{"id":"https://openalex.org/W4308236451","doi":"https://doi.org/10.1109/icip46576.2022.9897436","title":"Autolv: Automatic Lecture Video Generator","display_name":"Autolv: Automatic Lecture Video Generator","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236451","doi":"https://doi.org/10.1109/icip46576.2022.9897436"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897436","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100329719","display_name":"Wenbin Wang","orcid":"https://orcid.org/0000-0001-9710-0136"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenbin Wang","raw_affiliation_strings":["University of New South Wales,School of Computer Science and Engineering,Australia","School of Computer Science and Engineering, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Computer Science and Engineering,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041567418","display_name":"Yang Song","orcid":"https://orcid.org/0000-0003-1283-1672"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Song","raw_affiliation_strings":["University of New South Wales,School of Computer Science and Engineering,Australia","School of Computer Science and Engineering, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Computer Science and Engineering,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068053166","display_name":"Sanjay Jha","orcid":"https://orcid.org/0000-0002-1531-1798"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sanjay Jha","raw_affiliation_strings":["University of New South Wales,School of Computer Science and Engineering,Australia","School of Computer Science and Engineering, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,School of Computer Science and Engineering,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68011328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1086","last_page":"1090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9983000159263611,"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":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8473445177078247},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8169469833374023},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.7064740657806396},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6672448515892029},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5233494639396667},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5217854976654053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4566667377948761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4526826739311218},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4479396939277649},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4466986060142517},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4309430420398712},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.420301228761673},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11176499724388123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8473445177078247},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8169469833374023},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.7064740657806396},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6672448515892029},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5233494639396667},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5217854976654053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4566667377948761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4526826739311218},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4479396939277649},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4466986060142517},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4309430420398712},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.420301228761673},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11176499724388123},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897436","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2093107730","https://openalex.org/W2094721231","https://openalex.org/W2153914468","https://openalex.org/W2604379605","https://openalex.org/W2612434969","https://openalex.org/W2738406145","https://openalex.org/W2767052532","https://openalex.org/W2808631503","https://openalex.org/W2889028433","https://openalex.org/W2954667816","https://openalex.org/W2962788625","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2964982818","https://openalex.org/W2972610613","https://openalex.org/W3016159759","https://openalex.org/W3016889017","https://openalex.org/W3019952993","https://openalex.org/W3024747869","https://openalex.org/W3081492798","https://openalex.org/W3097538987","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3174758275","https://openalex.org/W3186090335","https://openalex.org/W3197507772","https://openalex.org/W6737575990","https://openalex.org/W6739901393","https://openalex.org/W6748181857","https://openalex.org/W6748409065","https://openalex.org/W6748573829","https://openalex.org/W6748588790","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6777445600","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751","https://openalex.org/W2017702615"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,43],"end-to-end":[3],"lecture":[4,14,72,81],"video":[5,105],"generation":[6,47],"system":[7,29,110],"that":[8,87],"can":[9,66],"generate":[10],"realistic":[11],"and":[12,23,42,63,75,100,112,118],"complete":[13],"videos":[15],"directly":[16],"from":[17],"annotated":[18],"slides,":[19],"instructor\u2019s":[20,24],"reference":[21,25],"voice":[22],"portrait":[26],"video.":[27],"Our":[28,83],"is":[30,50,103],"primarily":[31],"composed":[32],"of":[33,52,80,97,107,115],"a":[34,77,104],"speech":[35],"synthesis":[36],"module":[37],"with":[38],"few-shot":[39],"speaker":[40],"adaptation":[41],"adversarial":[44],"learning-based":[45],"talking-head":[46],"module.":[48],"It":[49],"capable":[51],"not":[53],"only":[54],"reducing":[55],"instructors\u2019":[56],"workload":[57],"but":[58],"also":[59],"changing":[60],"the":[61,68,71,88,113,116],"language":[62],"accent":[64],"which":[65],"help":[67],"students":[69],"follow":[70],"more":[73],"easily":[74],"enable":[76],"wider":[78],"dissemination":[79],"contents.":[82],"experimental":[84],"results":[85],"show":[86],"proposed":[89],"model":[90],"outperforms":[91],"other":[92],"current":[93],"approaches":[94],"in":[95],"terms":[96],"authenticity,":[98],"naturalness":[99],"accuracy.":[101],"Here":[102],"demonstration":[106],"how":[108],"our":[109],"works,":[111],"outcomes":[114],"evaluation":[117],"comparison:":[119],"https://youtu.be/cY6TYkI0cog.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}