{"id":"https://openalex.org/W4392347629","doi":"https://doi.org/10.1145/3650111","title":"Learning Scene Representations for Human-assistive Displays Using Self-attention Networks","display_name":"Learning Scene Representations for Human-assistive Displays Using Self-attention Networks","publication_year":2024,"publication_date":"2024-03-02","ids":{"openalex":"https://openalex.org/W4392347629","doi":"https://doi.org/10.1145/3650111"},"language":"en","primary_location":{"id":"doi:10.1145/3650111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650111","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5054135227","display_name":"Jaime Ruiz-Serra","orcid":"https://orcid.org/0000-0002-0220-3253"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jaime Ruiz-Serra","raw_affiliation_strings":["Swinburne University of Technology, Hawthorn, Australia and The University of Sydney, Darlington, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Hawthorn, Australia and The University of Sydney, Darlington, Australia","institution_ids":["https://openalex.org/I57093077","https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077794334","display_name":"Jack White","orcid":"https://orcid.org/0000-0003-1273-1786"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jack White","raw_affiliation_strings":["Swinburne University of Technology, Hawthorn, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Hawthorn, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002072511","display_name":"Stephen Petrie","orcid":"https://orcid.org/0000-0002-8773-516X"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Stephen Petrie","raw_affiliation_strings":["Swinburne University of Technology, Hawthorn, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Hawthorn, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004404618","display_name":"Tatiana Kameneva","orcid":"https://orcid.org/0000-0003-0081-8569"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tatiana Kameneva","raw_affiliation_strings":["Swinburne University of Technology, Hawthorn, Australia and The University of Melbourne, Parkville, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Hawthorn, Australia and The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I57093077","https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065533993","display_name":"Chris McCarthy","orcid":"https://orcid.org/0000-0003-3848-1631"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chris McCarthy","raw_affiliation_strings":["Swinburne University of Technology, Hawthorn, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Hawthorn, Australia","institution_ids":["https://openalex.org/I57093077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054135227"],"corresponding_institution_ids":["https://openalex.org/I129604602","https://openalex.org/I57093077"],"apc_list":null,"apc_paid":null,"fwci":1.0285,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72628289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"20","issue":"7","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9991000294685364,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8123933672904968},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5755504965782166},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5182530879974365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5028018951416016},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4650247097015381},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.45490747690200806},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.41600358486175537},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3890509009361267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123933672904968},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5755504965782166},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5182530879974365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5028018951416016},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4650247097015381},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.45490747690200806},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.41600358486175537},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3890509009361267},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650111","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320973","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W891451175","https://openalex.org/W1497443722","https://openalex.org/W1575843485","https://openalex.org/W1712000580","https://openalex.org/W1778783464","https://openalex.org/W1923184257","https://openalex.org/W1983506978","https://openalex.org/W2011394897","https://openalex.org/W2014017905","https://openalex.org/W2022819366","https://openalex.org/W2027547973","https://openalex.org/W2049