{"id":"https://openalex.org/W3167771209","doi":"https://doi.org/10.1109/iros51168.2021.9636711","title":"APEX: Unsupervised, Object-Centric Scene Segmentation and Tracking for Robot Manipulation","display_name":"APEX: Unsupervised, Object-Centric Scene Segmentation and Tracking for Robot Manipulation","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3167771209","doi":"https://doi.org/10.1109/iros51168.2021.9636711","mag":"3167771209"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636711","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008907115","display_name":"Yizhe Wu","orcid":"https://orcid.org/0009-0004-0369-5298"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yizhe Wu","raw_affiliation_strings":["Applied AI Lab, Oxford Robotics Institute, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Lab, Oxford Robotics Institute, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015428481","display_name":"\u014ciwi Parker Jones","orcid":"https://orcid.org/0000-0003-0307-9837"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oiwi Parker Jones","raw_affiliation_strings":["Applied AI Lab, Oxford Robotics Institute, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Lab, Oxford Robotics Institute, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023103880","display_name":"Martin Engelcke","orcid":"https://orcid.org/0000-0001-8306-1236"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Engelcke","raw_affiliation_strings":["Applied AI Lab, Oxford Robotics Institute, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Lab, Oxford Robotics Institute, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027013897","display_name":"Ingmar Posner","orcid":"https://orcid.org/0000-0001-6270-700X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ingmar Posner","raw_affiliation_strings":["Applied AI Lab, Oxford Robotics Institute, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Lab, Oxford Robotics Institute, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.4774,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71347812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3375","last_page":"3382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9987999796867371,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983000159263611,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8474093675613403},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7840346693992615},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7285527586936951},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7226436138153076},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6407124400138855},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.534419596195221},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5132174491882324},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4665358364582062},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46071797609329224},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.45307254791259766},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4523710310459137},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4431800842285156},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.42833173274993896},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4224376380443573},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4103752374649048}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8474093675613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840346693992615},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7285527586936951},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7226436138153076},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6407124400138855},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.534419596195221},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5132174491882324},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4665358364582062},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46071797609329224},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.45307254791259766},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4523710310459137},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4431800842285156},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.42833173274993896},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4224376380443573},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4103752374649048},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros51168.2021.9636711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636711","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:f2dd4798-b26f-445c-9854-da8d75115f2f","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:f2dd4798-b26f-445c-9854-da8d75115f2f","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3105706333","display_name":null,"funder_award_id":"EP/V000748/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W1485009520","https://openalex.org/W1516111018","https://openalex.org/W1522301498","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2033403400","https://openalex.org/W2150066425","https://openalex.org/W2180332918","https://openalex.org/W2291627510","https://openalex.org/W2327562811","https://openalex.org/W2340897893","https://openalex.org/W2547875792","https