{"id":"https://openalex.org/W7130959504","doi":"https://doi.org/10.31449/inf.v50i8.11435","title":"NBO-SAGAN: Namib Beetle Optimized Self-Attention GAN for Cross-Modal Short Video Generation with Semantic Decoupling","display_name":"NBO-SAGAN: Namib Beetle Optimized Self-Attention GAN for Cross-Modal Short Video Generation with Semantic Decoupling","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7130959504","doi":"https://doi.org/10.31449/inf.v50i8.11435"},"language":null,"primary_location":{"id":"doi:10.31449/inf.v50i8.11435","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i8.11435","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/11435/6544","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.informatica.si/index.php/informatica/article/download/11435/6544","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100332992","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0003-0827-8819"},"institutions":[{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["Sichuan Film and Television University, ChengDu, Si Chuan, 610036, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan Film and Television University, ChengDu, Si Chuan, 610036, China","institution_ids":["https://openalex.org/I4210125143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126568872","display_name":"Dan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Li","raw_affiliation_strings":["Sichuan Film and Television University, ChengDu, Si Chuan, 610036, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan Film and Television University, ChengDu, Si Chuan, 610036, China","institution_ids":["https://openalex.org/I4210125143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210125143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22095697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":"8","first_page":null,"last_page":null},"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":0.8391000032424927,"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":0.8391000032424927,"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":0.08309999853372574,"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/T11448","display_name":"Face recognition and analysis","score":0.014999999664723873,"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/video-tracking","display_name":"Video tracking","score":0.5530999898910522},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5263000130653381},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.47290000319480896},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.41999998688697815},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.4169999957084656},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3587000072002411},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3549000024795532},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3495999872684479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565999865531921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5766000151634216},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5530999898910522},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.47290000319480896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45739999413490295},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.3418999910354614},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.2994999885559082},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C198751489","wikidata":"https://www.wikidata.org/wiki/Q2195","display_name":"JPEG","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31449/inf.v50i8.11435","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i8.11435","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/11435/6544","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31449/inf.v50i8.11435","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i8.11435","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/11435/6544","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7130959504.pdf","grobid_xml":"https://content.openalex.org/works/W7130959504.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,74],"rapid":[1],"growth":[2],"of":[3,191,198],"short":[4,12,63,164],"video":[5,13,64,89,206,222],"platforms":[6],"has":[7,87],"fueled":[8],"interest":[9],"in":[10,155],"automated":[11],"generation,":[14],"a":[15,58,119],"task":[16,37],"that":[17,123,180],"demands":[18],"high":[19],"fidelity,":[20],"temporal":[21],"coherence,":[22],"and":[23,51,110,128,141,166,171,193,218],"semantic":[24,47,120,131],"alignment":[25],"with":[26,118],"input":[27,154],"data":[28],"such":[29,133],"as":[30,134],"text,":[31],"audio,":[32],"or":[33],"static":[34],"images.":[35],"This":[36,208],"poses":[38],"important":[39],"issues":[40],"since":[41],"to":[42,69,78,126,162,167,214],"the":[43,85,145,181],"requirement":[44],"for":[45,203],"accurate":[46],"understanding,":[48],"spatial-temporal":[49],"alignment,":[50],"realistic":[52],"visual":[53,173],"synthesis.":[54],"In":[55],"this":[56],"research,":[57],"novel":[59],"deep":[60],"learning-based":[61],"cross-modal":[62,205,221],"generation":[65],"framework":[66],"is":[67,82,116,160],"developed":[68],"address":[70],"these":[71],"challenges":[72],"effectively.":[73],"Microsoft":[75],"Research":[76],"Video":[77,105,188,195],"Text":[79],"(MSRVTT)":[80],"dataset":[81],"gathered":[83],"from":[84,91,144],"Kaggle,":[86],"10,000":[88],"clips":[90],"20":[92],"categories":[93],"undergoes":[94],"extensive":[95],"preprocessing,":[96],"tokenization,":[97],"Audio":[98],"Modality":[99,106],"using":[100,107,177],"Mel-Frequency":[101],"Cepstral":[102],"Coefficients":[103],"(MFCCs),":[104],"Temporal-Spatial":[108],"Synchronization":[109],"Normalization":[111],"(TSSN).":[112],"Then":[113],"feature":[114],"extraction":[115],"performed":[117],"decoupling":[121],"module":[122],"utilizes":[124],"encoders":[125],"extract":[127],"disentangle":[129],"high-level":[130],"components,":[132],"object":[135],"appearance,":[136],"motion":[137],"dynamics,":[138],"background":[139],"context,":[140],"emotional":[142],"tone":[143],"input.":[146],"A":[147],"Namib":[148],"Beetle":[149],"Optimized":[150],"Self-Attention":[151],"based":[152],"Generative":[153],"various":[156],"Adversarial":[157],"Networks":[158],"(NBO-SAGAN)":[159],"employed":[161],"generate":[163],"videos":[165],"enhance":[168],"fine":[169],"details":[170],"correct":[172],"artifacts.":[174],"Experimental":[175],"evaluations":[176],"Python":[178],"shows":[179],"NBO-SAGAN":[182],"approach":[183],"outperforms":[184],"traditional":[185],"methods":[186],"Frechet":[187],"Distance":[189,196],"(FVD)":[190],"230.74":[192],"Kernel":[194],"(KVD)":[197],"12.58":[199],"highlighting":[200],"its":[201],"effectiveness":[202],"expressive":[204],"generation.":[207],"integrated":[209],"methodology":[210],"effectively":[211],"combines":[212],"modeling":[213],"produce":[215],"controllable,":[216],"expressive,":[217],"visually":[219],"rich":[220],"content.":[223]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-02-23T00:00:00"}