567999","https://openalex.org/W2056046632","https://openalex.org/W2084323233","https://openalex.org/W2087327676","https://openalex.org/W2089765964","https://openalex.org/W2091759966","https://openalex.org/W2091865309","https://openalex.org/W2118638852","https://openalex.org/W2133797163","https://openalex.org/W2155668458","https://openalex.org/W2301060981","https://openalex.org/W2315531387","https://openalex.org/W2343057586","https://openalex.org/W2345422230","https://openalex.org/W2461758788","https://openalex.org/W2513263058","https://openalex.org/W2561675875","https://openalex.org/W2563198233","https://openalex.org/W2601877418","https://openalex.org/W2734448226","https://openalex.org/W2765283954","https://openalex.org/W2771683651","https://openalex.org/W2909244976","https://openalex.org/W2979565058","https://openalex.org/W2987288840","https://openalex.org/W2994736635","https://openalex.org/W3003581481","https://openalex.org/W3009020965","https://openalex.org/W3012502279","https://openalex.org/W3036285096","https://openalex.org/W3101438731","https://openalex.org/W3131080578","https://openalex.org/W3180247753","https://openalex.org/W3190215236","https://openalex.org/W3208624098","https://openalex.org/W3214944093","https://openalex.org/W4214727024","https://openalex.org/W4224281996","https://openalex.org/W4301951197","https://openalex.org/W4385245566","https://openalex.org/W6637391178","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2172197285","https://openalex.org/W2991048842","https://openalex.org/W2750280393","https://openalex.org/W2355696739","https://openalex.org/W3158001554","https://openalex.org/W2771909920","https://openalex.org/W1990434954","https://openalex.org/W3196817267","https://openalex.org/W1976600725","https://openalex.org/W2461480269"],"abstract_inverted_index":{"Video-see-through":[0],"(VST)":[1],"augmented":[2],"reality":[3],"(AR)":[4],"is":[5,230],"widely":[6],"used":[7],"to":[8,28,39,65,74,96,118,130,139,155,216,237],"present":[9,205],"novel":[10,206],"augmentative":[11],"visual":[12,37,57,80],"experiences":[13],"by":[14],"processing":[15,84,121,190,243],"video":[16],"frames":[17],"for":[18,30,45,86,123,162,245],"viewers.":[19],"Among":[20],"VST":[21],"AR":[22],"systems,":[23],"assistive":[24,52,87,124,202,249],"vision":[25,32,47,83,120,166,172,189,221,242,247],"displays":[26,53,88],"aim":[27],"compensate":[29],"low":[31],"or":[33,248],"blindness,":[34],"presenting":[35],"enhanced":[36],"information":[38,58],"support":[40,217],"activities":[41],"of":[42,72,106,147,159,226,234,240],"daily":[43],"living":[44],"the":[46,70,104,145,224,231,238],"impaired/deprived.":[48],"Despite":[49],"progress,":[50],"current":[51],"suffer":[54],"from":[55,210],"a":[56,116,134,152,187,197],"bottleneck,":[59],"limiting":[60],"their":[61],"functional":[62],"outcomes":[63],"compared":[64],"healthy":[66],"vision.":[67],"This":[68,101,183],"motivates":[69],"exploration":[71],"methods":[73],"selectively":[75,128],"enhance":[76],"and":[77,98,111,176,195],"augment":[78],"salient":[79],"information.":[81],"Traditionally,":[82],"pipelines":[85,122,244],"rely":[89],"on":[90],"hand-crafted,":[91],"single-modality":[92],"filters,":[93],"lacking":[94],"adaptability":[95],"time-varying":[97],"environment-dependent":[99],"needs.":[100],"article":[102,184],"proposes":[103],"use":[105],"Deep":[107],"Reinforcement":[108],"Learning":[109],"(DRL)":[110],"Self-attention":[112],"(SA)":[113],"networks":[114,127,150,236],"as":[115],"means":[117],"learn":[119],"displays.":[125,167,203,250],"SA":[126,149,211],"attend":[129],"task-relevant":[131],"features,":[132],"offering":[133],"more":[135],"parameter\u2014and":[136],"compute-efficient":[137],"approach":[138],"RL-based":[140],"task":[141,239],"learning.":[142],"We":[143,168,204],"assess":[144],"feasibility":[146],"using":[148,179,192],"in":[151],"simulation-trained":[153],"model":[154],"generate":[156],"relevant":[157],"representations":[158],"real-world":[160],"states":[161],"navigation":[163],"with":[164,219],"prosthetic":[165,171,220,246],"explore":[169],"two":[170],"applications,":[173],"vision-to-auditory":[174],"encoding,":[175],"retinal":[177],"prostheses,":[178],"simulated":[180],"phosphene":[181],"visualisations.":[182],"introduces":[185],"SA-px,":[186],"general-purpose":[188],"pipeline":[191],"self-attention":[193,235],"networks,":[194],"SA-phos,":[196],"display-specific":[198],"formulation":[199],"targeting":[200],"low-resolution":[201],"scene":[207],"visualisations":[208],"derived":[209],"image":[212],"patches":[213],"importance":[214],"rankings":[215],"mobility":[218],"devices.":[222],"To":[223],"best":[225],"our":[227],"knowledge,":[228],"this":[229],"first":[232],"application":[233],"learning":[241]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}