{"id":"https://openalex.org/W3024979138","doi":"https://doi.org/10.1109/wacv45572.2020.9093345","title":"AlignNet: A Unifying Approach to Audio-Visual Alignment","display_name":"AlignNet: A Unifying Approach to Audio-Visual Alignment","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3024979138","doi":"https://doi.org/10.1109/wacv45572.2020.9093345","mag":"3024979138"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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/A5102939225","display_name":"Jianren Wang","orcid":"https://orcid.org/0000-0001-9350-1813"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jianren Wang","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102739579","display_name":"Zhaoyuan Fang","orcid":"https://orcid.org/0000-0002-6671-3279"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaoyuan Fang","raw_affiliation_strings":["University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101826600","display_name":"Hang Zhao","orcid":"https://orcid.org/0009-0002-8690-415X"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102939225"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7884,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94121132,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3298","last_page":"3306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9968000054359436,"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":0.7849814891815186},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5771823525428772},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5654444694519043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5345785617828369},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.467984676361084},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.46495234966278076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46047747135162354},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39022982120513916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34505462646484375},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.323864221572876},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13080641627311707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7849814891815186},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5771823525428772},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5654444694519043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5345785617828369},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.467984676361084},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.46495234966278076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46047747135162354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39022982120513916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34505462646484375},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.323864221572876},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13080641627311707},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1988910659","https://openalex.org/W2020677283","https://openalex.org/W2025013471","https://openalex.org/W2042608483","https://openalex.org/W2082942761","https://openalex.org/W2098432798","https://openalex.org/W2101306910","https://openalex.org/W2114127405","https://openalex.org/W2118877769","https://openalex.org/W2150696241","https://openalex.org/W2152758153","https://openalex.org/W2434537049","https://openalex.org/W2461047981","https://openalex.org/W2604379605","https://openalex.org/W2623638694","https://openalex.org/W2726515241","https://openalex.org/W2796992393","https://openalex.org/W2808631503","https://openalex.org/W2811167645","https://openalex.org/W2886564777","https://openalex.org/W2903831537","https://openalex.org/W2936774411","https://openalex.org/W2950864153","https://openalex.org/W2962730651","https://openalex.org/W2962795401","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963065614","https://openalex.org/W2963782415","https://openalex.org/W2963786016","https://openalex.org/W2981851635","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6647338662","https://openalex.org/W6682511423","https://openalex.org/W6735927292","https://openalex.org/W6750591037","https://openalex.org/W6750599028","https://openalex.org/W6755192476","https://openalex.org/W6756633688","https://openalex.org/W6757240503","https://openalex.org/W6764376812","https://openalex.org/W6993097538"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698","https://openalex.org/W2130799169","https://openalex.org/W2340348677"],"abstract_inverted_index":{"We":[0],"present":[1],"AlignNet,":[2],"a":[3,25,54],"model":[4],"that":[5,75],"synchronizes":[6],"videos":[7,88],"with":[8,49],"reference":[9],"audios":[10],"undernon-uniform":[11],"and":[12,27,37,45,60,64,71,86],"irregularmis-":[13],"alignments.":[14],"AlignNet":[15],"learns":[16],"the":[17,50,80],"end-to-end":[18],"dense":[19],"correspondence":[20],"between":[21],"each":[22],"frame":[23],"of":[24],"video":[26],"an":[28],"audio.":[29],"Our":[30],"method":[31,77],"is":[32],"designed":[33],"according":[34],"to":[35],"simple":[36],"well-":[38],"established":[39],"principles:":[40],"attention,":[41],"pyramidal":[42],"processing,":[43],"warping,":[44],"affinity":[46],"function.":[47],"Together":[48],"model,":[51],"we":[52],"release":[53],"dancing":[55],"dataset":[56,85],"Dance50":[57],"for":[58],"training":[59],"evaluation.":[61],"Qualitative,":[62],"quantitative":[63],"subjective":[65],"evaluation":[66],"results":[67],"on":[68],"dance-music":[69],"alignment":[70,73],"speech-lip":[72],"demonstrate":[74],"our":[76,92],"far":[78],"outperforms":[79],"state-of-":[81],"the-art":[82],"methods.":[83],"Code,":[84],"sample":[87],"are":[89],"available":[90],"at":[91],"project":[93],"page":[94],"<sup":[95],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[96],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[97],".":[98]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}