{"id":"https://openalex.org/W2909827971","doi":"https://doi.org/10.1109/dicta.2018.8615788","title":"Size-Invariant Attention Accuracy Metric for Image Captioning with High-Resolution Residual Attention","display_name":"Size-Invariant Attention Accuracy Metric for Image Captioning with High-Resolution Residual Attention","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2909827971","doi":"https://doi.org/10.1109/dicta.2018.8615788","mag":"2909827971"},"language":"en","primary_location":{"id":"doi:10.1109/dicta.2018.8615788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2018.8615788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.lib.uts.edu.au/bitstream/10453/132535/4/dicta2018.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060113731","display_name":"Zongjian Zhang","orcid":"https://orcid.org/0000-0001-9309-1826"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zongjian Zhang","raw_affiliation_strings":["School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063629854","display_name":"Qiang Wu","orcid":"https://orcid.org/0000-0001-5641-2483"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714578","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-6815-0879"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Data61 CSIRO, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Data61 CSIRO, Sydney, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100400043","display_name":"Fang Chen","orcid":"https://orcid.org/0000-0003-4971-8729"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fang Chen","raw_affiliation_strings":["Data61 CSIRO, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Data61 CSIRO, Sydney, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060113731"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.2125,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58519167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.996999979019165,"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":0.9961000084877014,"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/metric","display_name":"Metric (unit)","score":0.7037926912307739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6593486070632935},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6465829014778137},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.625109851360321},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5934792757034302},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5106444954872131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46178609132766724},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4545922875404358},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.420685350894928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3812868595123291},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3510218560695648},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2293553352355957},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20914170145988464}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7037926912307739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593486070632935},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6465829014778137},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.625109851360321},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5934792757034302},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5106444954872131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46178609132766724},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4545922875404358},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.420685350894928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3812868595123291},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3510218560695648},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2293553352355957},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20914170145988464},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dicta.2018.8615788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2018.8615788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/132535","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/132535","pdf_url":"https://opus.lib.uts.edu.au/bitstream/10453/132535/4/dicta2018.pdf","source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:opus.lib.uts.edu.au:10453/132535","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/132535","pdf_url":"https://opus.lib.uts.edu.au/bitstream/10453/132535/4/dicta2018.pdf","source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2909827971.pdf","grobid_xml":"https://content.openalex.org/works/W2909827971.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2174492417","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2550553598","https://openalex.org/W2552002300","https://openalex.org/W2558401060","https://openalex.org/W2561196672","https://openalex.org/W2563296158","https://openalex.org/W2563705555","https://openalex.org/W2575842049","https://openalex.org/W2753232960","https://openalex.org/W2802194751","https://openalex.org/W2949341804","https://openalex.org/W2949376505","https://openalex.org/W2963084599","https://openalex.org/W2963088515","https://openalex.org/W2963175879","https://openalex.org/W2963201326","https://openalex.org/W2963630207","https://openalex.org/W2963758027","https://openalex.org/W2963954913","https://openalex.org/W3103022576","https://openalex.org/W4299298190","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6678262379","https://openalex.org/W6685520387","https://openalex.org/W6714414533","https://openalex.org/W6898505805"],"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/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Spatial":[0],"visual":[1],"attention":[2,18,32,46,67,109,145,184],"mechanisms":[3],"have":[4],"achieved":[5],"significant":[6],"performance":[7],"improvements":[8],"for":[9,35,181],"image":[10],"captioning.":[11],"To":[12,69,94],"quantitatively":[13],"evaluate":[14,142],"the":[15,20,29,45,49,82,87,91,96,115,123,143,163,174,183],"performances":[16,63,176],"of":[17,31,90,98],"mechanisms,":[19],"\"attention":[21,83,164],"correctness\"":[22,84,165],"metric":[23,41,79,85,140,169],"has":[24],"been":[25],"proposed":[26,144],"to":[27,141],"calculate":[28],"sum":[30],"weights":[33],"generated":[34],"ground":[36],"truth":[37],"regions.":[38,136],"However,":[39],"this":[40,73,102],"cannot":[42],"consistently":[43],"measure":[44],"accuracy":[47],"among":[48],"element":[50],"regions":[51],"with":[52,61,86,162,173],"large":[53],"size":[54,88],"variance.":[55],"Moreover,":[56],"its":[57],"evaluations":[58,130],"are":[59],"inconsistent":[60],"captioning":[62,175],"across":[64,147],"different":[65],"fine-grained":[66,150],"resolutions.":[68],"address":[70],"these":[71],"problems,":[72],"paper":[74,103],"proposes":[75,105],"a":[76,106],"size-invariant":[77,100,168],"evaluation":[78],"by":[80],"normalizing":[81],"percentage":[89],"attended":[92],"region.":[93],"demonstrate":[95,159],"efficiency":[97],"our":[99,139,167],"metric,":[101,166],"further":[104],"high-resolution":[107],"residual":[108],"model":[110,146],"that":[111],"uses":[112],"RefineNet":[113],"as":[114],"Fully":[116],"Convolutional":[117],"Network":[118],"(FCN)":[119],"encoder.":[120],"By":[121],"using":[122],"COCO-Stuff":[124],"dataset,":[125],"we":[126],"can":[127],"achieve":[128],"pixel-level":[129],"on":[131],"both":[132],"object":[133],"and":[134,177],"\"stuff\"":[135],"We":[137],"use":[138],"four":[148],"high":[149],"resolutions":[151],"(i.e.,":[152],"27\u00d727,":[153],"40\u00d740,":[154],"60\u00d760,":[155],"80\u00d780).":[156],"The":[157],"results":[158],"that,":[160],"compared":[161],"is":[170,178],"more":[171,179],"consistent":[172],"efficient":[180],"evaluating":[182],"accuracy.":[185]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}