{"id":"https://openalex.org/W4387451919","doi":"https://doi.org/10.1145/3611314.3615902","title":"Increasing Web3D Accessibility with Audio Captioning","display_name":"Increasing Web3D Accessibility with Audio Captioning","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387451919","doi":"https://doi.org/10.1145/3611314.3615902"},"language":"en","primary_location":{"id":"doi:10.1145/3611314.3615902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611314.3615902","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611314.3615902","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 28th International ACM Conference on 3D Web Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3611314.3615902","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080764655","display_name":"Nicholas F. Polys","orcid":"https://orcid.org/0000-0002-8503-970X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicholas Polys","raw_affiliation_strings":["Advanced Research Computing, Virginia Tech, USA"],"raw_orcid":"https://orcid.org/0000-0002-8503-970X","affiliations":[{"raw_affiliation_string":"Advanced Research Computing, Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093027641","display_name":"Sheeban Mohd Wasi","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheeban Mohd Wasi","raw_affiliation_strings":["Computer Science, Virginia Tech, USA"],"raw_orcid":"https://orcid.org/0009-0007-6200-4743","affiliations":[{"raw_affiliation_string":"Computer Science, Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080764655"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":6.3045,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96662274,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9955999851226807,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.983299970626831,"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/closed-captioning","display_name":"Closed captioning","score":0.9092454314231873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7898486852645874},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.46481165289878845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.424857497215271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16610699892044067}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9092454314231873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898486852645874},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.46481165289878845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.424857497215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16610699892044067},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3611314.3615902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611314.3615902","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611314.3615902","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 28th International ACM Conference on 3D Web Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/116608","is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/116608","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/321b9595-4661-474e-b7f8-939d637e212a/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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":"Text"}],"best_oa_location":{"id":"doi:10.1145/3611314.3615902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611314.3615902","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611314.3615902","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 28th International ACM Conference on 3D Web Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387451919.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1212821315","https://openalex.org/W1765238573","https://openalex.org/W1976830477","https://openalex.org/W2037227137","https://openalex.org/W2059742544","https://openalex.org/W2084879024","https://openalex.org/W2097117768","https://openalex.org/W2104617690","https://openalex.org/W2117539524","https://openalex.org/W2204026420","https://openalex.org/W2614403784","https://openalex.org/W2753626343","https://openalex.org/W2783674979","https://openalex.org/W2809629300","https://openalex.org/W2900701007","https://openalex.org/W2952020226","https://openalex.org/W2963037989","https://openalex.org/W2963948039","https://openalex.org/W2964427639","https://openalex.org/W2964874094","https://openalex.org/W2968951863","https://openalex.org/W3094535122","https://openalex.org/W3202733979","https://openalex.org/W4200190452","https://openalex.org/W4248570900","https://openalex.org/W4292826365","https://openalex.org/W4394642372"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Situational":[0],"awareness":[1,78],"plays":[2],"a":[3,46,65,91,99],"critical":[4],"role":[5],"in":[6,31,84,135],"daily":[7],"life,":[8],"enabling":[9],"individuals":[10,22,80],"to":[11,40,97],"comprehend":[12],"their":[13,33],"surroundings,":[14],"make":[15],"informed":[16],"decisions,":[17],"and":[18,55,86,111,126,140,143,151],"navigate":[19],"safely.":[20],"However,":[21],"with":[23,81],"low":[24],"vision":[25],"or":[26,35,109],"visual":[27,62,82],"impairments":[28,83],"face":[29],"difficulties":[30],"perceiving":[32],"real":[34],"virtual":[36,85],"environment.":[37],"In":[38],"order":[39],"address":[41],"this":[42],"challenge,":[43],"we":[44],"propose":[45],"3D":[47],"computer":[48],"vision-based":[49],"accessibility":[50,136],"solution,":[51],"empowered":[52],"by":[53],"object-detection":[54],"text-to-speech":[56],"technology.":[57],"Our":[58,128],"application":[59],"describes":[60],"the":[61,69,113,149,152],"content":[63],"of":[64,94,101,115,123],"Web3D":[66],"scene":[67],"from":[68],"user\u2019s":[70],"perspective":[71],"through":[72],"auditory":[73],"channels,":[74],"thereby":[75],"enhancing":[76],"situational":[77],"for":[79,103,137],"physical":[87],"environments.":[88],"We":[89],"conducted":[90],"user":[92,121],"study":[93,129],"44":[95],"participants":[96],"compare":[98],"set":[100],"algorithms":[102,118],"specific":[104],"tasks,":[105],"such":[106],"as":[107],"Search":[108],"Summarize,":[110],"assessed":[112],"effectiveness":[114],"our":[116],"captioning":[117,153],"based":[119],"on":[120],"ratings":[122],"naturalness,":[124],"correctness,":[125],"satisfaction.":[127],"results":[130,134],"indicate":[131],"positive":[132],"subjective":[133],"both":[138],"normal":[139],"visually-impaired":[141],"subjects":[142],"also":[144],"distinguish":[145],"significant":[146],"effects":[147],"between":[148],"task":[150],"algorithm.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}