{"id":"https://openalex.org/W4399261569","doi":"https://doi.org/10.1145/3643491.3660287","title":"Visual and audio scene classification for detecting discrepancies in video: a baseline method and experimental protocol","display_name":"Visual and audio scene classification for detecting discrepancies in video: a baseline method and experimental protocol","publication_year":2024,"publication_date":"2024-06-01","ids":{"openalex":"https://openalex.org/W4399261569","doi":"https://doi.org/10.1145/3643491.3660287"},"language":"en","primary_location":{"id":"doi:10.1145/3643491.3660287","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643491.3660287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3rd ACM International Workshop on Multimedia AI against Disinformation","raw_type":"proceedings-article"},"type":"article","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/A5089757074","display_name":"Konstantinos Apostolidis","orcid":"https://orcid.org/0000-0002-9470-6332"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Apostolidis","raw_affiliation_strings":["Information Technologies Institute, CERTH, Greece"],"raw_orcid":"https://orcid.org/0000-0002-9470-6332","affiliations":[{"raw_affiliation_string":"Information Technologies Institute, CERTH, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047532715","display_name":"Jakob Abe\u00dfer","orcid":"https://orcid.org/0000-0003-4689-7944"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakob Abesser","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4689-7944","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004017099","display_name":"Luca Cuccovillo","orcid":"https://orcid.org/0000-0001-5559-6508"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luca Cuccovillo","raw_affiliation_strings":["Fraunhofer Institute for Digital Media Technology, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5559-6508","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059096027","display_name":"Vasileios Mezaris","orcid":"https://orcid.org/0000-0002-0121-4364"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vasileios Mezaris","raw_affiliation_strings":["Information Technologies Institute, CERTH, Greece"],"raw_orcid":"https://orcid.org/0000-0002-0121-4364","affiliations":[{"raw_affiliation_string":"Information Technologies Institute, CERTH, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9172,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71704913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"30","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9984999895095825,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9973000288009644,"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/baseline","display_name":"Baseline (sea)","score":0.8117749691009521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7452830076217651},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.6388500332832336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5375350117683411},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4145662188529968},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39669886231422424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3704853951931},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2601366639137268},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.09002909064292908}],"concepts":[{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.8117749691009521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452830076217651},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.6388500332832336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375350117683411},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4145662188529968},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39669886231422424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3704853951931},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2601366639137268},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.09002909064292908},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3643491.3660287","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643491.3660287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3rd ACM International Workshop on Multimedia AI against Disinformation","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/472888","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/472888","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2612690371","https://openalex.org/W2739424525","https://openalex.org/W2759976799","https://openalex.org/W2765520839","https://openalex.org/W2994728585","https://openalex.org/W2997076748","https://openalex.org/W3094550259","https://openalex.org/W3114232785","https://openalex.org/W3117322776","https://openalex.org/W3135367836","https://openalex.org/W3143835353","https://openalex.org/W3161541317"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2271369634","https://openalex.org/W3147472394"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,72,82],"baseline":[4],"approach":[5,89],"and":[6,21,30,55,70,81,96],"an":[7,32,78],"experimental":[8,79],"protocol":[9,80],"for":[10],"specific":[12],"content":[13,107],"verification":[14,108],"problem:":[15],"detecting":[16],"discrepancies":[17,101],"between":[18,64],"the":[19,53,56],"audio":[20,54],"video":[22],"modalities":[23],"in":[24,93,99,106],"multimedia":[25],"content.":[26],"We":[27],"first":[28],"design":[29],"optimize":[31],"audio-visual":[33,100],"scene":[34,94],"classifier,":[35],"to":[36,52],"compare":[37],"with":[38],"existing":[39],"classification":[40,95],"baselines":[41],"that":[42],"use":[43],"both":[44],"modalities.":[45],"Then,":[46],"by":[47],"applying":[48],"this":[49],"classifier":[50],"separately":[51],"visual":[57],"modality,":[58],"we":[59,76],"can":[60],"detect":[61],"scene-class":[62],"inconsistencies":[63],"them.":[65],"To":[66],"facilitate":[67],"further":[68],"research":[69],"provide":[71],"common":[73],"evaluation":[74],"platform,":[75],"introduce":[77],"benchmark":[83],"dataset":[84],"simulating":[85],"such":[86],"inconsistencies.":[87],"Our":[88],"achieves":[90],"state-of-the-art":[91],"results":[92],"promising":[97],"outcomes":[98],"detection,":[102],"highlighting":[103],"its":[104],"potential":[105],"applications.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
