{"id":"https://openalex.org/W4387968791","doi":"https://doi.org/10.1145/3581783.3613765","title":"RD-FGFS: A Rule-Data Hybrid Framework for Fine-Grained Footstep Sound Synthesis from Visual Guidance","display_name":"RD-FGFS: A Rule-Data Hybrid Framework for Fine-Grained Footstep Sound Synthesis from Visual Guidance","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968791","doi":"https://doi.org/10.1145/3581783.3613765"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613765","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613765","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613765","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032931150","display_name":"Qiutang Qi","orcid":"https://orcid.org/0000-0001-6806-667X"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiutang Qi","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6806-667X","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065017752","display_name":"Haonan Cheng","orcid":"https://orcid.org/0000-0003-3407-4318"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Cheng","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3407-4318","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102895162","display_name":"Yang Wang","orcid":"https://orcid.org/0009-0003-8933-3433"},"institutions":[{"id":"https://openalex.org/I132210918","display_name":"North China Institute of Science and Technology","ror":"https://ror.org/0096c7651","country_code":"CN","type":"education","lineage":["https://openalex.org/I132210918"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["North China Institute of Science and Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-8933-3433","affiliations":[{"raw_affiliation_string":"North China Institute of Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I132210918"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600271","display_name":"Long Ye","orcid":"https://orcid.org/0000-0002-3562-5612"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Ye","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3562-5612","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065773273","display_name":"Shaobin Li","orcid":"https://orcid.org/0009-0007-5106-3246"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaobin Li","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5106-3246","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6935,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69893605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8525","last_page":"8533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9976000189781189,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9925000071525574,"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":0.7268843650817871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.517177939414978},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5035964846611023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.441893607378006},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.43154817819595337},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16581979393959045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268843650817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517177939414978},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5035964846611023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.441893607378006},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.43154817819595337},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16581979393959045},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613765","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613765","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3613765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613765","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613765","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G104419513","display_name":null,"funder_award_id":"61971383","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3139283728","display_name":null,"funder_award_id":"62201524","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6938695607","display_name":null,"funder_award_id":"62271455","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968791.pdf","grobid_xml":"https://content.openalex.org/works/W4387968791.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2111919806","https://openalex.org/W2116479175","https://openalex.org/W2141645628","https://openalex.org/W2148861863","https://openalex.org/W2253292704","https://openalex.org/W2293174243","https://openalex.org/W2484951126","https://openalex.org/W2593116425","https://openalex.org/W2596164567","https://openalex.org/W2897247252","https://openalex.org/W2963066677","https://openalex.org/W2963073614","https://openalex.org/W2963807156","https://openalex.org/W2964243274","https://openalex.org/W2964345931","https://openalex.org/W2990503944","https://openalex.org/W3035551320","https://openalex.org/W3046890131","https://openalex.org/W3093257790","https://openalex.org/W3105017218","https://openalex.org/W3163658555"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Existing":[0],"methods":[1],"are":[2],"difficult":[3],"to":[4,16,32],"synthesize":[5],"fine-grained":[6,106,143,170],"footsteps":[7,162],"based":[8,114],"on":[9,115],"video":[10],"frames":[11],"only.":[12],"This":[13],"is":[14,91,112],"due":[15],"the":[17,48,56,116,155],"complicated":[18],"nonlinear":[19],"mapping":[20,133],"relationships":[21],"between":[22,135],"motion":[23],"states,":[24],"spatial":[25],"locations":[26],"and":[27,62,86,124,139,157,163],"different":[28,136],"footstep":[29,69,77,107,140,146,168],"sounds.":[30,147],"Aiming":[31],"address":[33],"this":[34],"issue,":[35],"we":[36,73],"propose":[37],"a":[38,75,104,132],"Rule-Data":[39],"guided":[40],"Fine-Grained":[41],"Footstep":[42],"Sound":[43],"(RD-FGFS)":[44],"synthesis":[45],"method.":[46],"To":[47],"best":[49],"of":[50,145,161],"our":[51,53,152],"knowledge,":[52],"work":[54],"takes":[55],"first":[57],"step":[58],"in":[59,167],"integrating":[60],"data-driven":[61],"rule":[63],"modeling":[64],"approaches":[65],"for":[66,93],"visually":[67],"aligned":[68],"sound":[70,78,98,108,158,169],"synthesis.":[71],"Firstly,":[72],"design":[74],"learning-based":[76],"generation":[79],"network":[80],"(FSGN)":[81],"architecture":[82],"driven":[83],"by":[84],"pose":[85],"flow":[87],"features.":[88],"The":[89,127],"FSGN":[90],"proposed":[92,128],"generating":[94],"an":[95],"initial":[96],"target":[97],"which":[99],"captures":[100],"timing":[101],"cues.":[102],"Secondly,":[103],"rule-based":[105],"adjustment":[109],"(FGFSA)":[110],"method":[111,153],"designed":[113],"visual":[117,137,156],"guidance,":[118],"namely":[119],"ground":[120],"material,":[121],"movement":[122],"type,":[123],"displacement":[125],"distance.":[126],"FGFSA":[129],"effectively":[130],"constructs":[131],"relationship":[134],"cues":[138],"sounds,":[141],"enabling":[142],"variations":[144],"Experimental":[148],"results":[149,160],"show":[150],"that":[151],"improves":[154],"synchronization":[159],"achieves":[164],"impressive":[165],"performance":[166],"control.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}