{"id":"https://openalex.org/W4403332782","doi":"https://doi.org/10.1145/3686490.3686513","title":"Hybrid Feature Based Global Variational Transformer for Diverse Image Captioning","display_name":"Hybrid Feature Based Global Variational Transformer for Diverse Image Captioning","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4403332782","doi":"https://doi.org/10.1145/3686490.3686513"},"language":"en","primary_location":{"id":"doi:10.1145/3686490.3686513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3686490.3686513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Signal Processing and Machine Learning","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/A5115604638","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0003-1336-8800"},"institutions":[{"id":"https://openalex.org/I4210099297","display_name":"Jilian Technology Group (China)","ror":"https://ror.org/016q5ce10","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099297"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Xuzhou Guanglian Technology Co,Ltd, China"],"affiliations":[{"raw_affiliation_string":"Xuzhou Guanglian Technology Co,Ltd, China","institution_ids":["https://openalex.org/I4210099297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053227611","display_name":"Xiang Bo","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xiang","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108623406","display_name":"Weifeng Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Shi","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115604638"],"corresponding_institution_ids":["https://openalex.org/I4210099297"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17966667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"158"},"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":0.9991000294685364,"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":0.9975000023841858,"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":0.898039698600769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6406413316726685},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6356706619262695},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48695215582847595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48646852374076843},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4423682987689972},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42028889060020447},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36936262249946594},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1544148325920105},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1347980499267578},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08641886711120605}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.898039698600769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6406413316726685},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6356706619262695},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48695215582847595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48646852374076843},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4423682987689972},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42028889060020447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36936262249946594},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1544148325920105},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1347980499267578},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08641886711120605},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3686490.3686513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3686490.3686513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Signal Processing and Machine Learning","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":29,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2130942839","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2197223256","https://openalex.org/W2506483933","https://openalex.org/W2508429489","https://openalex.org/W2604178507","https://openalex.org/W2745461083","https://openalex.org/W2788277448","https://openalex.org/W2889418103","https://openalex.org/W2943885184","https://openalex.org/W2962968835","https://openalex.org/W2963101956","https://openalex.org/W2981165461","https://openalex.org/W2988793532","https://openalex.org/W2990818246","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3136792391","https://openalex.org/W3175824375","https://openalex.org/W4212817947","https://openalex.org/W4385245566","https://openalex.org/W6679436768","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"The":[0,120],"transformer-based":[1,68],"image":[2,27,58,140],"captioning":[3,59,69,141],"models":[4],"have":[5],"shown":[6],"remarkable":[7],"performance":[8],"based":[9,52],"on":[10,22],"the":[11,75,100,112,137],"powerful":[12],"sequence":[13],"modeling":[14],"capability.":[15],"However,":[16],"most":[17],"of":[18,116],"them":[19],"focus":[20],"only":[21],"learning":[23],"deterministic":[24],"mappings":[25],"from":[26],"space":[28],"to":[29,35,92,106],"caption":[30],"space,":[31],"which":[32,61],"generally":[33],"leads":[34],"common":[36],"words,":[37],"repeated":[38],"phrases":[39],"and":[40,89,110,114,133],"single":[41],"sentence.":[42],"To":[43],"this":[44],"end,":[45],"we":[46,80],"propose":[47],"a":[48],"novel":[49],"hybrid":[50],"feature":[51],"global":[53],"variational":[54,64],"transformer":[55,73],"for":[56,86],"diverse":[57,139],"(HF-GVT-IC),":[60],"incorporates":[62],"conditional":[63],"autoencoder":[65],"(CVAE)":[66],"into":[67],"model":[70],"by":[71],"augmenting":[72],"with":[74,96,136],"stochastic":[76],"latent":[77],"variables.":[78],"Meanwhile,":[79],"design":[81],"an":[82],"adaptive":[83],"attention":[84],"module":[85],"both":[87,131],"grid":[88],"region":[90],"features":[91],"learn":[93,107],"their":[94],"interaction":[95],"text":[97],"information":[98],"at":[99],"decoder.":[101],"Our":[102],"method":[103],"is":[104],"able":[105],"one-to-many":[108],"projections":[109],"improve":[111],"diversity":[113,132],"accuracy":[115,134],"generated":[117],"captions":[118],"simultaneously":[119],"experimental":[121],"results":[122],"demonstrate":[123],"that":[124],"our":[125],"proposal":[126],"achieves":[127],"significant":[128],"gains":[129],"in":[130],"compared":[135],"state-of-the-art":[138],"models.":[142]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}