{"id":"https://openalex.org/W4385270469","doi":"https://doi.org/10.1109/uv56588.2022.10185494","title":"Image Caption Enhancement with GRIT, Portable ResNet and BART Context-Tuning","display_name":"Image Caption Enhancement with GRIT, Portable ResNet and BART Context-Tuning","publication_year":2022,"publication_date":"2022-10-22","ids":{"openalex":"https://openalex.org/W4385270469","doi":"https://doi.org/10.1109/uv56588.2022.10185494"},"language":"en","primary_location":{"id":"doi:10.1109/uv56588.2022.10185494","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/uv56588.2022.10185494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 6th International Conference on Universal Village (UV)","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/A5103021115","display_name":"Wuyang Zhang","orcid":"https://orcid.org/0009-0001-8068-0282"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wuyang Zhang","raw_affiliation_strings":["Northeastern University,Department of Computer Systems Engineering,Boston,United States","Department of Computer Systems Engineering, Northeastern University, Boston, United States"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Computer Systems Engineering,Boston,United States","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Department of Computer Systems Engineering, Northeastern University, Boston, United States","institution_ids":["https://openalex.org/I12912129","https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100758070","display_name":"Jianmin Ma","orcid":"https://orcid.org/0000-0003-2081-2877"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianming Ma","raw_affiliation_strings":["Northeastern University,Department of Applied Machine Intelligence,Boston,United States","Department of Applied Machine Intelligence, Northeastern University, Boston, United States"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Applied Machine Intelligence,Boston,United States","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Department of Applied Machine Intelligence, Northeastern University, Boston, United States","institution_ids":["https://openalex.org/I12912129","https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103021115"],"corresponding_institution_ids":["https://openalex.org/I111088046","https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17650348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.998199999332428,"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":0.9954000115394592,"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/grit","display_name":"Grit","score":0.8376632928848267},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6910815238952637},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.6685278415679932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6211722493171692},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41984492540359497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39454448223114014},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14419955015182495},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.10387462377548218},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08547291159629822}],"concepts":[{"id":"https://openalex.org/C162451180","wikidata":"https://www.wikidata.org/wiki/Q4453370","display_name":"Grit","level":2,"score":0.8376632928848267},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6910815238952637},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.6685278415679932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6211722493171692},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41984492540359497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39454448223114014},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14419955015182495},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.10387462377548218},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08547291159629822},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/uv56588.2022.10185494","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/uv56588.2022.10185494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 6th International Conference on Universal Village (UV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W1977295328","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2575842049","https://openalex.org/W2896457183","https://openalex.org/W2943924962","https://openalex.org/W2963698657","https://openalex.org/W2972481734","https://openalex.org/W3022895911","https://openalex.org/W3034999214","https://openalex.org/W3046003264","https://openalex.org/W3088826108","https://openalex.org/W3167939936","https://openalex.org/W3185154749","https://openalex.org/W3200568291","https://openalex.org/W4206164267","https://openalex.org/W4235505822","https://openalex.org/W4288083516","https://openalex.org/W4312289196","https://openalex.org/W6630875275","https://openalex.org/W6631516269","https://openalex.org/W6682631176","https://openalex.org/W6687483927","https://openalex.org/W6755207826","https://openalex.org/W6769311223","https://openalex.org/W6798885000"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,23,51,55,72],"create":[4],"an":[5],"image":[6,15,28,33,96],"captioning":[7,29,34],"novel":[8],"architecture":[9],"that":[10],"infuses":[11],"Grid":[12],"and":[13,19,69,103],"Region-based":[14],"caption":[16],"transformer,":[17],"ResNet,":[18],"BART":[20],"language":[21],"model":[22],"offer":[24],"a":[25],"more":[26],"detail-oriented":[27],"model.":[30],"Conventional":[31],"state-of-the-art":[32],"models":[35],"mainly":[36],"focuses":[37],"on":[38,43],"region-based":[39],"features.":[40],"They":[41],"rely":[42],"decent":[44],"object":[45],"detector":[46],"architectures":[47],"like":[48],"Faster":[49],"R-CNN":[50],"extract":[52],"object-level":[53],"information":[54],"describe":[56],"the":[57,70,81],"image\u2019s":[58],"content.":[59],"Nevertheless,":[60],"they":[61],"cannot":[62],"remove":[63],"contextual":[64,106],"information,":[65],"high":[66],"computational":[67],"costs,":[68],"ability":[71],"introduce":[73],"in-depth":[74],"external":[75],"details":[76,104],"of":[77,84],"objects":[78],"presented":[79],"in":[80,89],"images\u2014the":[82],"replacement":[83],"conventional":[85],"CNN-based":[86],"detectors":[87],"results":[88],"faster":[90],"computation.":[91],"The":[92],"experiment":[93],"can":[94],"generate":[95],"captions":[97],"comparatively":[98],"fast":[99],"with":[100,105],"higher":[101],"accuracy":[102],"information.":[107]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}