{"id":"https://openalex.org/W4207079187","doi":"https://doi.org/10.1142/s0218001421600168","title":"Audio-Oriented Video Interpolation Using Key Pose","display_name":"Audio-Oriented Video Interpolation Using Key Pose","publication_year":2021,"publication_date":"2021-12-30","ids":{"openalex":"https://openalex.org/W4207079187","doi":"https://doi.org/10.1142/s0218001421600168"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001421600168","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001421600168","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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":"https://openalex.org/A5049439519","display_name":"Takayuki Nakatsuka","orcid":"https://orcid.org/0000-0003-3181-4894"},"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":"Takayuki Nakatsuka","raw_affiliation_strings":["Department of Pure and Applied Physics, Waseda University, 55N Building, Room 406, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pure and Applied Physics, Waseda University, 55N Building, Room 406, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102379122","display_name":"Yukitaka Tsuchiya","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":"Yukitaka Tsuchiya","raw_affiliation_strings":["Department of Pure and Applied Physics, Waseda University, 55N Building, Room 406, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pure and Applied Physics, Waseda University, 55N Building, Room 406, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054189319","display_name":"Masatoshi Hamanaka","orcid":"https://orcid.org/0000-0002-0249-4900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masatoshi Hamanaka","raw_affiliation_strings":["RIKEN, Nihonbashi 1-Chome Mitsui Building, 15th Floor, 1-4-1 Nihonbashi, Chuo-KU, Tokyo 103-0027, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN, Nihonbashi 1-Chome Mitsui Building, 15th Floor, 1-4-1 Nihonbashi, Chuo-KU, Tokyo 103-0027, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083427215","display_name":"Shigeo Morishima","orcid":"https://orcid.org/0000-0001-8859-6539"},"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":"Shigeo Morishima","raw_affiliation_strings":["Waseda Research Institute for Science and Engineering, 55N Building, Room 406, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda Research Institute for Science and Engineering, 55N Building, Room 406, 3-4-1 Okubo, Shinjuku, Tokyo 169-8555, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5049439519"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.1884,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50923974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"35","issue":"16","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9733999967575073,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9733999967575073,"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":0.9581000208854675,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.947700023651123,"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/computer-science","display_name":"Computer science","score":0.8157272934913635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7153356671333313},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6413789391517639},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.5900142192840576},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.552369236946106},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5455195903778076},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45124551653862},{"id":"https://openalex.org/keywords/motion-interpolation","display_name":"Motion interpolation","score":0.44667550921440125},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.4188789129257202},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3498886227607727},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3372853994369507},{"id":"https://openalex.org/keywords/block-matching-algorithm","display_name":"Block-matching algorithm","score":0.24668607115745544},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20077261328697205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157272934913635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7153356671333313},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6413789391517639},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.5900142192840576},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.552369236946106},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5455195903778076},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45124551653862},{"id":"https://openalex.org/C72560505","wikidata":"https://www.wikidata.org/wiki/Q204510","display_name":"Motion interpolation","level":5,"score":0.44667550921440125},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.4188789129257202},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3498886227607727},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3372853994369507},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.24668607115745544},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20077261328697205},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001421600168","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001421600168","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2363020693","display_name":"A Study on Multi-modal Automatic Simultaneous Interpretation System and Evaluation Method","funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G432938063","display_name":null,"funder_award_id":"JPMJAC1602","funder_id":"https://openalex.org/F4320338113","funder_display_name":"Accelerated Innovation Research Initiative Turning Top Science and Ideas into High-Impact