{"id":"https://openalex.org/W4414528062","doi":"https://doi.org/10.1109/iccv51701.2025.01181","title":"Precise Action-to-Video Generation Through Visual Action Prompts","display_name":"Precise Action-to-Video Generation Through Visual Action Prompts","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414528062","doi":"https://doi.org/10.1109/iccv51701.2025.01181"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.13104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103176434","display_name":"Yuang Wang","orcid":"https://orcid.org/0009-0000-9234-879X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuang Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070884593","display_name":"Chao Wen","orcid":"https://orcid.org/0000-0001-6611-8122"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wen","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106665185","display_name":"Haoyu Guo","orcid":"https://orcid.org/0000-0002-2939-6294"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Guo","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073087748","display_name":"Sida Peng","orcid":"https://orcid.org/0000-0001-6546-4525"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sida Peng","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108889598","display_name":"Minghan Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghan Qin","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059021869","display_name":"Hujun Bao","orcid":"https://orcid.org/0000-0002-2662-0334"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hujun Bao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814482","display_name":"Xiaowei Zhou","orcid":"https://orcid.org/0000-0003-1926-5597"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Zhou","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013892799","display_name":"Ruizhen Hu","orcid":"https://orcid.org/0000-0002-6798-0336"},"institutions":[{"id":"https://openalex.org/I4210114190","display_name":"Shanghai Zhangjiang Laboratory","ror":"https://ror.org/0208qbg77","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruizhen Hu","raw_affiliation_strings":["Xiangjiang Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiangjiang Lab","institution_ids":["https://openalex.org/I4210114190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21974746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12713","last_page":"12724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12290","display_name":"Human Motion and Animation","score":0.9945999979972839,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9817000031471252,"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/generality","display_name":"Generality","score":0.8276000022888184},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6262000203132629},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5551000237464905},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5374000072479248},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5350000262260437},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.42640000581741333},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3822000026702881},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.3668000102043152}],"concepts":[{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.8276000022888184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6341000199317932},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6262000203132629},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5551000237464905},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5374000072479248},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4708999991416931},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.36329999566078186},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.13104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13104","pdf_url":"https://arxiv.org/pdf/2508.13104","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.13104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.13104","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.13104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13104","pdf_url":"https://arxiv.org/pdf/2508.13104","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7486620179","display_name":null,"funder_award_id":"62322207,U24B20154","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,96],"present":[1],"visual":[2,19,70,89,126],"action":[3,7,46,58,139],"prompts,":[4],"a":[5,27],"unified":[6],"representation":[8],"for":[9,83,91],"action-to-video":[10],"generation":[11,25,131],"of":[12,53,120,141,148,160],"complex":[13,84,142],"high-DoF":[14],"interactions":[15,110],"while":[16,44,144],"maintaining":[17],"transferable":[18],"dynamics":[20],"across":[21],"domains.":[22],"Action-driven":[23],"video":[24,130],"faces":[26],"precision-generality":[28],"trade-off:":[29],"existing":[30],"methods":[31],"using":[32],"text,":[33],"primitive":[34],"actions,":[35],"or":[36],"coarse":[37],"masks":[38],"offer":[39],"generality":[40,93],"but":[41],"lack":[42],"precision,":[43],"agent-centric":[45],"signals":[47],"provide":[48],"precision":[49,59,79],"at":[50],"the":[51,146,158],"cost":[52],"cross-domain":[54,81,118,149],"transferability.":[55],"To":[56],"balance":[57],"and":[60,80,94,112,155],"dynamic":[61],"transferability,":[62],"we":[63,87,136],"propose":[64,97],"to":[65,100],"\"render\"":[66],"actions":[67],"into":[68,128],"precise":[69,138],"prompts":[71],"as":[72],"domain-agnostic":[73],"representations":[74],"that":[75],"preserve":[76],"both":[77],"geometric":[78],"adaptability":[82],"actions;":[85],"specifically,":[86],"choose":[88],"skeletons":[90,102,127],"their":[92],"accessibility.":[95],"robust":[98],"pipelines":[99],"construct":[101],"from":[103],"two":[104],"interaction-rich":[105],"data":[106],"sources":[107],"-":[108,116],"human-object":[109],"(HOI)":[111],"dexterous":[113],"robotic":[114],"manipulation":[115],"enabling":[117],"training":[119],"action-driven":[121],"generative":[122],"models.":[123],"By":[124],"integrating":[125],"pretrained":[129],"models":[132],"via":[133],"lightweight":[134],"fine-tuning,":[135],"enable":[137],"control":[140],"interaction":[143],"preserving":[145],"learning":[147],"dynamics.":[150],"Experiments":[151],"on":[152],"EgoVid,":[153],"RT-1":[154],"DROID":[156],"demonstrate":[157],"effectiveness":[159],"our":[161],"proposed":[162],"approach.":[163],"Project":[164],"page:":[165],"https://zju3dv.github.io/VAP/.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}