{"id":"https://openalex.org/W4401413773","doi":"https://doi.org/10.1109/icra57147.2024.10610943","title":"Mean Shift Mask Transformer for Unseen Object Instance Segmentation","display_name":"Mean Shift Mask Transformer for Unseen Object Instance Segmentation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401413773","doi":"https://doi.org/10.1109/icra57147.2024.10610943"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5081919750","display_name":"Yangxiao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yangxiao Lu","raw_affiliation_strings":["The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102553338","display_name":"Yuqiao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqiao Chen","raw_affiliation_strings":["The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017484756","display_name":"Nicholas Ruozzi","orcid":"https://orcid.org/0000-0002-4262-2698"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Ruozzi","raw_affiliation_strings":["The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100321682","display_name":"Xiang Yu","orcid":"https://orcid.org/0000-0002-5269-3975"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Xiang","raw_affiliation_strings":["The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081919750"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":5.182,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95584291,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2760","last_page":"2766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12549","display_name":"Image and Object Detection Techniques","score":0.982699990272522,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.97079998254776,"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":0.6240147352218628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5911189913749695},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.563762903213501},{"id":"https://openalex.org/keywords/mean-shift","display_name":"Mean-shift","score":0.5469832420349121},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.537456750869751},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5286282300949097},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4426746070384979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3926568031311035},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1496952772140503},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09204620122909546},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07398867607116699}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6240147352218628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5911189913749695},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.563762903213501},{"id":"https://openalex.org/C48548287","wikidata":"https://www.wikidata.org/wiki/Q6803557","display_name":"Mean-shift","level":3,"score":0.5469832420349121},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.537456750869751},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5286282300949097},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4426746070384979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3926568031311035},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1496952772140503},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09204620122909546},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07398867607116699}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W1972630525","https://openalex.org/W1991081220","https://openalex.org/W2068127265","https://openalex.org/W2076756823","https://openalex.org/W2412782625","https://openalex.org/W2749895778","https://openalex.org/W2908510526","https://openalex.org/W2953133772","https://openalex.org/W2962914239","https://openalex.org/W2963150697","https://openalex.org/W2963362118","https://openalex.org/W2966885779","https://openalex.org/W2967153639","https://openalex.org/W2986303149","https://openalex.org/W2999219213","https://openalex.org/W3034355852","https://openalex.org/W3106546328","https://openalex.org/W3107331169","https://openalex.org/W3137905681","https://openalex.org/W3194403109","https://openalex.org/W3200139538","https://openalex.org/W3203974803","https://openalex.org/W3207187156","https://openalex.org/W3213165621","https://openalex.org/W4206755693","https://openalex.org/W4246202668","https://openalex.org/W4312263794","https://openalex.org/W4312815172","https://openalex.org/W4312891162","https://openalex.org/W4383108475","https://openalex.org/W4385245566","https://openalex.org/W4394663867","https://openalex.org/W6620707391","https://openalex.org/W6716109767","https://openalex.org/W6757817989","https://openalex.org/W6766284323","https://openalex.org/W6778485988","https://openalex.org/W6781542114","https://openalex.org/W6783692663","https://openalex.org/W6798280791","https://openalex.org/W6798837711","https://openalex.org/W6864335059"],"related_works":["https://openalex.org/W2023748438","https://openalex.org/W2124385053","https://openalex.org/W2169903804","https://openalex.org/W2352790313","https://openalex.org/W2355406465","https://openalex.org/W2545971808","https://openalex.org/W2376628591","https://openalex.org/W2142709933","https://openalex.org/W1522196789","https://openalex.org/W1994653991"],"abstract_inverted_index":{"Segmenting":[0],"unseen":[1,28,131,148],"objects":[2],"from":[3],"images":[4],"is":[5,33,49,108],"a":[6,11,22,34,76,109,118],"critical":[7],"perception":[8],"skill":[9],"that":[10,80,138],"robot":[12,17,23],"needs":[13],"to":[14,24,55,130,144],"acquire.":[15],"In":[16,65],"manipulation,":[18],"it":[19,53,57],"can":[20],"facilitate":[21],"grasp":[25],"and":[26,95,102],"manipulate":[27],"objects.":[29],"Mean":[30,71],"shift":[31,46,87],"clustering":[32,47,88],"widely":[35],"used":[36],"method":[37],"for":[38,91,147],"image":[39],"segmentation":[40,151],"tasks.":[41],"However,":[42],"the":[43,70,82,92,99,103,122],"traditional":[44],"mean":[45,86],"algorithm":[48],"not":[50],"differentiable,":[51],"making":[52],"difficult":[54],"integrate":[56],"into":[58],"an":[59],"end-to-end":[60],"neural":[61],"network":[62],"training":[63,94],"framework.":[64],"this":[66],"work,":[67],"we":[68,127],"propose":[69],"Shift":[72],"Mask":[73],"Transformer":[74],"(MSMFormer),":[75],"new":[77],"transformer":[78],"architecture":[79],"simulates":[81],"von":[83],"Mises-Fisher":[84],"(vMF)":[85],"algorithm,":[89],"allowing":[90],"joint":[93],"inference":[96],"of":[97,124],"both":[98],"feature":[100],"extractor":[101],"clustering.":[104],"Its":[105],"central":[106],"component":[107],"hypersphere":[110],"attention":[111],"mechanism,":[112],"which":[113],"updates":[114],"object":[115,132,149],"queries":[116],"on":[117],"hypersphere.":[119],"To":[120],"illustrate":[121],"effectiveness":[123],"our":[125],"method,":[126],"apply":[128],"MSMFormer":[129,139],"instance":[133,150],"segmentation.":[134],"Our":[135],"experiments":[136],"show":[137],"achieves":[140],"competitive":[141],"performance":[142],"compared":[143],"state-of-the-art":[145],"methods":[146],"<sup":[152],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}