{"id":"https://openalex.org/W4417152383","doi":"https://doi.org/10.1109/iccv51701.2025.01006","title":"Joint Self-Supervised Video Alignment and Action Segmentation","display_name":"Joint Self-Supervised Video Alignment and Action Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417152383","doi":"https://doi.org/10.1109/iccv51701.2025.01006"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01006","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/2503.16832","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090638382","display_name":"Ali Shaikh Ali","orcid":null},"institutions":[],"countries":[],"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":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Syed Ahmed Mahmood","orcid":null},"institutions":[],"countries":[],"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":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113689342","display_name":"Muzammil Saeed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mubin Saeed","raw_affiliation_strings":["Retrocausal, Inc.,Redmond,WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Retrocausal, Inc.,Redmond,WA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088070581","display_name":"Andrey Konin","orcid":"https://orcid.org/0000-0003-1886-2402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrey Konin","raw_affiliation_strings":["Retrocausal, Inc.,Redmond,WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Retrocausal, Inc.,Redmond,WA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011037400","display_name":"M. Zeeshan Zia","orcid":null},"institutions":[],"countries":[],"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":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000328580","display_name":"Quoc-Huy Tran","orcid":"https://orcid.org/0000-0003-1396-6544"},"institutions":[],"countries":[],"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":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.45273505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10807","last_page":"10818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9269000291824341,"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":0.9269000291824341,"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":0.010900000110268593,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.008500000461935997,"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/segmentation","display_name":"Segmentation","score":0.8194000124931335},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5497000217437744},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4706999957561493},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.429500013589859},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.42809998989105225},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4138999879360199},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.3961000144481659}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8194000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434999704360962},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5802000164985657},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.429500013589859},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4138999879360199},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3961000144481659},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01006","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:2503.16832","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16832","pdf_url":"https://arxiv.org/pdf/2503.16832","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.2503.16832","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16832","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:2503.16832","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16832","pdf_url":"https://arxiv.org/pdf/2503.16832","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,15,30,37,48,75,92,110,181],"novel":[3],"approach":[4,89],"for":[5,51,97],"simultaneous":[6],"self-supervised":[7,25,99],"video":[8,26,66,100,131,144,155,175],"alignment":[9,27,67,101,132,145,156,176],"and":[10,45,69,102,108,113,117,133,157,177],"action":[11,103,134,148,158,178],"segmentation":[12,135,149,159,179],"based":[13],"on":[14,43,64,74,129,188],"unified":[16,93],"optimal":[17,33,54,78,94],"transport":[18,34,55,79,95],"framework.":[19],"In":[20],"particular,":[21],"we":[22,86],"first":[23,171],"tackle":[24],"by":[28,90],"developing":[29],"fused":[31],"Gromov-Wasserstein":[32],"formulation":[35,80],"with":[36,81],"structural":[38],"prior,":[39],"which":[40,72,105],"trains":[41],"efficiently":[42],"GPUs":[44],"needs":[46],"only":[47],"few":[49],"iterations":[50],"solving":[52],"the":[53,61,163,170],"problem.":[56],"Our":[57,184],"single-task":[58,125],"method":[59,141],"achieves":[60,142],"state-of-the-art":[62],"performance":[63],"multiple":[65],"benchmarks":[68],"outperforms":[70],"VAVA,":[71],"relies":[73],"traditional":[76],"Kantorovich":[77],"an":[82],"optimality":[83],"prior.":[84],"Furthermore,":[85],"extend":[87],"our":[88,139,166,189],"proposing":[91],"framework":[96],"joint":[98],"segmentation,":[104],"requires":[106],"training":[107],"storing":[109],"single":[111,182],"model":[112],"saves":[114],"both":[115],"time":[116],"memory":[118],"consumption":[119],"as":[120],"compared":[121],"to":[122,162,173],"two":[123],"different":[124],"models.":[126],"Extensive":[127],"evaluations":[128],"several":[130],"datasets":[136],"demonstrate":[137],"that":[138],"multi-task":[140],"comparable":[143],"yet":[146],"superior":[147],"results":[150],"over":[151],"previous":[152],"methods":[153],"in":[154],"respectively.":[160],"Finally,":[161],"best":[164],"of":[165],"knowledge,":[167],"this":[168],"is":[169,186],"work":[172],"unify":[174],"into":[180],"model.":[183],"code":[185],"available":[187],"research":[190],"website:":[191],"https://retrocausal.ai/research/.":[192]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}