{"id":"https://openalex.org/W4402427038","doi":"https://doi.org/10.1145/3654777.3676375","title":"WorldScribe: Towards Context-Aware Live Visual Descriptions","display_name":"WorldScribe: Towards Context-Aware Live Visual Descriptions","publication_year":2024,"publication_date":"2024-10-11","ids":{"openalex":"https://openalex.org/W4402427038","doi":"https://doi.org/10.1145/3654777.3676375"},"language":"en","primary_location":{"id":"doi:10.1145/3654777.3676375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654777.3676375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.06627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008164265","display_name":"Ruei-Che Chang","orcid":"https://orcid.org/0000-0001-7545-4136"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210111179","display_name":"Michigan United","ror":"https://ror.org/0291ys696","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210111179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruei-Che Chang","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan, United States"],"raw_orcid":"https://orcid.org/0000-0001-7545-4136","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan, United States","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210111179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460407","display_name":"Yuxuan Liu","orcid":"https://orcid.org/0000-0002-3040-9857"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210111179","display_name":"Michigan United","ror":"https://ror.org/0291ys696","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210111179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Liu","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan, United States"],"raw_orcid":"https://orcid.org/0009-0005-5023-1426","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan, United States","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210111179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021329493","display_name":"Anhong Guo","orcid":"https://orcid.org/0000-0002-4447-7818"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210111179","display_name":"Michigan United","ror":"https://ror.org/0291ys696","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210111179"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anhong Guo","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan, United States"],"raw_orcid":"https://orcid.org/0000-0002-4447-7818","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan, United States","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210111179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021329493"],"corresponding_institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210111179"],"apc_list":null,"apc_paid":null,"fwci":10.4631,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.98950291,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9983000159263611,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9932000041007996,"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/computer-science","display_name":"Computer science","score":0.7470793128013611},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5970913171768188},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3325199484825134},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08982682228088379}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470793128013611},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5970913171768188},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3325199484825134},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08982682228088379},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3654777.3676375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654777.3676375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.06627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.06627","pdf_url":"https://arxiv.org/pdf/2408.06627","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/198598","is_oa":false,"landing_page_url":"https://hdl.handle.net/2027.42/198598","pdf_url":null,"source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.06627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.06627","pdf_url":"https://arxiv.org/pdf/2408.06627","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402427038.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W144701237","https://openalex.org/W1861492603","https://openalex.org/W1969088462","https://openalex.org/W2022450171","https://openalex.org/W2059214800","https://openalex.org/W2090048052","https://openalex.org/W2116680608","https://openalex.org/W2128597132","https://openalex.org/W2508778727","https://openalex.org/W2518014185","https://openalex.org/W2748163013","https://openalex.org/W2789636240","https://openalex.org/W2790378580","https://openalex.org/W2820151110","https://openalex.org/W2913974265","https://openalex.org/W2940779895","https://openalex.org/W2983943451","https://openalex.org/W2998746484","https://openalex.org/W3029105705","https://openalex.org/W3029394045","https://openalex.org/W3030405946","https://openalex.org/W3030476761","https://openalex.org/W3031694810","https://openalex.org/W3032743533","https://openalex.org/W3042120022","https://openalex.org/W3093730614","https://openalex.org/W3094385957","https://openalex.org/W3096896486","https://openalex.org/W3118890732","https://openalex.org/W3160539989","https://openalex.org/W3169318522","https://openalex.org/W3193699827","https://openalex.org/W3207136799","https://openalex.org/W3207801264","https://openalex.org/W4224993535","https://openalex.org/W4286904999","https://openalex.org/W4293112598","https://openalex.org/W4296784407","https://openalex.org/W4307136615","https://openalex.org/W4307475429","https://openalex.org/W4312420092","https://openalex.org/W4366548995","https://openalex.org/W4366551164","https://openalex.org/W4366729076","https://openalex.org/W4385572843","https://openalex.org/W4387793209","https://openalex.org/W4387793554","https://openalex.org/W4387793598","https://openalex.org/W4387793681","https://openalex.org/W4387801394","https://openalex.org/W4391940741","https://openalex.org/W4400142589","https://openalex.org/W4402427035","https://openalex.org/W4403576862"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Automated":[0],"live":[1,43,201],"visual":[2,45,74,152,177,202],"descriptions":[3,18,46,57,80,153,178,203],"can":[4,171],"aid":[5],"blind":[6,159],"people":[7],"in":[8,30,103],"understanding":[9,182],"their":[10,133],"surroundings":[11],"with":[12,158],"autonomy":[13],"and":[14,23,50,63,87,118,135,154,164,174,186,196,206],"independence.":[15],"However,":[16],"providing":[17,77,151],"that":[19,40,47,128,169,183],"are":[20,48,58],"rich,":[21],"contextual,":[22],"just-in-time":[24],"has":[25],"been":[26],"a":[27,38,113,124,155],"long-standing":[28],"challenge":[29],"accessibility.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,192],"develop":[36],"WorldScribe,":[37],"system":[39],"generates":[41],"automated":[42],"real-world":[44],"customizable":[49],"adaptive":[51,72,96,185],"to":[52,60,73,97,137,179,188],"users\u2019":[53,61,189],"contexts:":[54],"(i)":[55],"WorldScribe\u2019s":[56],"tailored":[59],"intents":[62],"prioritized":[64],"based":[65],"on":[66,150],"semantic":[67],"relevance.":[68],"(ii)":[69],"WorldScribe":[70,94,122,144,170],"is":[71,95,145,184],"contexts,":[75,99],"e.g.,":[76,100],"consecutively":[78],"succinct":[79],"for":[81,90],"dynamic":[82],"scenes,":[83],"while":[84],"presenting":[85],"longer":[86],"detailed":[88],"ones":[89],"stable":[91],"settings.":[92],"(iii)":[93],"sound":[98,119],"increasing":[101],"volume":[102],"noisy":[104],"environments,":[105],"or":[106],"pausing":[107],"when":[108],"conversations":[109],"start.":[110],"Powered":[111],"by":[112,147],"suite":[114],"of":[115,143],"vision,":[116],"language,":[117],"recognition":[120],"models,":[121],"introduces":[123],"description":[125],"generation":[126],"pipeline":[127,166],"balances":[129],"the":[130,194],"tradeoffs":[131],"between":[132],"richness":[134],"latency":[136],"support":[138],"real-time":[139,173],"use.":[140],"The":[141],"design":[142],"informed":[146],"prior":[148],"work":[149],"formative":[156],"study":[157,163],"participants.":[160],"Our":[161],"user":[162],"subsequent":[165],"evaluation":[167],"show":[168],"provide":[172],"fairly":[175],"accurate":[176],"facilitate":[180],"environment":[181],"customized":[187],"contexts.":[190],"Finally,":[191],"discuss":[193],"implications":[195],"further":[197],"steps":[198],"toward":[199],"making":[200],"more":[204],"context-aware":[205],"humanized.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}