{"id":"https://openalex.org/W4408347286","doi":"https://doi.org/10.1109/icassp49660.2025.10887999","title":"Layer-Animate for Transparent Video Generation","display_name":"Layer-Animate for Transparent Video Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347286","doi":"https://doi.org/10.1109/icassp49660.2025.10887999"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5064297082","display_name":"Jingqi Bai","orcid":"https://orcid.org/0009-0008-3770-9933"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingqi Bai","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034700567","display_name":"Jingkai Zhou","orcid":"https://orcid.org/0000-0003-4629-0659"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingkai Zhou","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026392735","display_name":"B. L. Wang","orcid":"https://orcid.org/0009-0004-7052-6849"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benzhi Wang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625507","display_name":"Weihua Chen","orcid":"https://orcid.org/0000-0002-0548-330X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weihua Chen","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397785","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0003-3389-0268"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109299788","display_name":"Zhen Lei","orcid":"https://orcid.org/0000-0002-0791-189X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Lei","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380570","display_name":"Fan Wang","orcid":"https://orcid.org/0000-0003-3591-9394"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Wang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5064297082"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06489925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9320999979972839,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9320999979972839,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10888","display_name":"Augmented Reality Applications","score":0.9266999959945679,"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/T13518","display_name":"Architecture and Computational Design","score":0.9153000116348267,"subfield":{"id":"https://openalex.org/subfields/2216","display_name":"Architecture"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6925991177558899},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5055229663848877},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.48102837800979614},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.38357096910476685},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07147243618965149}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6925991177558899},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5055229663848877},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.48102837800979614},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.38357096910476685},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07147243618965149},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2964024144","https://openalex.org/W3109908659","https://openalex.org/W3180355996","https://openalex.org/W4312933868","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4390872297","https://openalex.org/W4390873135","https://openalex.org/W4390873195","https://openalex.org/W4400819434","https://openalex.org/W4402660110","https://openalex.org/W4402727092","https://openalex.org/W4402774092","https://openalex.org/W4404527320","https://openalex.org/W4404965692","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6838639034","https://openalex.org/W6853300428"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Transparent":[0],"videos":[1,124],"with":[2,125],"alpha":[3],"channels":[4],"play":[5],"a":[6],"crucial":[7],"role":[8],"in":[9,43,71,139],"film":[10],"production,":[11],"advertising,":[12],"and":[13,32,34,49,86,131,141],"augmented":[14],"reality":[15],"fields.":[16],"However,":[17],"there":[18],"is":[19,99,116],"currently":[20],"no":[21,132],"available":[22],"method":[23,60,67,119],"for":[24,38,89],"producing":[25],"transparent":[26,45,64,75,123,127],"videos.":[27,65],"Traditional":[28],"methods":[29],"are":[30,77],"time-consuming":[31],"labor-intensive,":[33],"employing":[35],"alternative":[36],"approaches":[37],"this":[39],"task":[40],"will":[41],"result":[42],"inaccurate":[44],"regions,":[46,128],"constrained":[47],"motion,":[48,105,130],"artifacts.":[50],"To":[51],"address":[52],"these":[53],"challenges,":[54],"we":[55],"propose":[56],"Layer-Animate,":[57],"the":[58,72,80,90,94,107,117],"first":[59,73,118],"capable":[61],"of":[62],"generating":[63],"Our":[66],"comprises":[68],"two":[69],"stages:":[70],"stage,":[74,96],"images":[76,82],"generated":[78],"as":[79,134],"base":[81],"to":[83,101,110,121],"provide":[84],"content":[85,103],"transparency":[87],"information":[88],"next":[91],"stage.":[92],"In":[93],"second":[95],"Inter-Frame":[97],"Attention":[98],"applied":[100],"decouple":[102],"from":[104],"enabling":[106],"motion":[108],"module":[109],"focus":[111],"better":[112],"on":[113],"action.":[114],"Layer-Animate":[115],"used":[120],"generate":[122],"accurate":[126],"sufficient":[129],"artifacts,":[133],"demonstrated":[135],"by":[136],"notable":[137],"improvements":[138],"qualitative":[140],"quantitative":[142],"metrics.":[143]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}