{"id":"https://openalex.org/W4407690534","doi":"https://doi.org/10.1109/tro.2025.3543274","title":"InvSlotGNN: Unsupervised Discovery of Viewpoint Invariant Multiobject Representations and Visual Dynamics","display_name":"InvSlotGNN: Unsupervised Discovery of Viewpoint Invariant Multiobject Representations and Visual Dynamics","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407690534","doi":"https://doi.org/10.1109/tro.2025.3543274"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2025.3543274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2025.3543274","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"article","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/A5088480186","display_name":"Alireza Rezazadeh","orcid":"https://orcid.org/0000-0002-2457-9470"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alireza Rezazadeh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0002-2457-9470","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088122096","display_name":"Houjian Yu","orcid":"https://orcid.org/0000-0001-8869-5078"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Houjian Yu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0001-8869-5078","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052038649","display_name":"Karthik Desingh","orcid":"https://orcid.org/0000-0002-1817-1575"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Desingh","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0002-1817-1575","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057994317","display_name":"Changhyun Choi","orcid":"https://orcid.org/0000-0003-4715-3576"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changhyun Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0003-4715-3576","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":0.8823,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70724038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"41","issue":null,"first_page":"1812","last_page":"1824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9965999722480774,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.992900013923645,"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":0.6563709378242493},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6282650828361511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6085781455039978},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4871982932090759},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43016931414604187},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.41831257939338684},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.37939387559890747},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19514748454093933},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08181893825531006}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6563709378242493},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6282650828361511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6085781455039978},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4871982932090759},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43016931414604187},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.41831257939338684},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37939387559890747},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19514748454093933},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08181893825531006},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"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":1,"locations":[{"id":"doi:10.1109/tro.2025.3543274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2025.3543274","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1505952289","https://openalex.org/W2052021678","https://openalex.org/W2158782408","https://openalex.org/W2528489519","https://openalex.org/W2962785568","https://openalex.org/W2967246123","https://openalex.org/W3215926197","https://openalex.org/W4246233237","https://openalex.org/W4312615341","https://openalex.org/W4385696075","https://openalex.org/W4386065597","https://openalex.org/W4389665522","https://openalex.org/W4390874575","https://openalex.org/W4401416294","https://openalex.org/W6720501231","https://openalex.org/W6729508183","https://openalex.org/W6736685754","https://openalex.org/W6746445604","https://openalex.org/W6748320467","https://openalex.org/W6751350349","https://openalex.org/W6764529735","https://openalex.org/W6765456200","https://openalex.org/W6769281838","https://openalex.org/W6774033856","https://openalex.org/W6779809370","https://openalex.org/W6781776314","https://openalex.org/W6782766965","https://openalex.org/W6792571853","https://openalex.org/W6796413303","https://openalex.org/W6800564222","https://openalex.org/W6809898026","https://openalex.org/W6857193639"],"related_works":["https://openalex.org/W2114275278","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W2139834217","https://openalex.org/W2163728705","https://openalex.org/W949345935","https://openalex.org/W2100099236","https://openalex.org/W1575585820"],"abstract_inverted_index":{"Learning":[0],"multiobject":[1,139,224],"dynamics":[2,54,79,140,238],"purely":[3],"from":[4,41,55,108,121,151,168],"visual":[5,205],"data":[6,97],"is":[7],"challenging":[8],"due":[9],"to":[10,46,83,119,142,176],"the":[11,63,84,143,148,163,166,178,182,193,212],"need":[12],"for":[13,37,51,73,184],"robust":[14],"object":[15],"representations":[16,40,107],"that":[17,80,90,99,137,202],"can":[18,92],"be":[19,93],"learned":[20],"through":[21],"robot":[22,60,189],"interactions.":[23],"In":[24],"previous":[25],"work":[26],"(Rezazadeh":[27],"et":[28],"al.,":[29],"2023),":[30],"we":[31,88,130,210],"introduced":[32],"two":[33],"novel":[34,71],"architectures:":[35],"SlotTransport":[36,91,169,196],"discovering":[38],"object-centric":[39,106,200],"singleview":[42,56],"RGB":[43,57],"images,":[44],"referred":[45],"as":[47],"slots,":[48],"and":[49,59,78,146,170,173,206,223,236],"SlotGNN":[50],"predicting":[52],"scene":[53,164,183],"images":[58],"interactions":[61],"using":[62,165],"discovered":[64],"slots.":[65],"This":[66],"article":[67],"introduces":[68],"InvSlotGNN,":[69,132],"a":[70,100,109,159],"framework":[72,232],"learning":[74,198],"multiview":[75,96,199,241],"slot":[76],"discovery":[77],"are":[81],"invariant":[82,141],"camera":[85,114,144],"viewpoint.":[86],"First,":[87],"demonstrate":[89,192],"trained":[94],"on":[95,188],"such":[98],"single":[101],"model":[102],"discovers":[103],"temporally":[104],"aligned,":[105],"wide":[110],"range":[111],"of":[112,135,162,181,195,214],"different":[113],"angles.":[115],"These":[116],"slots":[117,167,235],"bind":[118],"objects":[120],"various":[122],"viewpoints,":[123,186],"even":[124],"under":[125],"occlusion":[126],"or":[127],"absence.":[128],"Next,":[129],"introduce":[131],"an":[133],"extension":[134],"SlotGNN,":[136],"learns":[138,158],"angle":[145],"predicts":[147,234],"future":[149,179],"state":[150,180],"observations":[152],"taken":[153],"by":[154],"uncalibrated":[155],"cameras.":[156],"InvSlotGNN":[157,215],"graph":[160],"representation":[161],"performs":[171],"relational":[172],"spatial":[174],"reasoning":[175],"predict":[177],"arbitrary":[185],"conditioned":[187],"actions.":[190],"We":[191],"effectiveness":[194],"in":[197,216,239],"features":[201],"accurately":[203],"encode":[204],"positional":[207],"information.":[208],"Furthermore,":[209],"highlight":[211],"accuracy":[213],"downstream":[217],"robotic":[218],"tasks,":[219],"including":[220],"long-horizon":[221],"prediction":[222],"rearrangement.":[225],"Finally,":[226],"with":[227],"minimal":[228],"real":[229],"data,":[230],"our":[231],"robustly":[233],"their":[237],"real-world":[240],"scenarios.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}