{"id":"https://openalex.org/W4405786719","doi":"https://doi.org/10.1109/iros58592.2024.10802332","title":"Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search","display_name":"Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786719","doi":"https://doi.org/10.1109/iros58592.2024.10802332"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5104431186","display_name":"Kirill Paramonov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kirill Paramonov","raw_affiliation_strings":["Samsung R&#x0026;D Institute UK (SRUK),Communications House,Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&#x0026;D Institute UK (SRUK),Communications House,Surrey,United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015772076","display_name":"Jia-Xing Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jia-Xing Zhong","raw_affiliation_strings":["Samsung R&#x0026;D Institute UK (SRUK),Communications House,Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&#x0026;D Institute UK (SRUK),Communications House,Surrey,United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075734012","display_name":"Umberto Michieli","orcid":"https://orcid.org/0000-0003-2666-4342"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Umberto Michieli","raw_affiliation_strings":["Samsung R&#x0026;D Institute UK (SRUK),Communications House,Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&#x0026;D Institute UK (SRUK),Communications House,Surrey,United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072414837","display_name":"Jijoong Moon","orcid":"https://orcid.org/0000-0003-0888-2143"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jijoong Moon","raw_affiliation_strings":["Samsung Research Korea,Seoul,Rep. of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research Korea,Seoul,Rep. of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054882290","display_name":"Mete \u00d6zay","orcid":"https://orcid.org/0000-0002-7189-7260"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mete Ozay","raw_affiliation_strings":["Samsung R&#x0026;D Institute UK (SRUK),Communications House,Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&#x0026;D Institute UK (SRUK),Communications House,Surrey,United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104431186"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.7895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74955781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2564","last_page":"2571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9814000129699707,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9814000129699707,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9690999984741211,"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":0.9588000178337097,"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/computer-science","display_name":"Computer science","score":0.7019706964492798},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6065937876701355},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5220353603363037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43405455350875854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3710411489009857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019706964492798},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6065937876701355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5220353603363037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43405455350875854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3710411489009857}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2079582948","https://openalex.org/W2091695913","https://openalex.org/W2737258237","https://openalex.org/W2757539224","https://openalex.org/W2895752198","https://openalex.org/W2963078159","https://openalex.org/W2981787211","https://openalex.org/W2990230185","https://openalex.org/W3011986058","https://openalex.org/W3065974826","https://openalex.org/W3089740767","https://openalex.org/W3159481202","https://openalex.org/W3166525903","https://openalex.org/W3176065502","https://openalex.org/W3204171527","https://openalex.org/W3215041655","https://openalex.org/W4205254582","https://openalex.org/W4294310790","https://openalex.org/W4312815172","https://openalex.org/W4313150877","https://openalex.org/W4383108776","https://openalex.org/W4386065512","https://openalex.org/W4389665851","https://openalex.org/W4390874575","https://openalex.org/W6668990524","https://openalex.org/W6737377802","https://openalex.org/W6754568377","https://openalex.org/W6788135285","https://openalex.org/W6810625097","https://openalex.org/W6851769527","https://openalex.org/W6851800889","https://openalex.org/W6852612167","https://openalex.org/W6852694211","https://openalex.org/W6869946643","https://openalex.org/W6880937956"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,27,97,153],"this":[1,154],"paper,":[2],"we":[3,29,156],"address":[4,32],"a":[5,63,108,160],"recent":[6,173],"trend":[7],"in":[8,122,209],"robotic":[9,55,72],"home":[10,73],"appliances":[11,23,74],"to":[12,80,86,113,116,180,207,215,229,235,238],"include":[13],"vision":[14,110],"systems":[15],"on":[16,24,51,171],"personal":[17,38,47,82,90,99,167],"devices,":[18],"capable":[19],"of":[20,37,46,49,125,141,224],"personalizing":[21],"the":[22,25,123,130,135,139,172,216,239],"fly.":[26],"particular,":[28],"formulate":[30],"and":[31,44,75,127,148,195,211,220,231],"an":[33],"important":[34],"technical":[35,105],"task":[36,68],"object":[39,100,168],"search,":[40],"which":[41,78,177],"involves":[42],"localization":[43],"identification":[45],"items":[48],"interest":[50],"images":[52],"captured":[53],"by":[54,62],"appliances,":[56],"with":[57,88],"each":[58],"item":[59],"referenced":[60],"only":[61],"few":[64],"annotated":[65],"images.":[66],"The":[67],"is":[69],"crucial":[70],"for":[71,93,134,145,165],"mobile":[76],"systems,":[77],"need":[79],"process":[81],"visual":[83],"scenes":[84],"or":[85,95],"operate":[87],"particular":[89],"objects":[91],"(e.g.,":[92],"grasping":[94],"navigation).":[96],"practice,":[98],"search":[101,169],"presents":[102],"two":[103],"main":[104],"challenges.":[106],"First,":[107],"robot":[109],"system":[111,137],"needs":[112],"be":[114],"able":[115],"distinguish":[117],"between":[118],"many":[119],"fine-grained":[120],"classes,":[121],"presence":[124],"occlusions":[126],"clutter.":[128],"Second,":[129],"strict":[131],"resource":[132],"requirements":[133,194],"on-device":[136,151,190],"restrict":[138],"usage":[140],"most":[142],"state-of-the-art":[143],"methods":[144],"few-shot":[146],"learning":[147],"often":[149],"prevent":[150],"adaptation.":[152],"work,":[155],"propose":[157],"Swiss":[158,186],"DINO:":[159],"simple":[161],"yet":[162],"effective":[163],"framework":[164],"one-shot":[166],"based":[170],"DINOv2":[174],"transformer":[175],"model,":[176],"was":[178],"shown":[179],"have":[181],"strong":[182],"zero-shot":[183],"generalization":[184],"properties.":[185],"DINO":[187],"handles":[188],"challenging":[189],"personalized":[191],"scene":[192],"understanding":[193],"does":[196],"not":[197],"require":[198],"any":[199],"adaptation":[200],"training.":[201],"We":[202],"show":[203],"significant":[204,221],"improvement":[205],"(up":[206,228,234],"55%)":[208],"segmentation":[210],"recognition":[212],"accuracy":[213],"compared":[214,237],"common":[217],"lightweight":[218],"solutions,":[219],"footprint":[222],"reduction":[223],"backbone":[225],"inference":[226],"time":[227],"100\u00d7)":[230],"GPU":[232],"consumption":[233],"10\u00d7)":[236],"heavy":[240],"transformer-based":[241],"solutions<sup":[242],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[243],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}