{"id":"https://openalex.org/W4415398853","doi":"https://doi.org/10.1109/icdl63968.2025.11204356","title":"Push, See, Predict: Emergent Perception Through Intrinsically Motivated Play","display_name":"Push, See, Predict: Emergent Perception Through Intrinsically Motivated Play","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415398853","doi":"https://doi.org/10.1109/icdl63968.2025.11204356"},"language":"en","primary_location":{"id":"doi:10.1109/icdl63968.2025.11204356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204356","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/A5120084023","display_name":"Orestis Konstantaropoulos","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":"Orestis Konstantaropoulos","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/A5016381589","display_name":"Mehdi Khamassi","orcid":"https://orcid.org/0000-0002-2515-1046"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mehdi Khamassi","raw_affiliation_strings":["Sorbonne University,Institute of Intelligent Systems and Robotics, CNRS,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne University,Institute of Intelligent Systems and Robotics, CNRS,Paris,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]},{"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/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":"Petros Maragos","raw_affiliation_strings":["RI/Athena RC,Maroussi,Greece,15125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RI/Athena RC,Maroussi,Greece,15125","institution_ids":["https://openalex.org/I4210156054"]}]},{"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":["RI/AthenaRC,Maroussi,Greece,15125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RI/AthenaRC,Maroussi,Greece,15125","institution_ids":["https://openalex.org/I4210156054"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.34746054,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10731","display_name":"Educational Games and Gamification","score":0.8845000267028809,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10731","display_name":"Educational Games and Gamification","score":0.8845000267028809,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11079","display_name":"Creativity in Education and Neuroscience","score":0.7908999919891357,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6883000135421753},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5461000204086304},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4964999854564667},{"id":"https://openalex.org/keywords/perceptual-system","display_name":"Perceptual system","score":0.4643000066280365},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43050000071525574},{"id":"https://openalex.org/keywords/active-perception","display_name":"Active perception","score":0.42660000920295715},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.42570000886917114},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.39989998936653137},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.34630000591278076}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6510999798774719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6026999950408936},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C28063669","wikidata":"https://www.wikidata.org/wiki/Q7167042","display_name":"Perceptual system","level":3,"score":0.4643000066280365},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.42660000920295715},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.42570000886917114},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C20864712","wikidata":"https://www.wikidata.org/wiki/Q667800","display_name":"Biological motion","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204356","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"},{"id":"pmh:oai:HAL:hal-05366923v1","is_oa":false,"landing_page_url":"https://hal.sorbonne-universite.fr/hal-05366923","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.greeksin.ai","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-05366934v1","is_oa":false,"landing_page_url":"https://hal.sorbonne-universite.fr/hal-05366934","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://icdl2025.fel.cvut.cz","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unlike":[0],"conventional":[1],"vision":[2,158],"systems":[3],"that":[4,183],"rely":[5],"on":[6,79,124,162],"passive":[7],"observation,":[8],"biological":[9],"agents":[10,41],"learn":[11,44],"through":[12,26],"physical":[13,187],"interaction.":[14,194],"Can":[15],"a":[16,59,131,175],"robot":[17],"similarly":[18],"develop":[19],"an":[20,118],"understanding":[21],"of":[22,109,199],"its":[23],"environment":[24,178],"purely":[25],"interaction,":[27],"without":[28],"prior":[29],"knowledge":[30],"or":[31],"external":[32],"supervision?":[33],"In":[34],"this":[35],"work,":[36],"we":[37,116],"explore":[38],"how":[39,50],"artificial":[40],"can":[42,189],"autonomously":[43],"via":[45],"intrinsic":[46],"motivation,":[47],"much":[48],"like":[49],"children":[51],"engage":[52],"in":[53,140,174],"curious":[54],"free":[55],"play.":[56],"We":[57,170],"propose":[58],"novel,":[60],"fully":[61],"self-supervised,":[62],"object-centric":[63,95,202],"learning":[64,203],"framework.":[65],"The":[66],"system":[67],"first":[68],"segments":[69],"visual":[70,185],"input":[71],"into":[72],"discrete":[73],"entities":[74],"using":[75],"Slot":[76],"Attention,":[77],"trained":[78,92],"data":[80,164],"collected":[81],"from":[82,192],"random":[83,149],"robotic":[84,177],"actions.":[85],"A":[86],"graph-based":[87],"world":[88,125,160,206],"model":[89,161],"is":[90],"then":[91],"to":[93,100,105,133,142],"predict":[94],"dynamics":[96],"but":[97],"initially":[98],"struggles":[99],"capture":[101],"object":[102,146],"motion":[103],"due":[104],"the":[106,110,153,157,197],"limited":[107],"diversity":[108],"initial":[111],"interactions.":[112],"To":[113],"overcome":[114],"this,":[115],"introduce":[117],"intrinsically":[119,200],"motivated":[120],"reward":[121],"signal":[122],"based":[123],"model\u2019s":[126],"prediction":[127,166],"error,":[128],"which":[129],"drives":[130],"policy":[132],"collect":[134],"more":[135,145],"informative":[136],"trajectories.":[137],"This":[138,195],"results":[139],"up":[141],"three":[143],"times":[144],"displacement":[147],"than":[148],"actions,":[150],"significantly":[151],"enriching":[152],"dataset.":[154],"Fine-tuning":[155],"both":[156],"and":[159,167,186,208],"these":[163],"improves":[165],"reconstruction":[168],"performance.":[169],"validate":[171],"our":[172],"method":[173],"simulated":[176],"with":[179],"diverse":[180],"objects,":[181],"demonstrating":[182],"meaningful":[184],"representations":[188],"emerge":[190],"entirely":[191],"self-supervised":[193],"highlights":[196],"potential":[198],"motivated,":[201],"for":[204],"autonomous":[205],"perception":[207],"modeling.":[209]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-22T00:00:00"}