{"id":"https://openalex.org/W4415028164","doi":"https://doi.org/10.1145/3771724","title":"Video is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation","display_name":"Video is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation","publication_year":2025,"publication_date":"2025-10-10","ids":{"openalex":"https://openalex.org/W4415028164","doi":"https://doi.org/10.1145/3771724"},"language":"en","primary_location":{"id":"doi:10.1145/3771724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3771724","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3771724","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115707128","display_name":"Faraz Waseem","orcid":null},"institutions":[{"id":"https://openalex.org/I71052956","display_name":"University of Reading","ror":"https://ror.org/05v62cm79","country_code":"GB","type":"education","lineage":["https://openalex.org/I71052956"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Faraz Waseem","raw_affiliation_strings":["University of Reading"],"raw_orcid":"https://orcid.org/0009-0000-3382-9411","affiliations":[{"raw_affiliation_string":"University of Reading","institution_ids":["https://openalex.org/I71052956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101642262","display_name":"Muhammad Shahzad","orcid":"https://orcid.org/0009-0002-9394-343X"},"institutions":[{"id":"https://openalex.org/I71052956","display_name":"University of Reading","ror":"https://ror.org/05v62cm79","country_code":"GB","type":"education","lineage":["https://openalex.org/I71052956"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Muhammad Shahzad","raw_affiliation_strings":["Department of Computer Science, University of Reading"],"raw_orcid":"https://orcid.org/0009-0002-9394-343X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Reading","institution_ids":["https://openalex.org/I71052956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I71052956"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21706088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"58","issue":"6","first_page":"1","last_page":"35"},"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":0.9976000189781189,"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":0.9976000189781189,"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":0.9955999851226807,"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/T10758","display_name":"Cinema and Media Studies","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6118000149726868},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5720999836921692},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5406000018119812},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.4375999867916107},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4300999939441681},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8865000009536743},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5583000183105469},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3771724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3771724","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:centaur.reading.ac.uk:124876","is_oa":false,"landing_page_url":"https://centaur.reading.ac.uk/view/creators/90011867.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306402273","display_name":"CentAUR (University of Reading)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71052956","host_organization_name":"University of Reading","host_organization_lineage":["https://openalex.org/I71052956"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3771724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3771724","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2183341477","https://openalex.org/W2425121537","https://openalex.org/W2896457183","https://openalex.org/W2899463613","https://openalex.org/W2913059114","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963524571","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964245526","https://openalex.org/W2964318715","https://openalex.org/W2965813579","https://openalex.org/W2984008963","https://openalex.org/W3035574324","https://openalex.org/W3096831136","https://openalex.org/W3105232955","https://openalex.org/W3107803166","https://openalex.org/W3109908659","https://openalex.org/W3157199281","https://openalex.org/W3165647589","https://openalex.org/W3180355996","https://openalex.org/W3204588463","https://openalex.org/W4214612132","https://openalex.org/W4288089799","https://openalex.org/W4308233907","https://openalex.org/W4312423208","https://openalex.org/W4312933868","https://openalex.org/W4313156423","https://openalex.org/W4383472654","https://openalex.org/W4386065765","https://openalex.org/W4386066475","https://openalex.org/W4386071957","https://openalex.org/W4386076280","https://openalex.org/W4386083157","https://openalex.org/W4386598369","https://openalex.org/W4388844352","https://openalex.org/W4390602476","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390874113","https://openalex.org/W4392341509","https://openalex.org/W4393100107","https://openalex.org/W4393318705","https://openalex.org/W4399151802","https://openalex.org/W4399487349","https://openalex.org/W4401016973","https://openalex.org/W4402660110","https://openalex.org/W4402726937","https://openalex.org/W4402727699","https://openalex.org/W4402727736","https://openalex.org/W4402753903","https://openalex.org/W4402780389","https://openalex.org/W4402904066","https://openalex.org/W4402961796","https://openalex.org/W4403007010","https://openalex.org/W4404314105","https://openalex.org/W4405695475","https://openalex.org/W4413147290"],"related_works":[],"abstract_inverted_index":{"An":[0],"image":[1,16],"may":[2],"convey":[3],"a":[4,8,19,36,103,168],"thousand":[5],"words,":[6],"but":[7],"video,":[9],"composed":[10],"of":[11,15,40,58,71,124,157,183],"hundreds":[12],"or":[13],"thousands":[14],"frames,":[17],"tells":[18],"more":[20,77],"intricate":[21],"story.":[22],"Despite":[23],"significant":[24,97],"progress":[25],"in":[26,63,180],"multimodal":[27],"large":[28],"language":[29],"models":[30],"(MLLMs),":[31],"generating":[32],"extended":[33],"videos":[34,57,111],"remains":[35],"formidable":[37],"challenge.":[38],"As":[39],"this":[41,117],"writing,":[42],"OpenAI\u2019s":[43],"Sora":[44],"[":[45],"1":[46],"],":[47],"the":[48,69,121,155,181],"current":[49,122],"state-of-the-art":[50],"system,":[51],"is":[52],"still":[53],"limited":[54],"to":[55,60,153,174],"producing":[56],"up":[59],"one":[61],"minute":[62],"length.":[64],"This":[65],"limitation":[66],"stems":[67],"from":[68],"complexity":[70],"long":[72,125,147,184],"video":[73,126,137,159,185],"generation,":[74,127],"which":[75],"requires":[76],"than":[78],"generative":[79,100],"AI":[80,101],"techniques":[81,130],"for":[82,109,145],"approximating":[83],"density":[84],"functions.":[85],"Critical":[86],"elements,":[87],"such":[88,131],"as":[89,132,167],"planning,":[90],"narrative":[91],"construction,":[92],"and":[93,134,149,178],"spatiotemporal":[94],"continuity,":[95],"pose":[96],"challenges.":[98],"Integrating":[99],"with":[102],"divide-and-conquer":[104],"approach":[105],"could":[106],"improve":[107],"scalability":[108],"longer":[110],"while":[112],"offering":[113,171],"greater":[114],"control.":[115],"In":[116],"survey,":[118],"we":[119],"examine":[120],"landscape":[123],"covering":[128],"foundational":[129],"GANs":[133],"diffusion":[135],"models,":[136],"generation":[138,160],"strategies,":[139],"large-scale":[140],"training":[141],"datasets,":[142],"quality":[143],"metrics":[144],"evaluating":[146],"videos,":[148],"future":[150,176],"research":[151,179],"areas":[152],"address":[154],"limitations":[156],"existing":[158],"capabilities.":[161],"We":[162],"believe":[163],"it":[164],"would":[165],"serve":[166],"comprehensive":[169],"foundation,":[170],"extensive":[172],"information":[173],"guide":[175],"advancements":[177],"field":[182],"generation.":[186]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}