{"id":"https://openalex.org/W4323240759","doi":"https://doi.org/10.5220/0011796100003417","title":"Applying Positional Encoding to Enhance Vision-Language Transformers","display_name":"Applying Positional Encoding to Enhance Vision-Language Transformers","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323240759","doi":"https://doi.org/10.5220/0011796100003417"},"language":"en","primary_location":{"id":"doi:10.5220/0011796100003417","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011796100003417","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0011796100003417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025106702","display_name":"Xuehao Liu","orcid":"https://orcid.org/0000-0002-2982-4228"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Xuehao Liu","raw_affiliation_strings":["School of Computer Science, Technological University Dublin, Ireland, --- Select a Country ---","TU Dublin","Technological University Dublin","Technological University Dublin,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Technological University Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"TU Dublin","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"Technological University Dublin","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"Technological University Dublin,","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067047073","display_name":"Sarah Jane Delany","orcid":"https://orcid.org/0000-0002-2062-7439"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Sarah Delany","raw_affiliation_strings":["School of Computer Science, Technological University Dublin, Ireland, --- Select a Country ---","TU Dublin","Technological University Dublin","Technological University Dublin,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Technological University Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"TU Dublin","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"Technological University Dublin","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"Technological University Dublin,","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086973117","display_name":"Susan McKeever","orcid":"https://orcid.org/0000-0003-1766-2441"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Susan McKeever","raw_affiliation_strings":["School of Computer Science, Technological University Dublin, Ireland, --- Select a Country ---","TU Dublin","Technological University Dublin","Technological University Dublin,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Technological University Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"TU Dublin","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"Technological University Dublin","institution_ids":["https://openalex.org/I4210144925"]},{"raw_affiliation_string":"Technological University Dublin,","institution_ids":["https://openalex.org/I4210144925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144925"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01343542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"838","last_page":"845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9269000291824341,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9269000291824341,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7233094573020935},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6698076725006104},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5654367804527283},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44748198986053467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4437538981437683},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1541719138622284},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15344980359077454},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09480756521224976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233094573020935},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6698076725006104},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5654367804527283},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44748198986053467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4437538981437683},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1541719138622284},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15344980359077454},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09480756521224976}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0011796100003417","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011796100003417","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arrow.tudublin.ie:scschcomcon-1413","is_oa":true,"landing_page_url":"https://arrow.tudublin.ie/scschcomcon/390","pdf_url":null,"source":{"id":"https://openalex.org/S4377196307","display_name":"Arrow - TU Dublin (Technological University Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Conference papers","raw_type":"presentation"}],"best_oa_location":{"id":"doi:10.5220/0011796100003417","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011796100003417","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2109586012","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2963084599","https://openalex.org/W2963925437","https://openalex.org/W2964110616","https://openalex.org/W2983943451","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3034445277","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3106210592","https://openalex.org/W3138516171","https://openalex.org/W3139049060","https://openalex.org/W3173220247","https://openalex.org/W3173909648","https://openalex.org/W3184735396","https://openalex.org/W3203701986","https://openalex.org/W4206706211","https://openalex.org/W4281633595","https://openalex.org/W4287324101","https://openalex.org/W4298395628","https://openalex.org/W4312784228","https://openalex.org/W4385245566","https://openalex.org/W4385574358"],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2389073067","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W2755342338","https://openalex.org/W3116076068","https://openalex.org/W2229312674"],"abstract_inverted_index":{"Positional":[0],"encoding":[1,48,105,113],"is":[2],"used":[3],"in":[4,28],"both":[5,128],"natural":[6],"language":[7,37],"and":[8,18,38,115,126],"computer":[9],"vision":[10,39],"transformers.":[11],"It":[12],"provides":[13],"information":[14,59],"on":[15],"sequence":[16],"order":[17],"relative":[19,118],"position":[20],"of":[21,26,60,74,103,136],"input":[22,52],"tokens":[23],"(such":[24],"as":[25,80,92,109],"words":[27],"a":[29,93],"sentence)":[30],"for":[31,84,117],"higher":[32],"performance.":[33,69,98],"Unlike":[34],"the":[35,75,122,132],"pure":[36],"transformers,":[40],"vision-language":[41,65,78],"transformers":[42,66,79],"do":[43],"not":[44],"currently":[45],"exploit":[46],"positional":[47,86,104,112,119,129],"schemes":[49],"to":[50,96,141],"enrich":[51],"information.":[53],"We":[54,70,88,99],"show":[55],"that":[56],"capturing":[57],"location":[58],"visual":[61],"features":[62],"can":[63],"help":[64],"improve":[67],"their":[68],"take":[71],"Oscar,":[72],"one":[73],"state-of-the-art":[76],"(SOTA)":[77],"an":[81,110],"example":[82],"transformer":[83],"implanting":[85],"encoding.":[87,120],"use":[89],"image":[90,133,145],"captioning":[91,134,146],"downstream":[94],"task":[95],"test":[97],"added":[100],"two":[101],"types":[102],"into":[106],"Oscar:":[107],"DETR":[108],"absolute":[111],"approach":[114],"iRPE,":[116],"With":[121],"same":[123],"training":[124],"protocol":[125],"data,":[127],"encodings":[130],"improved":[131],"performance":[135],"Oscar":[137],"by":[138],"between":[139],"6.8%":[140],"24.1%":[142],"across":[143],"five":[144],"evaluation":[147],"criteria":[148],"used.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
