{"id":"https://openalex.org/W4399418371","doi":"https://doi.org/10.1145/3652583.3658055","title":"CMFF-Face: Attention-Based Cross-Modal Feature Fusion for High-Quality Audio-Driven Talking Face Generation","display_name":"CMFF-Face: Attention-Based Cross-Modal Feature Fusion for High-Quality Audio-Driven Talking Face Generation","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418371","doi":"https://doi.org/10.1145/3652583.3658055"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658055","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658055","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008495824","display_name":"Guangzhe Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I62853816","display_name":"Beijing University of Civil Engineering and Architecture","ror":"https://ror.org/02yj0p855","country_code":"CN","type":"education","lineage":["https://openalex.org/I62853816"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guangzhe Zhao","raw_affiliation_strings":["School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6850-9335","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China","institution_ids":["https://openalex.org/I62853816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103172687","display_name":"Yanan Liu","orcid":"https://orcid.org/0009-0005-2646-4465"},"institutions":[{"id":"https://openalex.org/I62853816","display_name":"Beijing University of Civil Engineering and Architecture","ror":"https://ror.org/02yj0p855","country_code":"CN","type":"education","lineage":["https://openalex.org/I62853816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanan Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, BeiJing, China"],"raw_orcid":"https://orcid.org/0009-0005-2646-4465","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, BeiJing, China","institution_ids":["https://openalex.org/I62853816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069859216","display_name":"Xueping Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I62853816","display_name":"Beijing University of Civil Engineering and Architecture","ror":"https://ror.org/02yj0p855","country_code":"CN","type":"education","lineage":["https://openalex.org/I62853816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueping Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8987-7578","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China","institution_ids":["https://openalex.org/I62853816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083521757","display_name":"Feihu Yan","orcid":"https://orcid.org/0000-0003-0821-3345"},"institutions":[{"id":"https://openalex.org/I62853816","display_name":"Beijing University of Civil Engineering and Architecture","ror":"https://ror.org/02yj0p855","country_code":"CN","type":"education","lineage":["https://openalex.org/I62853816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feihu Yan","raw_affiliation_strings":["School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0821-3345","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China","institution_ids":["https://openalex.org/I62853816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008495824"],"corresponding_institution_ids":["https://openalex.org/I62853816"],"apc_list":null,"apc_paid":null,"fwci":0.3288,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50060966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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/T11448","display_name":"Face recognition and analysis","score":0.9970999956130981,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9837999939918518,"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":0.8169724941253662},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6146456599235535},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5985351800918579},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5926870703697205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5761864185333252},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4936326742172241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4845649302005768},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4253658056259155},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.42456716299057007},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4199657440185547},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34616562724113464},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33710527420043945},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07576116919517517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169724941253662},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6146456599235535},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5985351800918579},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5926870703697205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5761864185333252},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4936326742172241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4845649302005768},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4253658056259155},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.42456716299057007},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4199657440185547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34616562724113464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33710527420043945},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07576116919517517},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658055","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658055","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418371.pdf","grobid_xml":"https://content.openalex.org/works/W4399418371.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2133665775","https://openalex.org/W2594690981","https://openalex.org/W2596627958","https://openalex.org/W2765811365","https://openalex.org/W2806833697","https://openalex.org/W2890952074","https://openalex.org/W2914217321","https://openalex.org/W2914393402","https://openalex.org/W2944294033","https://openalex.org/W2963307811","https://openalex.org/W2963981733","https://openalex.org/W2964559396","https://openalex.org/W2981767644","https://openalex.org/W2996833883","https://openalex.org/W3007485446","https://openalex.org/W3034257218","https://openalex.org/W3081492798","https://openalex.org/W3094502228","https://openalex.org/W3094897602","https://openalex.org/W3101631197","https://openalex.org/W3106783908","https://openalex.org/W3135367836","https://openalex.org/W3172863135","https://openalex.org/W3174906557","https://openalex.org/W3181255780","https://openalex.org/W3186090335","https://openalex.org/W3186678815","https://openalex.org/W3195529437","https://openalex.org/W3197199219","https://openalex.org/W3205904637","https://openalex.org/W4200630629","https://openalex.org/W4200631136","https://openalex.org/W4283818626","https://openalex.org/W4310379947","https://openalex.org/W4311137635","https://openalex.org/W4318906029","https://openalex.org/W4319301061","https://openalex.org/W4381598461","https://openalex.org/W4385626247","https://openalex.org/W4386065999","https://openalex.org/W4386066256","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4386076504","https://openalex.org/W6739901393","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W2366944513","https://openalex.org/W4312090303"],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,46,82],"face":[2,8,15,31,77,109],"generation":[3],"creates":[4],"lip-synchronized":[5],"and":[6,13,30,76,108,125,139,154],"high-quality":[7,81],"videos":[9],"from":[10],"given":[11],"audio":[12,29,75,107],"target":[14],"images,":[16],"which":[17,59,95],"is":[18,89],"a":[19,54,61,85,97,115],"challenging":[20],"task":[21],"due":[22],"to":[23,79,91,101,129],"the":[24,103,131,137,147],"inherent":[25],"modal":[26],"gap":[27],"between":[28,105,123],"images.":[32],"To":[33],"address":[34],"this":[35],"issue,":[36],"we":[37,52,113],"propose":[38],"an":[39],"attention-based":[40],"Cross-Modal":[41],"Feature":[42],"Fusion":[43],"network":[44],"for":[45,70],"Face":[47],"generation,":[48],"called":[49],"CMFF-Face.":[50],"Specifically,":[51],"introduce":[53],"cross-modal":[55],"feature":[56],"fusion":[57,62],"generator,":[58],"incorporates":[60],"process":[63],"in":[64,149],"each":[65],"convolutional":[66],"encoder":[67],"layer,":[68],"allowing":[69],"layer-wise":[71],"fusing":[72],"of":[73,151],"interactive":[74],"features":[78],"generate":[80],"faces.":[83],"Additionally,":[84],"lip":[86,132,152],"synchronization":[87,118,153],"discriminator":[88],"designed":[90],"improve":[92],"audio-lip":[93,117],"synchronization,":[94],"uses":[96],"two-branch":[98],"cross-attention":[99],"mechanism":[100],"capture":[102],"associations":[104],"synchronized":[106],"more":[110],"effectively.":[111],"Finally,":[112],"employ":[114],"CLIP-based":[116],"loss":[119],"that":[120,143],"helps":[121],"distinguish":[122],"positive":[124],"negative":[126],"sample":[127],"pairs":[128],"enhance":[130],"synchronization.":[133],"Comprehensive":[134],"experiments":[135],"on":[136],"LRS2":[138],"LRW":[140],"datasets":[141],"demonstrate":[142],"our":[144],"method":[145],"outperforms":[146],"state-of-the-arts":[148],"terms":[150],"visual":[155],"quality.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}