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779153.3779163","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779153.3779163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8005082607269287,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2185175083","https://openalex.org/W2963037989"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"image":[1,27,53,62],"captioning":[2,54],"has":[3],"emerged":[4],"as":[5,22,132,187],"a":[6,83,109],"key":[7],"task":[8],"at":[9],"the":[10,88,98,123,143,149,171,182,188],"intersection":[11],"of":[12,71,92,102,184,190],"computer":[13,72],"vision":[14,73],"and":[15,26,42,65,74,118,140,162,179,193,209],"natural":[16,75],"language":[17,76],"processing,":[18],"supporting":[19],"applications":[20],"such":[21,131,186],"content":[23],"retrieval,":[24],"accessibility,":[25],"understanding.":[28],"However,":[29],"existing":[30],"models":[31],"often":[32],"struggle":[33],"with":[34,97],"accurately":[35],"describing":[36],"complex":[37,154],"scenes":[38],"involving":[39],"long-range":[40,160],"dependencies":[41],"multiple":[43],"interacting":[44],"objects.":[45],"This":[46],"project":[47],"aims":[48],"to":[49,152],"construct":[50],"an":[51],"automatic":[52],"system":[55,80],"based":[56],"on":[57,128,195],"attention":[58,111,176,191],"mechanisms,":[59],"achieving":[60],"end-to-end":[61],"semantic":[63,207],"understanding":[64],"description":[66,165],"generation":[67,196],"through":[68,135],"deep":[69],"integration":[70],"processing":[77],"technologies.":[78],"The":[79,167,198],"innovatively":[81],"adopts":[82],"CNN-Transformer":[84],"hybrid":[85,145],"architecture,":[86],"combining":[87],"local":[89],"perception":[90],"capability":[91],"convolutional":[93],"neural":[94],"networks":[95],"(CNN)":[96],"global":[99],"modeling":[100],"advantages":[101],"Transformers":[103],"during":[104],"visual":[105],"feature":[106],"extraction.":[107],"Additionally,":[108],"multi-level":[110],"fusion":[112],"module":[113],"(including":[114],"spatial":[115],"attention,":[116],"self-attention,":[117],"cross-attention)":[119],"is":[120],"designed":[121],"for":[122],"cross-modal":[124],"interaction":[125,164],"layer.":[126],"Experiments":[127],"standard":[129],"datasets":[130],"MSCOCO":[133],"demonstrate":[134],"metrics":[136],"like":[137],"BLEU-4,":[138],"METEOR,":[139],"CIDEr":[141],"that":[142],"proposed":[144],"architecture":[146],"significantly":[147],"enhances":[148],"model's":[150],"ability":[151],"capture":[153],"scene":[155],"semantics,":[156],"particularly":[157],"excelling":[158],"in":[159,205],"dependency":[161],"multi-object":[163],"tasks.":[166],"study":[168],"further":[169],"compares":[170],"performance":[172],"differences":[173],"among":[174],"various":[175],"mechanism":[177],"variants":[178],"quantitatively":[180],"analyzes":[181],"impact":[183],"hyperparameters":[185],"number":[189],"heads":[192],"layers":[194],"quality.":[197],"final":[199],"generated":[200],"captions":[201],"outperform":[202],"traditional":[203],"methods":[204],"both":[206],"accuracy":[208],"linguistic":[210],"fluency.":[211]},"counts_by_year":[],"updated_date":"2026-01-28T23:18:48.515280","created_date":"2026-01-28T00:00:00"}