Values"},{"id":"https://openalex.org/G5205327250","display_name":null,"funder_award_id":"JP19H01129","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5650689433","display_name":null,"funder_award_id":"JP16H01744","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6616750388","display_name":null,"funder_award_id":"JP17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6796696814","display_name":null,"funder_award_id":"JP17H01847","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7215117765","display_name":null,"funder_award_id":"JP19H04137","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7880319378","display_name":"\u5206\u6563\u578b\u533f\u540d\u5316\u51e6\u7406\u306b\u3088\u308b\u30d7\u30e9\u30a4\u30d0\u30b7\u30fc\u30d7\u30ea\u30b6\u30fc\u30d6\u30c9AI\u57fa\u76e4\u69cb\u7bc9","funder_award_id":"JPMJMI19B2","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338113","display_name":"Accelerated Innovation Research Initiative Turning Top Science and Ideas into High-Impact Values","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1589182518","https://openalex.org/W2031410675","https://openalex.org/W2037874181","https://openalex.org/W2059020775","https://openalex.org/W2064675550","https://openalex.org/W2080489767","https://openalex.org/W2111331420","https://openalex.org/W2139107403","https://openalex.org/W2151654057","https://openalex.org/W2163301185","https://openalex.org/W2183341477","https://openalex.org/W2290349311","https://openalex.org/W2404706114","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2780124704","https://openalex.org/W2804619907","https://openalex.org/W2883938080","https://openalex.org/W2884460600","https://openalex.org/W2897492344","https://openalex.org/W2904829482","https://openalex.org/W2949258649","https://openalex.org/W2962730651","https://openalex.org/W2962795401","https://openalex.org/W2963093735","https://openalex.org/W2963268050","https://openalex.org/W2963483509","https://openalex.org/W2963527086","https://openalex.org/W2963800363","https://openalex.org/W2963876278","https://openalex.org/W2964108494","https://openalex.org/W2964208152","https://openalex.org/W2964251418","https://openalex.org/W2973673960","https://openalex.org/W2979157532","https://openalex.org/W2981081013","https://openalex.org/W2981263323","https://openalex.org/W2984529706","https://openalex.org/W2991502760","https://openalex.org/W2997005628","https://openalex.org/W2997150500","https://openalex.org/W2998645105","https://openalex.org/W3010049297","https://openalex.org/W3011906228","https://openalex.org/W3024979138","https://openalex.org/W3025353605","https://openalex.org/W3034769793","https://openalex.org/W3034921716","https://openalex.org/W3035239272","https://openalex.org/W3102619627","https://openalex.org/W3110612869","https://openalex.org/W3161635175","https://openalex.org/W4300914774","https://openalex.org/W4310895557"],"related_works":["https://openalex.org/W2394005538","https://openalex.org/W3123991145","https://openalex.org/W4389850132","https://openalex.org/W1574724839","https://openalex.org/W2379826426","https://openalex.org/W2377190948","https://openalex.org/W2096476311","https://openalex.org/W2622881578","https://openalex.org/W4361855866","https://openalex.org/W1803027153"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,21,24,189,214],"deep":[4,30],"learning-based":[5],"method":[6,245],"for":[7,51,96],"long-term":[8,54,100],"video":[9,44,55,101,137,145],"interpolation":[10,56],"that":[11,119,192,233],"generates":[12],"intermediate":[13,117,166,224],"frames":[14,118,167,225],"between":[15,226],"two":[16,227],"music":[17,71,75,93,97,109,175,228],"performance":[18,72,78,98,148,229,236],"videos":[19,149,237],"of":[20,60,65,130,134,142,239],"person":[22],"playing":[23],"specific":[25],"instrument.":[26],"Recent":[27],"advances":[28],"in":[29,42,53,70,99,146,164,198,205],"learning":[31],"techniques":[32],"have":[33],"successfully":[34],"generated":[35,67,235],"realistic":[36],"images":[37],"with":[38,108,121,173],"high-fidelity":[39],"and":[40,62,76,92,110,138],"high-resolution":[41],"short-term":[43],"interpolation.":[45,102],"However,":[46],"there":[47],"is":[48,113],"still":[49],"room":[50],"improvement":[52],"due":[57],"to":[58,81,115,150,182,222],"lack":[59],"resolution":[61],"temporal":[63],"consistency":[64],"the":[66,74,122,127,131,135,139,143,147,161,165,169,174,178,194,202,219,234,243],"video.":[68],"Particularly":[69],"videos,":[73,111],"human":[77,90,106,128,162,196,203,210],"motion":[79],"need":[80],"be":[82,151],"synchronized.":[83],"We":[84,231],"solved":[85],"these":[86],"problems":[87],"by":[88],"using":[89],"poses":[91,107,129,163,197],"features":[94,176],"essential":[95],"By":[103],"closely":[104],"matching":[105],"it":[112],"possible":[114],"generate":[116,223],"synchronize":[120],"music.":[123],"Specifically,":[124],"we":[125,187],"obtain":[126],"last":[132],"frame":[133,141],"first":[136,140],"second":[144],"interpolated":[152],"as":[153,177,209],"key":[154,171],"poses.":[155],"Then,":[156],"our":[157],"encoder\u2013decoder":[158],"network":[159,191,217],"estimates":[160],"from":[168],"obtained":[170],"poses,":[172],"condition.":[179],"In":[180],"order":[181],"construct":[183],"an":[184],"end-to-end":[185],"network,":[186],"utilize":[188],"differentiable":[190],"transforms":[193],"estimated":[195],"vector":[199],"form":[200],"into":[201],"pose":[204],"image":[206],"form,":[207],"such":[208],"stick":[211,220],"figures.":[212],"Finally,":[213],"video-to-video":[215],"synthesis":[216],"uses":[218],"figures":[221],"videos.":[230],"found":[232],"were":[238],"higher":[240],"quality":[241],"than":[242],"baseline":[244],"through":[246],"quantitative":[247],"experiments.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
