{"id":"https://openalex.org/W4412885864","doi":"https://doi.org/10.32604/cmc.2025.065529","title":"Optimizing Semantic and Texture Consistency in Video Generation","display_name":"Optimizing Semantic and Texture Consistency in Video Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412885864","doi":"https://doi.org/10.32604/cmc.2025.065529"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.065529","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.065529","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.065529","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100374639","display_name":"Xianjun Yu","orcid":"https://orcid.org/0000-0002-6697-7143"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xian Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109289554","display_name":"Jianxun Zhang","orcid":"https://orcid.org/0009-0000-5397-1669"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianxun Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058313024","display_name":"Siran Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siran Tian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110792835","display_name":"Xiaobao He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaobao He","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100374639"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21944257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"85","issue":"1","first_page":"1883","last_page":"1897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9891999959945679,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9891999959945679,"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/T12290","display_name":"Human Motion and Animation","score":0.9837999939918518,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6491086483001709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6067728996276855},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.5450605750083923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3991536796092987},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39560747146606445},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3342825174331665},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18201637268066406}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6491086483001709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067728996276855},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.5450605750083923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3991536796092987},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39560747146606445},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3342825174331665},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18201637268066406}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.065529","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.065529","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.065529","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.065529","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2996880115","https://openalex.org/W3096831136","https://openalex.org/W4386001503","https://openalex.org/W4391605364","https://openalex.org/W4394673632","https://openalex.org/W4402639496","https://openalex.org/W4411270486"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"diffusion":[3],"models":[4],"have":[5],"achieved":[6],"remarkable":[7],"progress":[8],"in":[9,22,45,72],"image":[10],"generation.":[11,74],"However,":[12],"extending":[13],"them":[14],"to":[15,65,82,115,142],"text-to-video":[16],"(T2V)":[17],"generation":[18,154,183],"remains":[19],"challenging,":[20],"particularly":[21],"maintaining":[23],"semantic":[24,68,117,138],"consistency":[25,71],"and":[26,40,69,87,94,101,106,118,125,139,146,177,188],"visual":[27,178],"quality":[28],"across":[29,180],"frames.":[30,127],"Existing":[31],"approaches":[32],"often":[33],"overlook":[34],"the":[35,89,135],"synergy":[36],"between":[37,123,137],"high-level":[38,99],"semantics":[39,100],"low-level":[41],"texture":[42,70,105,119,140],"information,":[43],"resulting":[44],"blurry":[46],"or":[47],"temporally":[48],"inconsistent":[49],"outputs.":[50],"To":[51],"address":[52],"these":[53],"issues,":[54],"we":[55,76,129],"propose":[56,130],"Dual":[57],"Consistency":[58],"Training":[59],"(DCT),":[60],"a":[61,78,110,157,162],"novel":[62],"framework":[63],"designed":[64],"jointly":[66],"optimize":[67],"video":[73,153,160,182],"Specifically,":[75],"introduce":[77],"multi-scale":[79],"spatial":[80,84],"adapter":[81],"enhance":[83],"feature":[85],"extraction,":[86],"leverage":[88],"complementary":[90],"strengths":[91],"of":[92],"CLIP":[93,96],"VGG\u2014where":[95],"focuses":[97],"on":[98,161],"VGG":[102],"captures":[103],"fine-grained":[104],"detail.":[107],"During":[108],"training,":[109],"stepwise":[111],"strategy":[112],"is":[113],"adopted":[114],"impose":[116],"losses,":[120],"constraining":[121],"discrepancies":[122],"generated":[124],"ground-truth":[126],"Furthermore,":[128],"CLWS,":[131],"which":[132],"dynamically":[133],"adjusts":[134],"balance":[136],"losses":[141],"facilitate":[143],"more":[144],"stable":[145],"effective":[147],"optimization.":[148],"Remarkably,":[149],"DCT":[150],"achieves":[151],"high-quality":[152],"using":[155],"only":[156],"single":[158,163],"training":[159],"NVIDIA":[164],"A6000":[165],"GPU.":[166],"Extensive":[167],"experiments":[168],"demonstrate":[169],"that":[170],"our":[171],"method":[172],"significantly":[173],"improves":[174],"temporal":[175],"coherence":[176],"fidelity":[179],"various":[181],"tasks,":[184],"verifying":[185],"its":[186],"effectiveness":[187],"generalizability.":[189]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}