{"id":"https://openalex.org/W4392904679","doi":"https://doi.org/10.1109/icassp48485.2024.10448489","title":"Synchformer: Efficient Synchronization From Sparse Cues","display_name":"Synchformer: Efficient Synchronization From Sparse Cues","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904679","doi":"https://doi.org/10.1109/icassp48485.2024.10448489"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5008909874","display_name":"Vladimir Iashin","orcid":"https://orcid.org/0000-0001-8879-587X"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Vladimir Iashin","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076097168","display_name":"Weidi Xie","orcid":"https://orcid.org/0000-0003-3804-2639"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["Shanghai Jiao Tong University","University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088180438","display_name":"Esa Rahtu","orcid":"https://orcid.org/0000-0001-8767-0864"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Esa Rahtu","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5325","last_page":"5329"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9943000078201294,"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/synchronization","display_name":"Synchronization (alternating current)","score":0.7920384407043457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7753289937973022},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7577952146530151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5613967776298523},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5338861346244812},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5331289768218994},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5198172330856323},{"id":"https://openalex.org/keywords/data-synchronization","display_name":"Data synchronization","score":0.47686776518821716},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41648536920547485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37703922390937805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36925333738327026},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3269493579864502}],"concepts":[{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.7920384407043457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753289937973022},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7577952146530151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5613967776298523},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5338861346244812},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5331289768218994},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5198172330856323},{"id":"https://openalex.org/C108734733","wikidata":"https://www.wikidata.org/wiki/Q1172333","display_name":"Data synchronization","level":3,"score":0.47686776518821716},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41648536920547485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37703922390937805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36925333738327026},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3269493579864502},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G8161891803","display_name":null,"funder_award_id":"EP/T028572/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W2100561338","https://openalex.org/W2164899449","https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2883429621","https://openalex.org/W2886564777","https://openalex.org/W2891205112","https://openalex.org/W2896457183","https://openalex.org/W2950864153","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W3096609285","https://openalex.org/W3116298410","https://openalex.org/W3172908893","https://openalex.org/W3196974791","https://openalex.org/W4287122452","https://openalex.org/W4297808394","https://openalex.org/W4297841713","https://openalex.org/W4375868826","https://openalex.org/W4385245566","https://openalex.org/W6675048546","https://openalex.org/W6684193366","https://openalex.org/W6739901393","https://openalex.org/W6754420807","https://openalex.org/W6755207826","https://openalex.org/W6756871312","https://openalex.org/W6776074830","https://openalex.org/W6790307280","https://openalex.org/W6791353385","https://openalex.org/W6810980340","https://openalex.org/W6844194202","https://openalex.org/W6845298728"],"related_works":["https://openalex.org/W2027357437","https://openalex.org/W2014622309","https://openalex.org/W2123134332","https://openalex.org/W2548702785","https://openalex.org/W2157126534","https://openalex.org/W2118487515","https://openalex.org/W2368252421","https://openalex.org/W1592820837","https://openalex.org/W78899842","https://openalex.org/W2158673508"],"abstract_inverted_index":{"Our":[0,22],"objective":[1],"is":[2],"audio-visual":[3,27,81],"synchronization":[4,17,28,37,58,79],"with":[5],"a":[6,25,63,75],"focus":[7],"on":[8,14],"\u2018in-the-wild\u2019":[9,65],"videos,":[10],"such":[11],"as":[12],"those":[13],"YouTube,":[15],"where":[16],"cues":[18],"can":[19],"be":[20],"sparse.":[21],"contributions":[23],"include":[24],"novel":[26],"model,":[29],"and":[30,52,73],"training":[31,60],"that":[32],"decouples":[33],"feature":[34],"extraction":[35],"from":[36],"modelling":[38],"through":[39],"multi-modal":[40],"segment-level":[41],"contrastive":[42],"pre-training.":[43],"This":[44],"approach":[45],"achieves":[46],"state-of-the-art":[47],"performance":[48],"in":[49],"both":[50],"dense":[51],"sparse":[53],"settings.":[54],"We":[55],"also":[56],"extend":[57],"model":[59],"to":[61],"AudioSet":[62],"million-scale":[64],"dataset,":[66],"investigate":[67],"evidence":[68],"attribution":[69],"techniques":[70],"for":[71,78],"interpretability,":[72],"explore":[74],"new":[76],"capability":[77],"models:":[80],"synchronizability.":[82],"robots.ox.ac.uk/~vgg/research/synchformer":[83]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}