://openalex.org/W2603737562","https://openalex.org/W2605055943","https://openalex.org/W2747264013","https://openalex.org/W2786615588","https://openalex.org/W2807242871","https://openalex.org/W2903585023","https://openalex.org/W2911448865","https://openalex.org/W2919112510","https://openalex.org/W2935837427","https://openalex.org/W2944892105","https://openalex.org/W2952484912","https://openalex.org/W2953106684","https://openalex.org/W2962889261","https://openalex.org/W2962897886","https://openalex.org/W2963150697","https://openalex.org/W2963323244","https://openalex.org/W2963717490","https://openalex.org/W2963951231","https://openalex.org/W2964121744","https://openalex.org/W2964213104","https://openalex.org/W2964846271","https://openalex.org/W2994971263","https://openalex.org/W2999417551","https://openalex.org/W3000266068","https://openalex.org/W3004808386","https://openalex.org/W3004815632","https://openalex.org/W3006036127","https://openalex.org/W3008721991","https://openalex.org/W3028924880","https://openalex.org/W3035161894","https://openalex.org/W3037784242","https://openalex.org/W3039384219","https://openalex.org/W3040490156","https://openalex.org/W3089920618","https://openalex.org/W3095753995","https://openalex.org/W3096773348","https://openalex.org/W3102696055","https://openalex.org/W3105675572","https://openalex.org/W3109420014","https://openalex.org/W3117784790","https://openalex.org/W3154552141","https://openalex.org/W3176179930","https://openalex.org/W3205261317","https://openalex.org/W4244030505","https://openalex.org/W4285704217","https://openalex.org/W4288088514","https://openalex.org/W4293376383","https://openalex.org/W4295246696","https://openalex.org/W4295747950","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6685666431","https://openalex.org/W6696672603","https://openalex.org/W6702162793","https://openalex.org/W6718986230","https://openalex.org/W6729448088","https://openalex.org/W6736244717","https://openalex.org/W6742720488","https://openalex.org/W6752279500","https://openalex.org/W6758420182","https://openalex.org/W6759669191","https://openalex.org/W6760424586","https://openalex.org/W6762284573","https://openalex.org/W6766312635","https://openalex.org/W6769570503","https://openalex.org/W6772619266","https://openalex.org/W6773320568","https://openalex.org/W6773930613","https://openalex.org/W6775668235","https://openalex.org/W6779174393","https://openalex.org/W6779809370","https://openalex.org/W6780399172","https://openalex.org/W6783637975","https://openalex.org/W6785418010","https://openalex.org/W6786736258","https://openalex.org/W6793805516"],"related_works":["https://openalex.org/W2047973478","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W1508899372","https://openalex.org/W2039460805","https://openalex.org/W4250956039","https://openalex.org/W2965594636","https://openalex.org/W2912550626"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,16,28,51,70,79,149,171],"unsupervised":[3,172],"learning":[4],"for":[5,14,126,160,184],"object":[6,124,158,173,190],"detection,":[7],"segmentation,":[8],"and":[9,67,81,97,123,151,157,175],"tracking":[10],"hold":[11],"significant":[12],"promise":[13],"applications":[15],"robotics.":[17],"A":[18],"common":[19],"approach":[20],"is":[21,63,89],"to":[22,65],"frame":[23],"these":[24],"tasks":[25],"as":[26,48],"inference":[27],"probabilistic":[29],"latent-variable":[30,60],"models.":[31],"In":[32,162],"this":[33],"paper,":[34],"however,":[35,116],"we":[36,106,194],"show":[37],"that":[38,76],"the":[39,84,110,133,168,179,197,204],"current":[40,169],"state-of-the-art":[41,170],"struggles":[42],"with":[43,144],"visually":[44],"complex":[45],"scenes":[46,73],"such":[47],"typically":[49],"encountered":[50],"robot":[52,85,185],"manipulation":[53],"tasks.":[54],"We":[55,130,177],"propose":[56],"APEX,":[57],"a":[58,92,98,127,140,147],"new":[59],"model":[61],"which":[62,138,152],"able":[64],"segment":[66],"track":[68],"objects":[69,75,145],"more":[71],"realistic":[72],"featuring":[74],"vary":[77],"widely":[78],"size":[80],"texture,":[82],"including":[83],"arm":[86,142],"itself.":[87],"This":[88,114],"achieved":[90],"by":[91],"principled":[93],"mask":[94],"normalisation":[95],"algorithm":[96],"high-resolution":[99],"scene":[100],"encoder.":[101],"To":[102],"evaluate":[103],"our":[104,182],"approach,":[105],"present":[107],"results":[108],"on":[109,146,188],"real-world":[111],"Sketchy":[112],"dataset.":[113],"dataset,":[115],"does":[117],"not":[118],"contain":[119],"ground":[120],"truth":[121],"masks":[122,156],"IDs":[125,159],"quantitative":[128],"evaluation.":[129],"thus":[131],"introduce":[132],"Panda":[134,141],"Pushing":[135],"Dataset":[136],"(P2D)":[137],"shows":[139],"interacting":[143],"table":[148],"simulation":[150],"includes":[153],"ground-truth":[154],"segmentation":[155,174],"tracking.":[161,176],"both":[163],"cases,":[164],"APEX":[165],"comprehensively":[166],"outperforms":[167],"demonstrate":[178],"efficacy":[180],"of":[181],"segmentations":[183],"skill":[186],"execution":[187],"an":[189],"arrangement":[191],"task,":[192],"where":[193],"also":[195],"achieve":[196],"best":[198],"or":[199],"comparable":[200],"performance":[201],"among":[202],"all":[203],"baselines.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}