{"id":"https://openalex.org/W7204238688","doi":"https://doi.org/10.48550/arxiv.2608.24043","title":"ConsensusTAS: Self-Supervised Temporal Action Segmentation for Long-Horizon Construction Videos","display_name":"ConsensusTAS: Self-Supervised Temporal Action Segmentation for Long-Horizon Construction Videos","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204238688","doi":"https://doi.org/10.48550/arxiv.2608.24043"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.24043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24043","pdf_url":"https://arxiv.org/pdf/2608.24043","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.24043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148316753","display_name":"Xiaoshan Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhou, Xiaoshan","raw_affiliation_strings":["School of Civil and Environmental Engineering , University of New South Wales , Australia","School of Project Management , University of Sydney , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Civil and Environmental Engineering , University of New South Wales , Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Project Management , University of Sydney , Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100936133","display_name":"Yafei Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yafei","raw_affiliation_strings":["Yafei"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yafei","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9911999702453613,"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":0.9911999702453613,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.0024999999441206455,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/temporal-action-segmentation","display_name":"temporal action segmentation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.843999981880188},{"id":"https://openalex.org/keywords/label-free-segmentation","display_name":"label-free segmentation","score":0.6800000071525574},{"id":"https://openalex.org/keywords/bricklaying","display_name":"bricklaying","score":0.8140000104904175},{"id":"https://openalex.org/keywords/human-robot-collaboration","display_name":"human-robot collaboration","score":0.9800000190734863},{"id":"https://openalex.org/keywords/video-surveillance","display_name":"video surveillance","score":0.6489999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379999756813049},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6342999935150146},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.614799976348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3384999930858612},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2721000015735626}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24043","pdf_url":"https://arxiv.org/pdf/2608.24043","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,"listed_in":[],"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.2608.24043","doi":"https://doi.org/10.48550/arxiv.2608.24043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24043","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,"listed_in":[],"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:2608.24043","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24043","pdf_url":"https://arxiv.org/pdf/2608.24043","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,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204238688.pdf","grobid_xml":"https://content.openalex.org/works/W7204238688.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recognizing":[0],"sequential":[1],"construction":[2,35,75,149],"activities":[3],"is":[4,66,77],"important":[5],"for":[6,10,207],"collaborative":[7],"human-robot":[8,211],"work;":[9],"example,":[11],"robots":[12],"are":[13],"able":[14],"to":[15,44,90],"understand":[16],"workers'":[17],"current":[18],"and":[19,22,52,133,160,180,210],"upcoming":[20],"actions":[21,162],"provide":[23],"timely":[24],"tool":[25],"delivery":[26],"or":[27],"physical":[28],"support.":[29],"However,":[30],"despite":[31],"extensive":[32],"research":[33],"on":[34,111,125,131,138,147,173,200,213],"worker":[36],"activity":[37,46,58,97,166],"recognition,":[38],"existing":[39],"studies":[40],"have":[41],"been":[42],"limited":[43],"classifying":[45],"categories,":[47],"such":[48,169],"as":[49,170],"climbing,":[50],"lifting,":[51],"walking,":[53],"instead":[54],"of":[55,104,123,129,136,167],"recognizing":[56],"fine-grained":[57],"transitions":[59],"from":[60,141],"long-horizon":[61],"sequences.":[62],"Addressing":[63],"this":[64,80],"problem":[65],"challenging":[67],"because":[68],"annotating":[69],"action":[70,186],"temporal":[71,185],"boundaries":[72],"in":[73],"long":[74],"videos":[76,140],"time-consuming.":[78],"In":[79],"study,":[81],"we":[82],"propose":[83],"ConsensusTAS,":[84],"a":[85,174,201],"label-free,":[86],"self-supervised":[87],"learning":[88],"approach":[89],"segment":[91],"continuous":[92],"video":[93,208],"streams":[94],"into":[95],"distinct":[96],"phases":[98],"by":[99],"exploiting":[100],"the":[101,156,164,177],"internal":[102],"consensus":[103],"candidate":[105],"segmentations.":[106],"We":[107,143],"evaluated":[108],"our":[109,196],"algorithm":[110],"three":[112],"public":[113],"datasets,":[114],"where":[115,151],"it":[116,146],"outperformed":[117],"state-of-the-art":[118],"methods,":[119],"achieving":[120],"an":[121,127,134],"F1@10":[122,128],"73.08":[124],"GTEA,":[126],"64.33":[130],"Breakfast,":[132],"F1@50":[135],"33.50":[137],"static-camera":[139],"Assembly101.":[142],"also":[144],"tested":[145],"real-world":[148],"videos,":[150],"post-hoc":[152],"evaluation":[153],"showed":[154],"that":[155,189],"model":[157],"successfully":[158],"recognized":[159],"segmented":[161],"within":[163],"composite":[165],"bricklaying,":[168],"spreading":[171],"mortar":[172],"brick,":[175,178],"placing":[176],"pressing,":[179],"aligning.":[181],"Compared":[182],"with":[183],"other":[184],"segmentation":[187],"models":[188],"require":[190],"computationally":[191],"intensive":[192],"large":[193],"vision-language":[194],"models,":[195],"method":[197],"can":[198],"run":[199],"CPU,":[202],"which":[203],"provides":[204],"practical":[205],"value":[206],"surveillance":[209],"collaboration":[212],"mobile":[214],"robotic":[215],"platforms.":[216]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-08-27T00:00:00"}