{"id":"https://openalex.org/W4402112257","doi":"https://doi.org/10.21437/interspeech.2024-978","title":"MaViLS, a Benchmark Dataset for Video-to-Slide Alignment, Assessing Baseline Accuracy with a Multimodal Alignment Algorithm Leveraging Speech, OCR, and Visual Features","display_name":"MaViLS, a Benchmark Dataset for Video-to-Slide Alignment, Assessing Baseline Accuracy with a Multimodal Alignment Algorithm Leveraging Speech, OCR, and Visual Features","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112257","doi":"https://doi.org/10.21437/interspeech.2024-978"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-978","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.16765","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093585737","display_name":"Katharina Anderer","orcid":"https://orcid.org/0009-0004-2100-0998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katharina Anderer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009241202","display_name":"Andreas Reich","orcid":"https://orcid.org/0000-0002-2426-6490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Reich","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064051745","display_name":"Matthias W\u00f6lfel","orcid":"https://orcid.org/0000-0003-1601-5146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias W\u00f6lfel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4139,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5993947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1375","last_page":"1379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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":0.9994000196456909,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9948999881744385,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9894000291824341,"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":0.8164960145950317},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7615925073623657},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7109944820404053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6593396067619324},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5738810896873474},{"id":"https://openalex.org/keywords/scale-invariant-feature-transform","display_name":"Scale-invariant feature transform","score":0.5567267537117004},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4860868752002716},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4698604345321655},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3835797607898712},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3790656328201294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3728804588317871},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06747668981552124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164960145950317},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7615925073623657},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7109944820404053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593396067619324},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5738810896873474},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.5567267537117004},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4860868752002716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4698604345321655},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3835797607898712},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3790656328201294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3728804588317871},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06747668981552124},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-978","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.16765","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16765","pdf_url":"https://arxiv.org/pdf/2409.16765","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.16765","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16765","pdf_url":"https://arxiv.org/pdf/2409.16765","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","license_id":"https://openalex.org/licenses/cc-by","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/W4402112257.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3034955165","https://openalex.org/W2094920358","https://openalex.org/W2041448692","https://openalex.org/W2247121321","https://openalex.org/W2391926582","https://openalex.org/W2087391438","https://openalex.org/W1966831329","https://openalex.org/W2316074893","https://openalex.org/W2617958085","https://openalex.org/W2049930962"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,15,76],"benchmark":[4],"dataset":[5],"for":[6,94],"aligning":[7],"lecture":[8,119],"videos":[9],"with":[10,115],"corresponding":[11],"slides":[12],"and":[13,24,96,118],"introduces":[14],"novel":[16,122],"multimodal":[17,123],"algorithm":[18,48,124],"leveraging":[19],"features":[20],"from":[21],"speech,":[22],"text,":[23],"images.":[25],"It":[26],"achieves":[27],"an":[28],"average":[29],"accuracy":[30,107],"of":[31,129,135],"0.82":[32],"in":[33,105],"comparison":[34],"to":[35,50,75,127],"SIFT":[36],"(0.56)":[37],"while":[38],"being":[39],"approximately":[40],"11":[41],"times":[42],"faster.":[43],"Using":[44],"dynamic":[45],"programming":[46],"the":[47,52,73,112,133,136],"tries":[49],"determine":[51],"optimal":[53],"slide":[54,61],"sequence.":[55],"The":[56,84,121],"results":[57],"show":[58],"that":[59,87],"penalizing":[60],"transitions":[62],"increases":[63],"accuracy.":[64],"Features":[65],"obtained":[66],"via":[67],"optical":[68],"character":[69],"recognition":[70],"(OCR)":[71],"contribute":[72],"most":[74],"high":[77],"matching":[78,106],"accuracy,":[79],"followed":[80],"by":[81],"image":[82],"features.":[83],"findings":[85],"highlight":[86,111],"audio":[88],"transcripts":[89],"alone":[90],"provide":[91],"valuable":[92],"information":[93],"alignment":[95],"are":[97],"beneficial":[98],"if":[99],"OCR":[100],"data":[101],"is":[102],"lacking.":[103],"Variations":[104],"across":[108],"different":[109],"lectures":[110],"challenges":[113],"associated":[114],"video":[116],"quality":[117],"style.":[120],"demonstrates":[125],"robustness":[126],"some":[128],"these":[130],"challenges,":[131],"underscoring":[132],"potential":[134],"approach.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}