{"id":"https://openalex.org/W4415315604","doi":"https://doi.org/10.1016/j.cviu.2025.104528","title":"Learning to recognize correctly completed procedure steps in egocentric assembly videos through spatio-temporal modeling","display_name":"Learning to recognize correctly completed procedure steps in egocentric assembly videos through spatio-temporal modeling","publication_year":2025,"publication_date":"2025-10-18","ids":{"openalex":"https://openalex.org/W4415315604","doi":"https://doi.org/10.1016/j.cviu.2025.104528"},"language":"en","primary_location":{"id":"doi:10.1016/j.cviu.2025.104528","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2025.104528","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.cviu.2025.104528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000452423","display_name":"Tim J. Schoonbeek","orcid":"https://orcid.org/0000-0003-2403-6764"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]},{"id":"https://openalex.org/I927257375","display_name":"ASML (Netherlands)","ror":"https://ror.org/01vxknj13","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210092504","https://openalex.org/I927257375"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Tim J. Schoonbeek","raw_affiliation_strings":["ASML, De Run 6501, 5504 DR, Veldhoven, Netherlands","Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-2403-6764","affiliations":[{"raw_affiliation_string":"ASML, De Run 6501, 5504 DR, Veldhoven, Netherlands","institution_ids":["https://openalex.org/I927257375"]},{"raw_affiliation_string":"Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111340519","display_name":"Shao-Hsuan Hung","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shao-Hsuan Hung","raw_affiliation_strings":["Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dan Lehman","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dan Lehman","raw_affiliation_strings":["Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036527205","display_name":"Hans Onvlee","orcid":null},"institutions":[{"id":"https://openalex.org/I927257375","display_name":"ASML (Netherlands)","ror":"https://ror.org/01vxknj13","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210092504","https://openalex.org/I927257375"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hans Onvlee","raw_affiliation_strings":["ASML, De Run 6501, 5504 DR, Veldhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASML, De Run 6501, 5504 DR, Veldhoven, Netherlands","institution_ids":["https://openalex.org/I927257375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056645389","display_name":"Jacek Kustra","orcid":"https://orcid.org/0000-0002-8526-8561"},"institutions":[{"id":"https://openalex.org/I927257375","display_name":"ASML (Netherlands)","ror":"https://ror.org/01vxknj13","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210092504","https://openalex.org/I927257375"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jacek Kustra","raw_affiliation_strings":["ASML, De Run 6501, 5504 DR, Veldhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASML, De Run 6501, 5504 DR, Veldhoven, Netherlands","institution_ids":["https://openalex.org/I927257375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029008213","display_name":"Peter H. N. de With","orcid":"https://orcid.org/0000-0002-7639-7716"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Peter H.N. De With","raw_affiliation_strings":["Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075677746","display_name":"Fons van der Sommen","orcid":"https://orcid.org/0000-0002-3593-2356"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Fons Van der Sommen","raw_affiliation_strings":["Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Eindhoven University of Technology, P.O. Box 513, 5600 MB, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000452423"],"corresponding_institution_ids":["https://openalex.org/I83019370","https://openalex.org/I927257375"],"apc_list":{"value":2370,"currency":"USD","value_usd":2370},"apc_paid":{"value":2370,"currency":"USD","value_usd":2370},"fwci":1.0528,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78715839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"262","issue":null,"first_page":"104528","last_page":"104528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9955999851226807,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9710000157356262,"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/robustness","display_name":"Robustness (evolution)","score":0.6884999871253967},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6468999981880188},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6337000131607056},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.448199987411499},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4009000062942505},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3961000144481659},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3806999921798706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845300018787384},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6884999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6790000200271606},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6468999981880188},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4009000062942505},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3961000144481659},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3767000138759613},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25450000166893005},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.cviu.2025.104528","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2025.104528","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"},{"id":"pmh:oai:pure.tue.nl:openaire/50bd0564-a85a-4322-b573-685dac53d07d","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/50bd0564-a85a-4322-b573-685dac53d07d","pdf_url":"https://pure.tue.nl/ws/files/381118700/1-s2.0-S1077314225002516-main.