{"id":"https://openalex.org/W4415538300","doi":"https://doi.org/10.1145/3746027.3754584","title":"VisAug: Facilitating Speech-Rich Web Video Navigation and Engagement with Auto-Generated Visual Augmentations","display_name":"VisAug: Facilitating Speech-Rich Web Video Navigation and Engagement with Auto-Generated Visual Augmentations","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538300","doi":"https://doi.org/10.1145/3746027.3754584"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754584","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.03410","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102379113","display_name":"Baoquan Zhao","orcid":"https://orcid.org/0000-0002-0574-1663"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baoquan Zhao","raw_affiliation_strings":["Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0002-0574-1663","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091598240","display_name":"Xiaofan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofan Ma","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-1555-7279","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120131822","display_name":"Qianshi Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianshi Pang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-7702-7897","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000079751","display_name":"Ruomei Wang","orcid":"https://orcid.org/0000-0002-2712-4412"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruomei Wang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2712-4412","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090896025","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0002-0400-9366"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0400-9366","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101122545","display_name":"Shujin Lin","orcid":"https://orcid.org/0000-0002-9871-4014"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujin Lin","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9871-4014","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102379113"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28755499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9168","last_page":"9176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958000183105469,"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/contrast","display_name":"Contrast (vision)","score":0.3598000109195709},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35929998755455017},{"id":"https://openalex.org/keywords/consumption","display_name":"Consumption (sociology)","score":0.35850000381469727},{"id":"https://openalex.org/keywords/digital-video","display_name":"Digital video","score":0.3490999937057495},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.30880001187324524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508999705314636},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.6484000086784363},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3598000109195709},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2988454689","wikidata":"https://www.wikidata.org/wiki/Q173131","display_name":"Digital video","level":3,"score":0.3490999937057495},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C2984870255","wikidata":"https://www.wikidata.org/wiki/Q5196451","display_name":"User engagement","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2776509796","wikidata":"https://www.wikidata.org/wiki/Q5276056","display_name":"Content creation","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754584","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.03410","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03410","pdf_url":"https://arxiv.org/pdf/2508.03410","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:oai:arXiv.org:2508.03410","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03410","pdf_url":"https://arxiv.org/pdf/2508.03410","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2172261022","https://openalex.org/W2767156303","https://openalex.org/W2796075754","https://openalex.org/W2965576093","https://openalex.org/W3003182440","https://openalex.org/W3007452718","https://openalex.org/W3032941059","https://openalex.org/W3093732029","https://openalex.org/W3198377975","https://openalex.org/W4298157095","https://openalex.org/W4312514481","https://openalex.org/W4313547873","https://openalex.org/W4362735599","https://openalex.org/W4366547453","https://openalex.org/W4366548996","https://openalex.org/W4386076027","https://openalex.org/W4387969545","https://openalex.org/W4388187930","https://openalex.org/W4390872421"],"related_works":[],"abstract_inverted_index":{"The":[0],"widespread":[1],"adoption":[2],"of":[3,12,18,65,120,138],"digital":[4,13,144],"technology":[5],"has":[6,128],"ushered":[7],"in":[8,41,140],"a":[9,38,95],"new":[10],"era":[11],"transformation":[14],"across":[15],"all":[16],"aspects":[17],"our":[19],"lives.":[20],"Online":[21],"learning,":[22],"social,":[23],"and":[24,33,86,105,111,136],"work":[25],"activities,":[26],"such":[27,51],"as":[28,52],"distance":[29],"education,":[30],"videoconferencing,":[31],"interviews,":[32],"talks,":[34],"have":[35],"led":[36],"to":[37,47,100,131],"dramatic":[39],"increase":[40],"speech-rich":[42,61,102],"video":[43,49,83,103],"content.":[44],"In":[45,89],"contrast":[46],"other":[48],"types,":[50],"surveillance":[53],"footage,":[54],"which":[55],"typically":[56],"contain":[57],"abundant":[58],"visual":[59,113],"cues,":[60],"videos":[62],"convey":[63],"most":[64],"their":[66],"meaningful":[67],"information":[68,139],"through":[69],"the":[70,117,129,134],"audio":[71],"channel.":[72],"This":[73],"poses":[74],"challenges":[75],"for":[76],"improving":[77],"content":[78,119],"consumption":[79,135],"using":[80],"existing":[81],"visual-based":[82],"summarization,":[84],"navigation,":[85],"exploration":[87],"systems.":[88],"this":[90,126],"paper,":[91],"we":[92],"present":[93],"VisAug,":[94],"novel":[96],"interactive":[97],"system":[98,127],"designed":[99],"enhance":[101,133],"navigation":[104],"engagement":[106,137],"by":[107],"automatically":[108],"generating":[109],"informative":[110],"expressive":[112],"augmentations":[114],"based":[115],"on":[116],"speech":[118],"videos.":[121],"Our":[122],"findings":[123],"suggest":[124],"that":[125],"potential":[130],"significantly":[132],"an":[141],"increasingly":[142],"video-driven":[143],"landscape.":[145]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}
