{"id":"https://openalex.org/W4414786599","doi":"https://doi.org/10.1109/iccv51701.2025.00648","title":"O-MaMa: Learning Object Mask Matching Between Egocentric and Exocentric Views","display_name":"O-MaMa: Learning Object Mask Matching Between Egocentric and Exocentric Views","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414786599","doi":"https://doi.org/10.1109/iccv51701.2025.00648"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.06026","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001202571","display_name":"Lorenzo Mur-Labadia","orcid":null},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Lorenzo Mur-Labadia","raw_affiliation_strings":["I3A - University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A - University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093760981","display_name":"Maria Santos-Villafranca","orcid":"https://orcid.org/0009-0009-5663-3185"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Maria Santos-Villafranca","raw_affiliation_strings":["I3A - University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A - University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006618959","display_name":"Jes\u00fas Berm\u00fadez-Cameo","orcid":"https://orcid.org/0000-0002-8479-1748"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jesus Bermudez-Cameo","raw_affiliation_strings":["I3A - University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A - University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062972983","display_name":"Alejandro P\u00e9rez-Yus","orcid":"https://orcid.org/0000-0002-8949-2632"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alejandro Perez-Yus","raw_affiliation_strings":["I3A - University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A - University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049372967","display_name":"Rub\u00e9n Mart\u00ednez-Cant\u00edn","orcid":"https://orcid.org/0000-0002-6741-844X"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ruben Martinez-Cantin","raw_affiliation_strings":["I3A - University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A - University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004168","display_name":"Jos\u00e9 Guerrero","orcid":"https://orcid.org/0000-0002-4772-6568"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose J. Guerrero","raw_affiliation_strings":["I3A - University of Zaragoza"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A - University of Zaragoza","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.30011241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6892","last_page":"6903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9700999855995178,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9700999855995178,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6322000026702881},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6182000041007996},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6164000034332275},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5889000296592712},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47620001435279846},{"id":"https://openalex.org/keywords/endocentric-and-exocentric","display_name":"Endocentric and exocentric","score":0.3671000003814697},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.361299991607666},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3163999915122986}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7645999789237976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246000170707703},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6322000026702881},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5587999820709229},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C131042201","wikidata":"https://www.wikidata.org/wiki/Q493198","display_name":"Endocentric and exocentric","level":4,"score":0.3671000003814697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.06026","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06026","pdf_url":"https://arxiv.org/pdf/2506.06026","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.06026","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.06026","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.06026","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06026","pdf_url":"https://arxiv.org/pdf/2506.06026","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"the":[1,97,107,110,113,125,131,142,147],"world":[2],"from":[3,60],"multiple":[4],"perspectives":[5],"is":[6],"essential":[7],"for":[8],"intelligent":[9],"systems":[10],"operating":[11],"together,":[12],"where":[13],"segmenting":[14],"common":[15],"objects":[16],"across":[17],"different":[18],"views":[19],"remains":[20],"an":[21,65],"open":[22],"problem.":[23],"We":[24],"introduce":[25],"a":[26,37,73,83,89,136],"new":[27],"approach":[28],"that":[29,49,68,78],"re-defines":[30],"cross-image":[31],"segmentation":[32],"by":[33],"treating":[34],"it":[35],"as":[36],"mask":[38,62],"matching":[39],"task.":[40],"Our":[41],"method":[42],"consists":[43],"of:":[44],"(1)":[45],"A":[46],"Mask-Context":[47],"Encoder":[48],"pools":[50],"dense":[51],"DINOv2":[52],"semantic":[53],"features":[54,81],"to":[55,95,99],"obtain":[56],"discriminative":[57],"object-level":[58],"representations":[59],"FastSAM":[61],"candidates,":[63],"(2)":[64],"Ego$\\leftrightarrow$Exo":[66],"Cross-Attention":[67],"fuses":[69],"multi-perspective":[70],"observations,":[71],"(3)":[72],"Mask":[74],"Matching":[75],"contrastive":[76],"loss":[77],"aligns":[79],"cross-view":[80],"in":[82,112,124],"shared":[84],"latent":[85],"space,":[86],"and":[87,122,127,135,138],"(4)":[88],"Hard":[90],"Negative":[91],"Adjacent":[92],"Mining":[93],"strategy":[94],"encourage":[96],"model":[98],"better":[100],"differentiate":[101],"between":[102],"nearby":[103],"objects.":[104],"O-MaMa":[105],"achieves":[106],"state":[108],"of":[109,120,146],"art":[111],"Ego-Exo4D":[114],"Correspondences":[115],"benchmark,":[116],"obtaining":[117],"relative":[118],"gains":[119],"+22%":[121],"+76%":[123],"Ego2Exo":[126],"Exo2Ego":[128],"IoU":[129],"against":[130],"official":[132],"challenge":[133],"baselines,":[134],"+13%":[137],"+6%":[139],"compared":[140],"with":[141,144],"SOTA":[143],"1%":[145],"training":[148],"parameters.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}