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Schoonbeek, T J, Hung, S-H, Lehman, D, Onvlee, H, Kustra, J, De With, P H N & Van der Sommen, F 2025, 'Learning to recognize correctly completed procedure steps in egocentric assembly videos through spatio-temporal modeling', Computer Vision and Image Understanding, vol. 262, 104528. https://doi.org/10.1016/j.cviu.2025.104528","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.cviu.2025.104528","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2025.104528","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1712847615","display_name":null,"funder_award_id":"TKI2112P07","funder_id":"https://openalex.org/F4320323783","funder_display_name":"ASML"}],"funders":[{"id":"https://openalex.org/F4320323783","display_name":"ASML","ror":"https://ror.org/01vxknj13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1983364832","https://openalex.org/W2066792529","https://openalex.org/W2156303437","https://openalex.org/W2513263058","https://openalex.org/W2523246573","https://openalex.org/W2792764867","https://openalex.org/W2896457183","https://openalex.org/W2961553857","https://openalex.org/W2974686944","https://openalex.org/W2976669726","https://openalex.org/W3021013305","https://openalex.org/W3022796439","https://openalex.org/W3096719817","https://openalex.org/W3100859887","https://openalex.org/W3117567287","https://openalex.org/W3121052081","https://openalex.org/W3191734489","https://openalex.org/W3210279979","https://openalex.org/W4200150166","https://openalex.org/W4207046678","https://openalex.org/W4220710236","https://openalex.org/W4221153256","https://openalex.org/W4234767367","https://openalex.org/W4287812705","https://openalex.org/W4309368547","https://openalex.org/W4311121622","https://openalex.org/W4313071313","https://openalex.org/W4384807615","https://openalex.org/W4385245566","https://openalex.org/W4386065873","https://openalex.org/W4387917672","https://openalex.org/W4390872096","https://openalex.org/W4402753918","https://openalex.org/W4402770916","https://openalex.org/W4402830326","https://openalex.org/W4408011118"],"related_works":[],"abstract_inverted_index":{"Procedure":[0,61],"step":[1,102,158,222],"recognition":[2,223],"(PSR)":[3],"aims":[4],"to":[5,100,121,166,192,253],"identify":[6],"all":[7],"correctly":[8],"completed":[9,194],"steps":[10],"and":[11,41,74,97,126,146,155,162,247],"their":[12],"sequential":[13],"order":[14],"in":[15,31,174],"videos":[16],"of":[17,87,189,240],"procedural":[18],"tasks.":[19],"The":[20,77,196],"existing":[21],"state-of-the-art":[22],"models":[23],"rely":[24,185],"solely":[25],"on":[26,143,186,249],"detecting":[27],"assembly":[28,78,157],"object":[29,191],"states":[30],"individual":[32],"video":[33],"frames.":[34],"By":[35],"neglecting":[36],"temporal":[37,75,98,129,242],"features,":[38],"model":[39],"robustness":[40],"accuracy":[42],"are":[43,48],"limited,":[44],"especially":[45],"when":[46],"objects":[47],"partially":[49],"occluded.":[50],"To":[51],"overcome":[52],"these":[53,134],"limitations,":[54],"we":[55],"propose":[56],"Spatio-Temporal":[57],"Occlusion-Resilient":[58],"Modeling":[59],"for":[60,68,198,220],"Step":[62],"Recognition":[63],"(STORM-PSR),":[64],"a":[65,111,116,127],"dual-stream":[66],"framework":[67],"PSR":[69,245],"that":[70,131,171],"leverages":[71],"both":[72,95],"spatial":[73,96,112,124,135,231],"features.":[76,232],"state":[79],"detection":[80],"stream":[81,93,109],"operates":[82],"effectively":[83],"with":[84,201],"unobstructed":[85,187],"views":[86,188],"the":[88,91,144,150,179,190,202,241,250],"object,":[89],"while":[90],"spatio-temporal":[92,180],"captures":[94],"features":[99,136,216],"recognize":[101],"completions":[103,159],"even":[104],"under":[105],"partial":[106],"occlusion.":[107],"This":[108],"includes":[110],"encoder,":[113],"pre-trained":[114],"using":[115],"novel":[117],"weakly":[118],"supervised":[119],"approach":[120],"capture":[122],"meaningful":[123,230],"representations,":[125],"transformer-based":[128],"encoder":[130],"learns":[132],"how":[133],"relate":[137],"over":[138],"time.":[139],"STORM-PSR":[140],"is":[141,176,207],"evaluated":[142],"MECCANO":[145,205,251],"IndustReal":[147],"datasets,":[148],"reducing":[149],"average":[151],"delay":[152,175,219],"between":[153],"actual":[154],"predicted":[156],"by":[160,178],"11.2%":[161],"26.1%,":[163],"respectively,":[164],"compared":[165],"prior":[167],"methods.":[168],"We":[169],"demonstrate":[170],"this":[172],"reduction":[173],"driven":[177],"stream,":[181],"which":[182],"does":[183],"not":[184],"infer":[193],"steps.":[195],"code":[197],"STORM-PSR,":[199],"along":[200],"newly":[203],"annotated":[204],"labels,":[206],"made":[208],"publicly":[209],"available":[210],"at":[211],"https://timschoonbeek.github.io/stormpsr":[212],".":[213],"\u2022":[214,225,233,244],"Spatio-temporal":[215],"reduce":[217],"prediction":[218],"procedure":[221],"(PSR).":[224],"Weakly-supervised":[226],"key-frame":[227],"selection":[228],"enables":[229],"Key-clip":[234],"aware":[235],"sampling":[236],"significantly":[237],"improves":[238],"training":[239],"encoder.":[243],"annotations":[246],"benchmark":[248],"dataset":[252],"stimulate":[254],"further":[255],"research.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-18T00:00:00"}