{"id":"https://openalex.org/W7123610842","doi":"https://doi.org/10.1109/mmsp64401.2025.11324101","title":"Adapting Image-to-Video Diffusion Models for Large-Motion Frame Interpolation","display_name":"Adapting Image-to-Video Diffusion Models for Large-Motion Frame Interpolation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123610842","doi":"https://doi.org/10.1109/mmsp64401.2025.11324101"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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/A5122991721","display_name":"Luoxu Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Luoxu Jin","raw_affiliation_strings":["Waseda University,CSCE, Graduate School of FSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,CSCE, Graduate School of FSE,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080047284","display_name":"H. Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Watanabe","raw_affiliation_strings":["Waseda University,CSCE, Graduate School of FSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,CSCE, Graduate School of FSE,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5122991721"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68781105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"285"},"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":0.31619998812675476,"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":0.31619998812675476,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.26409998536109924,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.17479999363422394,"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/interpolation","display_name":"Interpolation (computer graphics)","score":0.6383000016212463},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5698000192642212},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5372999906539917},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5307000279426575},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.522599995136261},{"id":"https://openalex.org/keywords/motion-interpolation","display_name":"Motion interpolation","score":0.4952000081539154},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4189000129699707},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4034999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027000188827515},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6383000016212463},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5327000021934509},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281000137329102},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C72560505","wikidata":"https://www.wikidata.org/wiki/Q204510","display_name":"Motion interpolation","level":5,"score":0.4952000081539154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4641000032424927},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.3391999900341034},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C203332170","wikidata":"https://www.wikidata.org/wiki/Q6334079","display_name":"Multivariate interpolation","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25609999895095825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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":22,"referenced_works":["https://openalex.org/W2769654144","https://openalex.org/W2955639361","https://openalex.org/W2962785568","https://openalex.org/W2963093735","https://openalex.org/W2998645105","https://openalex.org/W3034921716","https://openalex.org/W3109908659","https://openalex.org/W3204588463","https://openalex.org/W4214626557","https://openalex.org/W4289752563","https://openalex.org/W4312364368","https://openalex.org/W4312445951","https://openalex.org/W4312623579","https://openalex.org/W4312770027","https://openalex.org/W4312933868","https://openalex.org/W4386071957","https://openalex.org/W4386075779","https://openalex.org/W4390873054","https://openalex.org/W4393149921","https://openalex.org/W4402727587","https://openalex.org/W4402754262","https://openalex.org/W4403021266"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,74],"development":[2],"of":[3,65],"video":[4,21],"generation":[5],"models":[6,19],"has":[7],"advanced":[8],"significantly":[9],"in":[10,88,95],"recent":[11],"years,":[12],"we":[13,42],"adopt":[14],"large-":[15],"scale":[16],"image-to-video":[17,33],"diffusion":[18],"for":[20,35],"frame":[22,37],"interpolation.":[23,38],"We":[24],"present":[25],"a":[26,44,50],"conditional":[27],"encoder":[28],"designed":[29],"to":[30],"adapt":[31],"an":[32],"model":[34],"large-motion":[36],"To":[39],"enhance":[40],"performance,":[41],"integrate":[43],"dual-branch":[45],"feature":[46],"extractor":[47],"and":[48,59],"propose":[49],"cross-frame":[51],"attention":[52],"mechanism":[53],"that":[54],"effectively":[55],"captures":[56],"both":[57],"spatial":[58],"temporal":[60],"information,":[61],"enabling":[62],"accurate":[63],"interpolations":[64],"intermediate":[66],"frames.":[67],"Our":[68],"approach":[69],"demonstrates":[70],"superior":[71],"performance":[72],"on":[73],"Fr\u00e9chet":[75],"Video":[76],"Distance":[77],"(FVD)":[78],"metric":[79],"when":[80],"evaluated":[81],"against":[82],"other":[83],"state-of-the-":[84],"art":[85],"approaches,":[86],"particularly":[87],"handling":[89],"large":[90],"motion":[91],"scenarios,":[92],"highlighting":[93],"advancements":[94],"generative-based":[96],"methodologies.":[97]},"counts_by_year":[],"updated_date":"2026-01-14T23:44:37.837170","created_date":"2026-01-14T00:00:00"}