{"id":"https://openalex.org/W4402352833","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651147","title":"Masked Multi-Query Slot Attention for Unsupervised Object Discovery","display_name":"Masked Multi-Query Slot Attention for Unsupervised Object Discovery","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352833","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651147"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5089956202","display_name":"Rishav Pramanik","orcid":"https://orcid.org/0000-0003-0144-8539"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rishav Pramanik","raw_affiliation_strings":["Jadavpur University,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jadavpur University,Kolkata,India","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096147981","display_name":"Jos\u00e9-Fabian Villa-V\u00e1squez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9-Fabian Villa-V\u00e1squez","raw_affiliation_strings":["ÉTS Montréal,Montréal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ÉTS Montréal,Montréal,Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039660800","display_name":"Marco Pedersoli","orcid":"https://orcid.org/0000-0002-7601-8640"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Pedersoli","raw_affiliation_strings":["ÉTS Montréal,Montréal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ÉTS Montréal,Montréal,Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9988999962806702,"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":0.9988999962806702,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.8155117034912109},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5400638580322266},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4541865587234497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4068987965583801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155117034912109},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5400638580322266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4541865587234497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4068987965583801}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:espace2.etsmtl.ca:29717","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/29717/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Compte rendu de conf\u00e9rence"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334971","display_name":"Science and Engineering Research Council","ror":"https://ror.org/00zgdb249"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W343636949","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1919709169","https://openalex.org/W1920234547","https://openalex.org/W2002781701","https://openalex.org/W2025768430","https://openalex.org/W2037227137","https://openalex.org/W2088049833","https://openalex.org/W2105628432","https://openalex.org/W2131297486","https://openalex.org/W2222512263","https://openalex.org/W2321533354","https://openalex.org/W2739365207","https://openalex.org/W2913954345","https://openalex.org/W2919112510","https://openalex.org/W2962749812","https://openalex.org/W2963087201","https://openalex.org/W2963420272","https://openalex.org/W2963598268","https://openalex.org/W2964028976","https://openalex.org/W3005680577","https://openalex.org/W3034781633","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3037784242","https://openalex.org/W3070936185","https://openalex.org/W3159481202","https://openalex.org/W3170863103","https://openalex.org/W3204171527","https://openalex.org/W4221161778","https://openalex.org/W4287102853","https://openalex.org/W4287120947","https://openalex.org/W4288024349","https://openalex.org/W4288028629","https://openalex.org/W4298186173","https://openalex.org/W4312804044","https://openalex.org/W4313145515","https://openalex.org/W4313150877","https://openalex.org/W4313156423","https://openalex.org/W4320166019","https://openalex.org/W4385245566","https://openalex.org/W4386071643","https://openalex.org/W6675869821","https://openalex.org/W6739901393","https://openalex.org/W6758665762","https://openalex.org/W6759669191","https://openalex.org/W6770196601","https://openalex.org/W6770820644","https://openalex.org/W6774314701","https://openalex.org/W6779809370","https://openalex.org/W6779997284","https://openalex.org/W6796303064","https://openalex.org/W6796761347","https://openalex.org/W6797962799","https://openalex.org/W6843797405","https://openalex.org/W6849641695"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Unsupervised":[0],"object":[1,26,187],"discovery":[2],"is":[3,192],"becoming":[4],"an":[5,17,67],"essential":[6],"line":[7],"of":[8,80,132,143,177],"research":[9],"for":[10],"tackling":[11],"recognition":[12],"problems":[13],"that":[14,31,96],"require":[15],"decomposing":[16],"image":[18],"into":[19],"entities,":[20],"such":[21],"as":[22],"semantic":[23],"segmentation":[24],"and":[25,41,46,167,180],"detection.":[27],"Recently,":[28],"object-centric":[29,68],"methods":[30,50],"leverage":[32],"self-supervision":[33],"have":[34],"gained":[35],"popularity,":[36],"due":[37],"to":[38,43,105,121,128,159],"their":[39,183],"simplicity":[40],"adaptability":[42],"different":[44],"settings":[45],"conditions.":[47],"However,":[48],"those":[49],"do":[51],"not":[52],"exploit":[53],"effective":[54],"techniques":[55],"already":[56],"employed":[57],"in":[58,70],"modern":[59],"self-supervised":[60],"approaches.":[61],"In":[62],"this":[63],"work,":[64],"we":[65,88,116],"consider":[66],"approach":[69],"which":[71],"DINO":[72],"ViT":[73],"features":[74,95],"are":[75,145,154],"reconstructed":[76],"via":[77],"a":[78,90,122],"set":[79],"queried":[81],"representations":[82],"called":[83],"slots.":[84,163],"Based":[85],"on":[86,93,108,169],"that,":[87],"propose":[89],"masking":[91],"scheme":[92],"input":[94],"selectively":[97],"disregards":[98],"the":[99,112,118,126,161,170,175],"background":[100],"regions,":[101],"inducing":[102],"our":[103],"model":[104,127],"focus":[106],"more":[107,135],"salient":[109],"objects":[110],"during":[111],"reconstruction":[113],"phase.":[114],"Moreover,":[115],"extend":[117],"slot":[119],"attention":[120],"multi-query":[123],"approach,":[124],"allowing":[125],"learn":[129],"multiple":[130,141],"sets":[131,142,153],"slots,":[133],"producing":[134],"stable":[136],"masks.":[137],"During":[138],"training,":[139],"these":[140,152],"slots":[144],"learned":[146],"independently":[147],"while,":[148],"at":[149],"test":[150],"time,":[151],"merged":[155],"through":[156],"Hungarian":[157],"matching":[158],"obtain":[160],"final":[162],"Our":[164,189],"experimental":[165],"results":[166],"ablations":[168],"PASCAL-VOC":[171],"2012":[172],"dataset":[173],"show":[174],"importance":[176],"each":[178],"component":[179],"highlight":[181],"how":[182],"combination":[184],"consistently":[185],"improves":[186],"localization.":[188],"source":[190],"code":[191],"available":[193],"at:":[194],"github.com/rishavpramanik/maskedmultiqueryslot":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}