{"id":"https://openalex.org/W4416233037","doi":"https://doi.org/10.1109/wacv61042.2026.00669","title":"Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport","display_name":"Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416233037","doi":"https://doi.org/10.1109/wacv61042.2026.00669"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/2507.15540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Syed Ahmed Mahmood","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Ahmed Mahmood","raw_affiliation_strings":["Retrocausal, Inc,Redmond,WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Retrocausal, Inc,Redmond,WA","institution_ids":["https://openalex.org/I4210109355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090638382","display_name":"Ali Shaikh Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Shah Ali","raw_affiliation_strings":["Retrocausal, Inc,Redmond,WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Retrocausal, Inc,Redmond,WA","institution_ids":["https://openalex.org/I4210109355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115021337","display_name":"Umer Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umer Ahmed","raw_affiliation_strings":["Retrocausal, Inc,Redmond,WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Retrocausal, Inc,Redmond,WA","institution_ids":["https://openalex.org/I4210109355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106356853","display_name":"Fawad Javed Fateh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fawad Javed Fateh","raw_affiliation_strings":["Retrocausal, Inc,Redmond,WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Retrocausal, Inc,Redmond,WA","institution_ids":["https://openalex.org/I4210109355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011037400","display_name":"M. Zeeshan Zia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Zeeshan Zia","raw_affiliation_strings":["Retrocausal, Inc,Redmond,WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Retrocausal, Inc,Redmond,WA","institution_ids":["https://openalex.org/I4210109355"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000328580","display_name":"Quoc-Huy Tran","orcid":"https://orcid.org/0000-0003-1396-6544"},"institutions":[{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quoc-Huy Tran","raw_affiliation_strings":["Retrocausal, Inc,Redmond,WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Retrocausal, Inc,Redmond,WA","institution_ids":["https://openalex.org/I4210109355"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210109355"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01663324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6925","last_page":"6935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.4999000132083893,"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":0.4999000132083893,"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":0.16840000450611115,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.11110000312328339,"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/key","display_name":"Key (lock)","score":0.6646000146865845},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6067000031471252},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5745000243186951},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3375000059604645},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.328000009059906},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.2874000072479248}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6646000146865845},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5764999985694885},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.492000013589859},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46549999713897705},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33329999446868896},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.15540","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15540","pdf_url":"https://arxiv.org/pdf/2507.15540","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2507.15540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.15540","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2507.15540","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15540","pdf_url":"https://arxiv.org/pdf/2507.15540","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"study":[1],"self-supervised":[2,53],"procedure":[3],"learning,":[4],"which":[5,55,115,142],"discovers":[6],"key":[7,28,104],"steps":[8,29],"and":[9,30,43,95,130],"their":[10,31,34],"order":[11,39],"from":[12,38],"a":[13,52,57,63,88,112,145],"set":[14],"of":[15],"unlabeled":[16],"videos.":[17],"Previous":[18],"methods":[19],"typically":[20],"learn":[21],"frame-to-frame":[22,67],"correspondences":[23],"between":[24],"videos":[25],"before":[26],"determining":[27],"order.":[32],"However,":[33,69],"performance":[35,136],"often":[36],"suffers":[37],"variations,":[40],"background/redundant":[41],"frames,":[42],"repeated":[44],"actions.":[45],"To":[46,106],"overcome":[47],"these":[48],"challenges,":[49],"we":[50,110],"propose":[51],"framework,":[54],"utilizes":[56],"fused":[58],"Gromov-Wasserstein":[59],"optimal":[60,148],"transport":[61,149],"with":[62,150],"structural":[64],"prior":[65,138],"for":[66,72],"mapping.":[68],"optimizing":[70],"only":[71],"the":[73,92],"above":[74],"temporal":[75],"alignment":[76],"may":[77],"lead":[78],"to":[79,87,101,119],"degenerate":[80],"solutions,":[81],"where":[82],"all":[83],"frames":[84,118],"are":[85],"mapped":[86],"small":[89],"cluster":[90],"in":[91],"embedding":[93],"space":[94],"thus":[96],"every":[97],"video":[98],"is":[99],"assigned":[100],"just":[102],"one":[103],"step.":[105],"address":[107],"that":[108],"issue,":[109],"integrate":[111],"contrastive":[113],"regularization,":[114],"maps":[116],"different":[117],"various":[120],"points,":[121],"avoiding":[122],"trivial":[123],"solutions.":[124],"Finally,":[125],"extensive":[126],"experiments":[127],"on":[128,144],"egocentric":[129],"third-person":[131],"benchmarks":[132],"demonstrate":[133],"our":[134],"superior":[135],"over":[137],"works,":[139],"including":[140],"OPEL":[141],"relies":[143],"classical":[146],"Kantorovich":[147],"an":[151],"optimality":[152],"prior.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}