{"id":"https://openalex.org/W7118090487","doi":"https://doi.org/10.1145/3786794","title":"EvSAM: Segment Anything Model with Event-based Assistance","display_name":"EvSAM: Segment Anything Model with Event-based Assistance","publication_year":2026,"publication_date":"2026-01-03","ids":{"openalex":"https://openalex.org/W7118090487","doi":"https://doi.org/10.1145/3786794"},"language":"en","primary_location":{"id":"doi:10.1145/3786794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3786794","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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":null,"display_name":"Yi Ding","orcid":"https://orcid.org/0009-0009-7221-6453"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ding","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7221-6453","affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bowen Yao","orcid":"https://orcid.org/0009-0004-4819-9976"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Yao","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-4819-9976","affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhan Liu","orcid":"https://orcid.org/0009-0000-4748-1639"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Liu","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4748-1639","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-3138-505X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3138-505X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054045864","display_name":"Ding Ding","orcid":"https://orcid.org/0000-0001-6597-3725"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Ding","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6597-3725","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121863768","display_name":"Zhen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yang","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6058-0217","affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121865866","display_name":"Youfu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Youfu Li","raw_affiliation_strings":["Department of Mechanical Engineering, City University of Hong Kong, Hong Kong, SAR"],"raw_orcid":"https://orcid.org/0000-0002-5227-1326","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, City University of Hong Kong, Hong Kong, SAR","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048895548","display_name":"Yongjian Deng","orcid":"https://orcid.org/0000-0001-6253-3564"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Deng","raw_affiliation_strings":["Computer Science, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6253-3564","affiliations":[{"raw_affiliation_string":"Computer Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.016428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10036","display_name":"Advanced Neural Network Applications","score":0.0006000000284984708,"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/semantics","display_name":"Semantics (computer science)","score":0.6389999985694885},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6150000095367432},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6086000204086304},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.47760000824928284},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4320000112056732},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.35519999265670776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8977000117301941},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6389999985694885},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6086000204086304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45179998874664307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C123606473","wikidata":"https://www.wikidata.org/wiki/Q907918","display_name":"Complex event processing","level":3,"score":0.33500000834465027},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3786794","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3464956225","display_name":null,"funder_award_id":"62203024, 62573369, 62261160576","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2412782625","https://openalex.org/W2904275768","https://openalex.org/W2969022059","https://openalex.org/W2998281665","https://openalex.org/W4200630704","https://openalex.org/W4214520160","https://openalex.org/W4221147914","https://openalex.org/W4224274660","https://openalex.org/W4312852806","https://openalex.org/W4313156423","https://openalex.org/W4323065857","https://openalex.org/W4386065698","https://openalex.org/W4390874575","https://openalex.org/W4392901701"],"related_works":[],"abstract_inverted_index":{"The":[0,55,183],"general-purpose":[1],"Segment":[2],"Anything":[3],"Model":[4],"(SAM)":[5],"is":[6],"limited":[7],"by":[8,59],"the":[9,76,98,106,122,141,150,158,167,193,201,211,252],"inherent":[10],"constraints":[11],"of":[12,38,78,102,109,124,204,213,254],"RGB":[13,214],"sensors,":[14],"which":[15,257],"render":[16],"it":[17,172],"inadequate":[18],"for":[19,155,266],"challenging":[20],"real-world":[21],"scenarios":[22],"such":[23],"as":[24],"adverse":[25,118],"lighting":[26],"conditions":[27],"and":[28,50,129,149,170,264],"rapid":[29],"motion.":[30],"In":[31],"contrast,":[32],"event":[33,56,110,168,188,206],"cameras,":[34],"a":[35,51,89,174,179,186,197],"novel":[36,90],"type":[37],"bio-inspired":[39],"visual":[40,244],"sensor,":[41],"offer":[42],"distinct":[43,239],"imaging":[44],"advantages,":[45],"including":[46],"high":[47,52],"temporal":[48],"resolution":[49],"dynamic":[53,64,187],"range.":[54],"streams":[57],"generated":[58],"these":[60,223],"cameras":[61],"provide":[62],"spatiotemporal":[63,163],"cues":[65],"that":[66],"are":[67],"often":[68],"absent":[69],"in":[70,241],"conventional":[71],"image":[72],"frames.":[73],"To":[74,120],"overcome":[75],"limitations":[77],"RGB-based":[79],"models,":[80],"we":[81,136,247],"propose":[82],"SAM":[83,103],"with":[84,131,217],"Event-based":[85,151],"Assistance":[86],"(EvSAM)":[87],",":[88],"RGB-event":[91],"multi-modal":[92],"semantic":[93,164,232],"segmentation":[94,233],"framework.":[95],"EvSAM":[96,226],"leverages":[97],"strong":[99,261],"generalization":[100,262],"capabilities":[101],"while":[104],"incorporating":[105],"complementary":[107,176],"characteristics":[108],"data":[111,133],"to":[112,222,251],"enhance":[113],"scene":[114],"comprehension,":[115],"particularly":[116],"under":[117],"conditions.":[119],"address":[121],"challenges":[123],"fusing":[125],"two":[126,138],"modals":[127],"(image":[128],"event)":[130],"large":[132],"format":[134],"discrepancy,":[135],"introduce":[137],"core":[139,224],"components:":[140],"Multi-spatiotemporal-scale":[142],"Patch":[143],"Alignment":[144],"Block":[145],"(MS":[146],"2":[147],"PAB)":[148],"Feature":[152],"Injector":[153],"(EFInj)":[154],"SAM.":[156],"Specifically,":[157],"MS":[159],"\\({}^{2}\\)":[160],"PAB":[161],"captures":[162],"coherence":[165],"from":[166],"stream":[169],"transforms":[171],"into":[173],"frame-based":[175],"representation":[177],"using":[178],"multi-spatiotemporal":[180],"alignment":[181],"strategy.":[182],"EFInj":[184],"introduces":[185],"feature":[189],"update":[190],"mechanism,":[191],"wherein":[192],"fused":[194],"features":[195],"at":[196],"given":[198],"layer":[199],"guide":[200],"adaptive":[202],"generation":[203],"deeper":[205],"representations.":[207],"This":[208],"process":[209],"facilitates":[210],"integration":[212],"spatial":[215],"semantics":[216],"event-based":[218,231],"motion":[219],"cues.":[220],"Owing":[221],"designs,":[225],"demonstrates":[227,259],"superior":[228],"performance":[229],"on":[230],"datasets,":[234],"thereby":[235],"fully":[236],"validating":[237],"its":[238,260],"advantages":[240],"handling":[242],"extreme":[243],"scenarios.":[245],"Furthermore,":[246],"extend":[248],"our":[249],"model":[250],"task":[253],"depth":[255],"estimation,":[256],"further":[258],"ability":[263],"scalability":[265],"various":[267],"downstream":[268],"applications.":[269]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-03T00:00:00"}