{"id":"https://openalex.org/W4415398803","doi":"https://doi.org/10.1109/icdl63968.2025.11204392","title":"Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning","display_name":"Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415398803","doi":"https://doi.org/10.1109/icdl63968.2025.11204392"},"language":null,"primary_location":{"id":"doi:10.1109/icdl63968.2025.11204392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","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/A5119938508","display_name":"Nikos Giannakakis","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikos Giannakakis","raw_affiliation_strings":["National Technical University of Athens,School of Electrical & Computer Engineering,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens,School of Electrical & Computer Engineering,Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115645831","display_name":"Argyris Manetas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Argyris Manetas","raw_affiliation_strings":["Robotics Institute, Athena Research Center,Maroussi,Greece,15125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Athena Research Center,Maroussi,Greece,15125","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025430640","display_name":"Panagiotis P. Filntisis","orcid":"https://orcid.org/0000-0002-2042-245X"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panagiotis P. Filntisis","raw_affiliation_strings":["Robotics Institute, Athena Research Center,Maroussi,Greece,15125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Athena Research Center,Maroussi,Greece,15125","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079243420","display_name":"Petros Maragos","orcid":"https://orcid.org/0000-0003-0534-2707"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Petros Maragos","raw_affiliation_strings":["National Technical University of Athens,School of Electrical & Computer Engineering,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens,School of Electrical & Computer Engineering,Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021130742","display_name":"George Retsinas","orcid":"https://orcid.org/0000-0001-6734-3575"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Retsinas","raw_affiliation_strings":["Robotics Institute, Athena Research Center,Maroussi,Greece,15125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Athena Research Center,Maroussi,Greece,15125","institution_ids":["https://openalex.org/I4210156054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.25775906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9444000124931335,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9444000124931335,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/leverage","display_name":"Leverage (statistics)","score":0.7246000170707703},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6051999926567078},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5817999839782715},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5612999796867371},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5227000117301941},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5135999917984009},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49880000948905945},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47850000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609999775886536},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7246000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7092999815940857},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6051999926567078},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47850000858306885},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4043999910354614},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3100000023841858},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Learning":[0],"visual":[1,52,103,181],"representations":[2,104],"from":[3],"observing":[4],"actions":[5,145],"to":[6,88,154,165,177,183],"benefit":[7,135],"robot":[8],"visuo-motor":[9],"policy":[10],"generation":[11,54],"is":[12],"a":[13,56],"promising":[14],"direction":[15],"that":[16,34,47,102,127,139],"closely":[17],"resembles":[18],"human":[19,92,144],"cognitive":[20],"function":[21],"and":[22,27,51,77,108,122,138,174,186],"perception.":[23],"Motivated":[24],"by":[25,30],"this,":[26,70],"further":[28],"inspired":[29],"psychological":[31],"theories":[32],"suggesting":[33],"humans":[35],"process":[36],"scenes":[37],"in":[38,55],"an":[39,44],"object-based":[40],"fashion,":[41],"we":[42,71,100,125],"propose":[43],"object-centric":[45],"encoder":[46],"performs":[48],"semantic":[49,120],"segmentation":[50,121],"representation":[53],"coupled":[57],"manner,":[58],"unlike":[59],"other":[60],"works,":[61],"which":[62],"treat":[63],"these":[64],"as":[65],"separate":[66],"processes.":[67],"To":[68],"achieve":[69],"leverage":[72],"the":[73,79,113,163,175],"Slot":[74],"Attention":[75],"mechanism":[76],"use":[78],"SOLV":[80],"[1]":[81],"model,":[82],"pretrained":[83,130],"on":[84,91,131,141,168,179],"large":[85],"out-of-domain":[86,132],"datasets,":[87],"bootstrap":[89],"fine-tuning":[90,140],"action":[93,172],"video":[94],"data.":[95],"Through":[96],"simulated":[97],"robotic":[98,158],"tasks,":[99],"demonstrate":[101],"can":[105,134,149],"enhance":[106],"reinforcement":[107],"imitation":[109],"learning":[110],"training,":[111],"highlighting":[112],"effectiveness":[114],"of":[115],"our":[116],"integrated":[117],"approach":[118],"for":[119],"encoding.":[123],"Furthermore,":[124],"show":[126,162],"exploiting":[128],"models":[129],"datasets":[133,142,173],"this":[136],"process,":[137],"depicting":[143],"\u2014although":[146],"still":[147],"out-of-domain\u2014":[148],"significantly":[150],"improve":[151,187],"performance":[152],"due":[153],"close":[155],"alignment":[156],"with":[157],"tasks.":[159],"These":[160],"findings":[161],"capability":[164],"reduce":[166],"reliance":[167],"annotated":[169],"or":[170],"robot-specific":[171],"potential":[176],"build":[178],"existing":[180],"encoders":[182],"accelerate":[184],"training":[185],"generalizability.":[188]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-22T00:00:00"}