{"id":"https://openalex.org/W7155629088","doi":"https://doi.org/10.1145/3787279.3788494","title":"Category-Level Segmentation of Repeated Objects using SAM2 Memory System","display_name":"Category-Level Segmentation of Repeated Objects using SAM2 Memory System","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W7155629088","doi":"https://doi.org/10.1145/3787279.3788494"},"language":null,"primary_location":{"id":"doi:10.1145/3787279.3788494","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787279.3788494","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Advances in Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3787279.3788494","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118983749","display_name":"Jiayi Wang","orcid":"https://orcid.org/0009-0009-9174-1667"},"institutions":[{"id":"https://openalex.org/I4210128710","display_name":"Robert Bosch (United Kingdom)","ror":"https://ror.org/031zzq071","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210128710","https://openalex.org/I889804353"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiayi Wang","raw_affiliation_strings":["Corporate Research, Robert Bosch GmbH, Renningen, Germany and Pattern Recognition Lab, Friedrich-Alexander-Universit, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0009-0000-2005-0986","affiliations":[{"raw_affiliation_string":"Corporate Research, Robert Bosch GmbH, Renningen, Germany and Pattern Recognition Lab, Friedrich-Alexander-Universit, Erlangen, Germany","institution_ids":["https://openalex.org/I4210128710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052445957","display_name":"Matthias Kayser","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Kayser","raw_affiliation_strings":["Corporate Research, Robert Bosch GmbH, Renningen, Germany"],"raw_orcid":"https://orcid.org/0009-0000-5228-3397","affiliations":[{"raw_affiliation_string":"Corporate Research, Robert Bosch GmbH, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110375849","display_name":"Yipeng Sun","orcid":"https://orcid.org/0009-0009-8587-8894"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yipeng Sun","raw_affiliation_strings":["Pattern Recognition Lab, Friedrich-Alexander-Universit, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0009-0009-8587-8894","affiliations":[{"raw_affiliation_string":"Pattern Recognition Lab, Friedrich-Alexander-Universit, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8203999996185303,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8203999996185303,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.027499999850988388,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.02329999953508377,"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/segmentation","display_name":"Segmentation","score":0.7096999883651733},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6450999975204468},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5389999747276306},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.49070000648498535},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4302999973297119},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.4059000015258789},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3986999988555908},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.38370001316070557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968000173568726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7124000191688538},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7096999883651733},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6450999975204468},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6258000135421753},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.49070000648498535},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4302999973297119},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4059000015258789},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.375},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.34619998931884766},{"id":"https://openalex.org/C28063669","wikidata":"https://www.wikidata.org/wiki/Q7167042","display_name":"Perceptual system","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.27300000190734863},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787279.3788494","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787279.3788494","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Advances in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3787279.3788494","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787279.3788494","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Advances in Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1917989004","https://openalex.org/W2151103935","https://openalex.org/W2613096586","https://openalex.org/W2895752198","https://openalex.org/W2963150697","https://openalex.org/W4383108776","https://openalex.org/W4390874575"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,40,64],"propose":[4],"a":[5,23,36,42],"novel":[6],"segmentation":[7,25,81],"approach":[8,116],"that":[9,46,98],"adapts":[10],"the":[11,15,71,85],"memory":[12,44],"module":[13],"of":[14,51],"Segment":[16],"Anything":[17],"Model":[18],"2":[19],"(SAM2)":[20],"[15]":[21],"for":[22],"category-sensitive":[24],"within":[26,130],"images.":[27,131],"By":[28],"combining":[29],"SAM2\u2019s":[30],"Automatic":[31],"Mask":[32],"Generator":[33],"(AMG)":[34],"with":[35,120],"cross-modal":[37],"attention":[38],"mechanism,":[39],"build":[41],"dynamic":[43],"bank":[45],"enables":[47],"robust":[48],"semantic":[49],"associations":[50],"objects":[52,126],"across":[53],"frames.":[54],"To":[55],"mitigate":[56],"challenges":[57],"such":[58],"as":[59],"over-segmentation":[60],"and":[61,74,94,106],"reflection":[62],"artifacts,":[63],"introduce":[65],"an":[66],"innovative":[67],"fine-tuning":[68],"strategy":[69,78],"between":[70],"image":[72],"encoder":[73],"mask":[75],"decoder.":[76],"This":[77],"substantially":[79],"improves":[80],"robustness":[82],"while":[83],"maintaining":[84],"model\u2019s":[86],"zero-shot":[87,105],"generalization":[88],"capability.":[89],"Comparative":[90],"experiments":[91],"on":[92],"ARMBench":[93],"real-world":[95],"datasets":[96],"demonstrate":[97],"our":[99,115],"model":[100],"performs":[101],"effectively":[102],"in":[103],"both":[104],"fine-tuned":[107],"settings,":[108],"adapting":[109],"seamlessly":[110],"to":[111,124],"diverse":[112],"environments.":[113],"Ultimately,":[114],"empowers":[117],"robotic":[118],"systems":[119],"enhanced":[121],"perceptual":[122],"capabilities":[123],"recognize":[125],"from":[127],"selected":[128],"categories":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-26T00:00:00"}