{"id":"https://openalex.org/W4415536586","doi":"https://doi.org/10.1145/3746027.3755083","title":"EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation","display_name":"EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536586","doi":"https://doi.org/10.1145/3746027.3755083"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5103896576","display_name":"Jingzehua Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Xu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-7658-2959","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047326293","display_name":"Kunzhe Huang","orcid":"https://orcid.org/0009-0003-6047-2827"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunzhe Huang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-6047-2827","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyi Zou","orcid":"https://orcid.org/0009-0004-0628-3715"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Zou","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-0628-3715","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038701286","display_name":"Yunkuo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunkuo Chen","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-4691-8696","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Liu","orcid":"https://orcid.org/0009-0001-0405-3818"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-0405-3818","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengli Cheng","orcid":"https://orcid.org/0009-0007-7603-9787"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengli Cheng","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-7603-9787","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054621636","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0002-7706-7081"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7706-7081","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100534716","display_name":"Xing Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Shi","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-5946-3187","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25220563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10925","last_page":"10934"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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":0.9991999864578247,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6647999882698059},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5742999911308289},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4542999863624573},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.41769999265670776},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41620001196861267},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.3695000112056732},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3691999912261963},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.3547999858856201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8452000021934509},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6647999882698059},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5742999911308289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5037000179290771},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.41769999265670776},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.3695000112056732},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1755205674","https://openalex.org/W2967615747","https://openalex.org/W4312933868","https://openalex.org/W4390874575","https://openalex.org/W4402660110","https://openalex.org/W4402727736","https://openalex.org/W4402753770","https://openalex.org/W4404965447"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"EasyAnimate,":[3],"an":[4],"efficient":[5],"and":[6,26,47,54,149,174,217,221],"high":[7],"quality":[8],"video":[9,19,34,38,49,96,102],"generation":[10,39,45,103],"framework":[11],"that":[12,143],"leverages":[13],"diffusion":[14,35],"transformers":[15],"to":[16,85,111,132,163,191],"achieve":[17],"high-quality":[18],"production,":[20],"encompassing":[21],"data":[22],"processing,":[23],"model":[24,150,186],"training,":[25],"end-to-end":[27],"inference.":[28],"Despite":[29],"substantial":[30],"advancements":[31],"achieved":[32],"by":[33],"models,":[36],"existing":[37],"models":[40,223],"still":[41],"struggles":[42],"with":[43,114,160],"slow":[44],"speeds":[46],"less-than-ideal":[48],"quality.":[50],"To":[51,100],"improve":[52,145,192],"training":[53,156,169],"inference":[55],"efficiency":[56,148],"without":[57],"compromising":[58],"performance,":[59],"we":[60,105,180],"propose":[61],"Hybrid":[62,73],"Window":[63,74],"Attention.":[64],"We":[65,152],"design":[66],"the":[67,90,95,124,133,188,196,204,214],"multidirectional":[68],"sliding":[69],"window":[70],"attention":[71],"in":[72,81,168],"Attention,":[75],"which":[76],"provides":[77],"stronger":[78],"receptive":[79],"capabilities":[80],"3D":[82],"dimensions":[83],"compared":[84],"naive":[86],"one,":[87],"while":[88,127],"reducing":[89],"model's":[91,125],"computational":[92,147],"complexity":[93],"as":[94,187],"sequence":[97],"length":[98],"increases.":[99],"enhance":[101],"quality,":[104],"optimize":[106],"EasyAnimate":[107,136,208],"using":[108],"reward":[109],"backpropagation":[110],"better":[112],"align":[113],"human":[115,218],"preferences.":[116],"As":[117],"a":[118,138,154,182],"post-training":[119],"method,":[120],"it":[121],"greatly":[122],"enhances":[123],"performance":[126,211],"ensuring":[128],"efficiency.":[129,178],"In":[130],"addition":[131],"aforementioned":[134],"improvements,":[135],"integrates":[137],"series":[139],"of":[140,171,195],"further":[141],"refinements":[142],"significantly":[144],"both":[146,213],"performance.":[151],"introduce":[153],"new":[155],"strategy":[157],"called":[158],"Training":[159],"Token":[161],"Length":[162],"resolve":[164],"uneven":[165],"GPU":[166],"utilization":[167],"videos":[170],"varying":[172],"resolutions":[173],"lengths,":[175],"thereby":[176],"enhancing":[177],"Additionally,":[179],"use":[181],"multimodal":[183],"large":[184],"language":[185],"text":[189,193],"encoder":[190],"comprehension":[194],"model.":[197],"Experiments":[198],"demonstrate":[199],"significant":[200],"enhancements":[201],"resulting":[202],"from":[203],"above":[205],"improvements.":[206],"The":[207],"achieves":[209],"state-of-the-art":[210],"on":[212],"VBench":[215],"leaderboard":[216],"evaluation.":[219],"Code":[220],"pre-trained":[222],"are":[224],"available":[225],"at":[226],"https://github.com/aigc-apps/EasyAnimate.":[227]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-25T00:00:00"}