{"id":"https://openalex.org/W4414687873","doi":"https://doi.org/10.1109/iccv51701.2025.00669","title":"Spatial-Temporal Aware Visuomotor Diffusion Policy Learning","display_name":"Spatial-Temporal Aware Visuomotor Diffusion Policy Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414687873","doi":"https://doi.org/10.1109/iccv51701.2025.00669"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00669","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.06710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101822681","display_name":"Zhenyang Liu","orcid":"https://orcid.org/0000-0002-4279-7199"},"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":"Zhenyang Liu","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/A5060062103","display_name":"Yikai Wang","orcid":"https://orcid.org/0000-0001-6699-5037"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yikai Wang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089564299","display_name":"Kuanning Wang","orcid":null},"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":"Kuanning Wang","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/A5063691574","display_name":"Longfei Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I2800781119","display_name":"Pallium India","ror":"https://ror.org/022bs7z24","country_code":"IN","type":"nonprofit","lineage":["https://openalex.org/I2800781119"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Longfei Liang","raw_affiliation_strings":["NeuHelium Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NeuHelium Co., Ltd","institution_ids":["https://openalex.org/I2800781119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"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":"Xiangyang Xue","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"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":"Yanwei Fu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10510","display_name":"Stroke Rehabilitation and Recovery","score":0.9524999856948853,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10510","display_name":"Stroke Rehabilitation and Recovery","score":0.9524999856948853,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.909600019454956,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9072999954223633,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/trajectory","display_name":"Trajectory","score":0.6026999950408936},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6018999814987183},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.517300009727478},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5026000142097473},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.45010000467300415},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4438000023365021},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.40860000252723694},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.39890000224113464},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38440001010894775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6381000280380249},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6026999950408936},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49630001187324524},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.45010000467300415},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00669","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:2507.06710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06710","pdf_url":"https://arxiv.org/pdf/2507.06710","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.06710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.06710","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.06710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06710","pdf_url":"https://arxiv.org/pdf/2507.06710","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2478649345","display_name":null,"funder_award_id":"24511103100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"imitation":[1,60],"learning":[2,61,88],"is":[3],"effective":[4],"for":[5,45],"robots":[6],"to":[7,35,85],"learn":[8],"versatile":[9],"tasks.":[10],"However,":[11],"many":[12],"existing":[13],"methods":[14,33],"rely":[15,74],"on":[16,75],"behavior":[17],"cloning":[18],"with":[19,134],"supervised":[20],"historical":[21],"trajectories,":[22],"limiting":[23],"their":[24],"3D":[25,38,90,104,115],"spatial":[26,91,124],"and":[27,40,92,111,125,137,164,167],"4D":[28,41,53,93,145],"spatiotemporal":[29,42,65,94],"awareness.":[30],"Consequently,":[31],"these":[32],"struggle":[34],"capture":[36],"the":[37,87,102,113,144,153,168],"structures":[39],"relationships":[43],"necessary":[44],"real-world":[46,139,170],"deployment.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"propose":[52],"Diffusion":[54,146],"Policy":[55,147],"(DP4),":[56],"a":[57,80,107],"novel":[58],"visual":[59],"method":[62,100],"that":[63,73,143],"incorporates":[64],"awareness":[66],"into":[67],"diffusion-based":[68],"policies.":[69],"Unlike":[70],"traditional":[71],"approaches":[72],"trajectory":[76,118],"cloning,":[77],"DP4":[78],"leverages":[79],"dynamic":[81],"Gaussian":[82],"world":[83],"model":[84],"guide":[86],"of":[89],"perceptions":[95],"from":[96,106],"interactive":[97],"environments.":[98],"Our":[99],"constructs":[101],"current":[103],"scene":[105],"single-view":[108],"RGB-D":[109],"observation":[110],"predicts":[112],"future":[114],"scene,":[116],"optimizing":[117],"generation":[119],"by":[120,159,175],"explicitly":[121],"modeling":[122],"both":[123],"temporal":[126],"dependencies.":[127],"Extensive":[128],"experiments":[129],"across":[130],"17":[131],"simulation":[132,155],"tasks":[133,141],"173":[135],"variants":[136],"3":[138],"robotic":[140,171],"demonstrate":[142],"(DP4)":[148],"outperforms":[149],"baseline":[150],"methods,":[151],"improving":[152],"average":[154,169],"task":[156,172],"success":[157,173],"rate":[158,174],"16.4%":[160],"(Adroit),":[161],"14%":[162],"(DexArt),":[163],"6.45%":[165],"(RLBench),":[166],"8.6%.":[176]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}