{"id":"https://openalex.org/W4405440310","doi":"https://doi.org/10.1109/tpami.2024.3518762","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","display_name":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4405440310","doi":"https://doi.org/10.1109/tpami.2024.3518762","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030702"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3518762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3518762","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hanlin Wang","orcid":"https://orcid.org/0009-0008-5431-1468"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanlin Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-5431-1468","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072801848","display_name":"Yilu Wu","orcid":"https://orcid.org/0009-0001-9390-9963"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilu Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752605","display_name":"Sheng Guo","orcid":"https://orcid.org/0000-0002-8959-2473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Guo","raw_affiliation_strings":["MYbank, Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8959-2473","affiliations":[{"raw_affiliation_string":"MYbank, Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436505","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0002-3674-7718"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3674-7718","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1645,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46689795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"47","issue":"3","first_page":"2107","last_page":"2124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9991000294685364,"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":0.995199978351593,"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":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6700291037559509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6441230177879333},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5733959078788757},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.48747920989990234},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36995816230773926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3416082262992859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700291037559509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6441230177879333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5733959078788757},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.48747920989990234},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36995816230773926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3416082262992859},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3518762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3518762","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030702","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030702","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G4889781089","display_name":null,"funder_award_id":"020214380119","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6791897338","display_name":null,"funder_award_id":"62076119","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1991133427","https://openalex.org/W2116680824","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2528489519","https://openalex.org/W2588181953","https://openalex.org/W2957775769","https://openalex.org/W2962795934","https://openalex.org/W2963368541","https://openalex.org/W2963524571","https://openalex.org/W2964094654","https://openalex.org/W2969937244","https://openalex.org/W2984008963","https://openalex.org/W2995301359","https://openalex.org/W3038470387","https://openalex.org/W3090800462","https://openalex.org/W3106768499","https://openalex.org/W3163465952","https://openalex.org/W3177150392","https://openalex.org/W3199332348","https://openalex.org/W3203256294","https://openalex.org/W4250482878","https://openalex.org/W4281690218","https://openalex.org/W4288099666","https://openalex.org/W4292794020","https://openalex.org/W4295751877","https://openalex.org/W4298186886","https://openalex.org/W4303440777","https://openalex.org/W4310695675","https://openalex.org/W4312338297","https://openalex.org/W4312518915","https://openalex.org/W4312933868","https://openalex.org/W4319300049","https://openalex.org/W4367359628","https://openalex.org/W4385245566","https://openalex.org/W4386075710","https://openalex.org/W4390872297","https://openalex.org/W4390873991","https://openalex.org/W6631190155","https://openalex.org/W6677255997","https://openalex.org/W6679045638","https://openalex.org/W6732520560","https://openalex.org/W6752217255","https://openalex.org/W6756379755","https://openalex.org/W6766837696","https://openalex.org/W6767312599","https://openalex.org/W6779823529","https://openalex.org/W6780226713","https://openalex.org/W6780805062","https://openalex.org/W6783713337","https://openalex.org/W6788990321","https://openalex.org/W6791353385","https://openalex.org/W6795252178","https://openalex.org/W6795288823","https://openalex.org/W6796487566","https://openalex.org/W6797906067","https://openalex.org/W6800512119","https://openalex.org/W6810793953","https://openalex.org/W6838483015","https://openalex.org/W6838745215","https://openalex.org/W6838815585","https://openalex.org/W6840157293","https://openalex.org/W6840815571","https://openalex.org/W6844223692","https://openalex.org/W6845281891"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"this":[1,36,133],"paper,":[2],"we":[3,78,153,211],"study":[4],"the":[5,25,30,95,120,125,144,174,216,226,250,266],"problem":[6,41,118,127,223],"of":[7,22,176,193,242,271],"procedure":[8,112,148],"planning":[9,76,113,126],"in":[10,58,147,196,229],"instructional":[11],"videos,":[12],"which":[13,224],"aims":[14],"to":[15,53,92,110,128,158,161,215],"make":[16,54],"a":[17,20,38,80,115,129,169,191],"plan":[18],"(i.e.":[19],"sequence":[21,39,98],"actions)":[23],"given":[24,121],"current":[26],"visual":[27,46,234],"observation":[28],"and":[29,42,62,71,172,189,206,245,268,275],"desired":[31],"goal.":[32],"Previous":[33],"works":[34],"cast":[35],"as":[37,51,84,103,114],"modeling":[40,139],"leverage":[43],"either":[44],"intermediate":[45,68],"observations":[47],"or":[48],"language":[49,231],"instructions":[50],"supervision":[52,69,104],"autoregressive":[55],"planning,":[56],"resulting":[57],"complex":[59],"learning":[60],"schemes":[61],"expensive":[63],"annotation":[64,70],"costs.":[65],"To":[66],"avoid":[67],"error":[72],"accumulation":[73],"caused":[74],"by":[75],"autoregressively,":[77],"propose":[79],"diffusion-based":[81,138],"framework,":[82,198],"coined":[83],"PDPP":[85,183,214,247],"(Projected":[86],"Diffusion":[87],"model":[88,94,171,248],"for":[89,219],"Procedure":[90],"Planning),":[91],"directly":[93],"whole":[96],"action":[97],"distribution":[99,116,134],"with":[100,164,184,258],"task":[101],"label":[102],"instead.":[105],"Our":[106],"core":[107],"idea":[108],"is":[109],"treat":[111],"fitting":[117],"under":[119],"observations,":[122],"thus":[123],"transform":[124],"sampling":[130],"process":[131],"from":[132],"during":[135],"inference.":[136],"The":[137],"approach":[140],"also":[141],"effectively":[142],"addresses":[143],"uncertainty":[145],"issue":[146],"planning.":[149],"Based":[150],"on":[151,239,253],"PDPP,":[152],"further":[154,264],"apply":[155,212],"joint":[156],"training":[157,177],"our":[159,182,197,213,246,272],"framework":[160],"generate":[162],"plans":[163],"varying":[165],"horizon":[166],"lengths":[167],"using":[168],"single":[170],"reduce":[173],"number":[175],"parameters":[178],"required.":[179],"We":[180,236],"instantiate":[181],"three":[185],"popular":[186],"diffusion":[187],"models":[188,277],"investigate":[190],"serious":[192],"condition-introducing":[194],"methods":[195],"including":[199],"condition":[200],"embeddings,":[201],"Mixture-of-Experts":[202],"(MoEs),":[203],"two-stage":[204],"prediction":[205],"Classifier-Free":[207],"Guidance":[208],"strategy.":[209],"Finally,":[210],"Visual":[217],"Planners":[218],"human":[220],"Assistance":[221],"(VPA)":[222],"requires":[225],"goal":[227],"specified":[228],"natural":[230],"rather":[232],"than":[233],"observation.":[235],"conduct":[237],"experiments":[238],"challenging":[240],"datasets":[241],"different":[243],"scales":[244],"achieves":[249],"state-of-the-art":[251],"performance":[252],"multiple":[254],"metrics,":[255],"even":[256],"compared":[257],"those":[259],"strongly-supervised":[260],"counterparts.":[261],"These":[262],"results":[263],"demonstrates":[265],"effectiveness":[267],"generalization":[269],"ability":[270],"model.":[273],"Code":[274],"trained":[276],"are":[278],"available":[279],"at":[280],"https://github.com/MCG-NJU/PDPP.":[281]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}