{"id":"https://openalex.org/W7123356248","doi":"https://doi.org/10.1109/tmm.2026.3651052","title":"LSTD: Long Short-Term Temporal Diffusion for Video Generation","display_name":"LSTD: Long Short-Term Temporal Diffusion for Video Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123356248","doi":"https://doi.org/10.1109/tmm.2026.3651052"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651052","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":null,"display_name":"Haoyu Zhao","orcid":"https://orcid.org/0000-0003-3832-6439"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Zhao","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3832-6439","affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091310860","display_name":"Jiaxi Gu","orcid":"https://orcid.org/0000-0002-6201-9503"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Gu","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6201-9503","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shicong Wang","orcid":"https://orcid.org/0009-0007-3981-0552"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shicong Wang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-3981-0552","affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109291377","display_name":"Tianyi Lu","orcid":"https://orcid.org/0009-0003-7803-194X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Lu","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-7803-194X","affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122895522","display_name":"Xing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Zhang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1721-035X","affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106166372","display_name":"Zuxuan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8689-5807","affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hang Xu","orcid":"https://orcid.org/0000-0003-3645-8972"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Huawei Noah&#x0027;ark Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3645-8972","affiliations":[{"raw_affiliation_string":"Huawei Noah&#x0027;ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122884702","display_name":"Yu-Gang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94569259,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"2460","last_page":"2473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8342000246047974,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8342000246047974,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05380000174045563,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0215000007301569,"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/inference","display_name":"Inference","score":0.6078000068664551},{"id":"https://openalex.org/keywords/temporal-database","display_name":"Temporal database","score":0.5990999937057495},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5332000255584717},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.42570000886917114},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.42149999737739563},{"id":"https://openalex.org/keywords/temporal-resolution","display_name":"Temporal resolution","score":0.4092999994754791},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4083999991416931},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4043999910354614},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.39739999175071716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8830999732017517},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6078000068664551},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.5990999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.54339998960495},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5332000255584717},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45010000467300415},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.42149999737739563},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.3531000018119812},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.3497999906539917},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.25850000977516174},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651052","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5455862283706665,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G472569701","display_name":null,"funder_award_id":"62032006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8051001991","display_name":null,"funder_award_id":"62472098","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"text-driven":[1],"video":[2,55,156,167,177],"generation":[3,56,157],"has":[4],"achieved":[5],"tremendous":[6],"progress.":[7],"However,":[8],"existing":[9],"methods":[10],"neglect":[11],"the":[12,19,35,38,99,104,119,137,142,146,190,193],"contexts":[13],"of":[14,29,37,125,136,145,166,192],"long":[15,54,155,176],"short-term":[16,112],"frames":[17],"in":[18],"video,":[20],"thereby":[21],"compromising":[22],"temporal":[23,40,88,94,143],"consistency.":[24,68,89],"They":[25],"also":[26,159],"encounter":[27],"challenges":[28],"heavy":[30],"memory":[31],"costs":[32],"due":[33],"to":[34,63,83],"use":[36],"standard":[39],"attention":[41,132],"mechanism":[42],"and":[43,48,67,103,118,174],"misalignment":[44],"between":[45],"training":[46,194],"videos":[47,85],"captions.":[49],"Additionally,":[50],"previous":[51],"approaches":[52],"for":[53,154],"are":[57,61],"flawed":[58],"because":[59],"they":[60],"hard":[62],"ensure":[64,141],"content":[65],"diversity":[66],"To":[69],"alleviate":[70],"these":[71],"issues,":[72],"we":[73],"propose":[74],"a":[75,115,129,150],"novel":[76,93,151],"Long":[77],"Short-term":[78,100],"Temporal":[79,101,106],"Diffusion":[80],"(LSTD)":[81],"model":[82],"generate":[84,164],"with":[86,114,128],"superior":[87,184],"We":[90],"introduce":[91],"two":[92,138,175],"modules,":[95],"<italic":[96],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e.</i>,":[98],"Convolution":[102],"Long-term":[105],"Attention.":[107],"The":[108,134],"former":[109],"can":[110,140,162],"learn":[111],"features":[113],"shallow":[116],"structure,":[117],"latter":[120],"concentrates":[121],"on":[122,171],"long-term":[123],"information":[124],"complex":[126],"motion":[127],"new":[130],"memory-efficient":[131],"mechanism.":[133],"combination":[135],"modules":[139],"consistency":[144],"generated":[147],"videos.":[148],"Furthermore,":[149],"inference":[152,186],"method":[153,182],"is":[158,196],"proposed,":[160],"which":[161],"iteratively":[163],"hundreds":[165],"frames.":[168],"Experimental":[169],"results":[170],"UCF-101,":[172],"MSR-VTT,":[173],"benchmarks":[178],"prove":[179],"that":[180],"our":[181],"achieves":[183],"zero-shot":[185],"performance":[187],"even":[188],"when":[189],"size":[191],"data":[195],"reduced":[197],"by":[198],"26.5":[199],"times.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2026-01-14T00:00:00"}