{"id":"https://openalex.org/W7117309083","doi":"https://doi.org/10.1109/tpami.2025.3648863","title":"SAM-I2V++: Efficiently Upgrading SAM for Promptable Video Segmentation","display_name":"SAM-I2V++: Efficiently Upgrading SAM for Promptable Video Segmentation","publication_year":2025,"publication_date":"2025-12-26","ids":{"openalex":"https://openalex.org/W7117309083","doi":"https://doi.org/10.1109/tpami.2025.3648863","pmid":"https://pubmed.ncbi.nlm.nih.gov/41452691"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3648863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3648863","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Haiyang Mei","orcid":"https://orcid.org/0000-0003-3549-9684"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haiyang Mei","raw_affiliation_strings":["Show Lab, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3549-9684","affiliations":[{"raw_affiliation_string":"Show Lab, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121311890","display_name":"Pengyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Pengyu Zhang","raw_affiliation_strings":["Show Lab, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Show Lab, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["Show Lab, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7681-2166","affiliations":[{"raw_affiliation_string":"Show Lab, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5259343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"4","first_page":"4878","last_page":"4895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8213000297546387,"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":0.8213000297546387,"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":0.06679999828338623,"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/T11019","display_name":"Image Enhancement Techniques","score":0.019600000232458115,"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":0.6323000192642212},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6258999705314636},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5389999747276306},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45350000262260437},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43220001459121704},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4115999937057495},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.382099986076355},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3537999987602234},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3314000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8621000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.637499988079071},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6258999705314636},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5389999747276306},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4943000078201294},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3537999987602234},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3125},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2646999955177307},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3648863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3648863","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41452691","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41452691","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2799157347","https://openalex.org/W2889986507","https://openalex.org/W2962825871","https://openalex.org/W2963253279","https://openalex.org/W2964343881","https://openalex.org/W2998449272","https://openalex.org/W3034798428","https://openalex.org/W3040304705","https://openalex.org/W3094664776","https://openalex.org/W3107304365","https://openalex.org/W3183673520","https://openalex.org/W4306827030","https://openalex.org/W4312396403","https://openalex.org/W4312480274","https://openalex.org/W4312558481","https://openalex.org/W4383501623","https://openalex.org/W4385481295","https://openalex.org/W4386072015","https://openalex.org/W4388683499","https://openalex.org/W4390873027","https://openalex.org/W4390874025","https://openalex.org/W4390874144","https://openalex.org/W4390874575","https://openalex.org/W4390874578","https://openalex.org/W4390874670","https://openalex.org/W4391021462","https://openalex.org/W4391109864","https://openalex.org/W4391223676","https://openalex.org/W4394597311","https://openalex.org/W4402501200","https://openalex.org/W4402727760","https://openalex.org/W4402753923","https://openalex.org/W4404199191","https://openalex.org/W4404238289","https://openalex.org/W4404914866","https://openalex.org/W4408634392","https://openalex.org/W4409261941","https://openalex.org/W4409363472","https://openalex.org/W4413146370","https://openalex.org/W4413147546","https://openalex.org/W4413156388","https://openalex.org/W4415797997","https://openalex.org/W7123354414","https://openalex.org/W7133219196"],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"models":[1],"like":[2],"the":[3,95,140,158,222],"Segment":[4],"Anything":[5],"Model":[6],"(SAM)":[7],"have":[8],"significantly":[9,101],"advanced":[10],"promptable":[11,86],"image":[12,50,126],"segmentation":[13,88],"in":[14,27,35,62,175,211,221],"computer":[15],"vision.":[16],"However,":[17],"extending":[18],"these":[19],"capabilities":[20],"to":[21,41,56,98,128,152,169,204],"videos":[22],"presents":[23,200],"substantial":[24],"challenges,":[25],"particularly":[26],"ensuring":[28],"precise":[29],"and":[30,51,69,105,148,161,215,219],"temporally":[31,171],"consistent":[32,172],"mask":[33,173],"propagation":[34,174],"dynamic":[36,176],"scenes.":[37,177],"SAM":[38,97,187],"2":[39],"attempts":[40],"address":[42],"this":[43,73],"by":[44],"training":[45,64,103,196],"a":[46,78,85,134,163,201],"model":[47,213],"on":[48],"massive":[49],"video":[52,87,131],"data":[53],"from":[54],"scratch":[55],"learn":[57],"complex":[58],"spatiotemporal":[59,130],"associations,":[60],"resulting":[61],"huge":[63],"costs":[65],"that":[66,138,181],"hinder":[67],"research":[68,210],"practical":[70],"deployment.":[71],"In":[72],"paper,":[74],"we":[75,111],"introduce":[76,112],"SAM-I2V++,":[77],"training-efficient":[79],"image-to-video":[80,118],"upgradation":[81],"method":[82,183],"for":[83,208],"cultivating":[84],"(PVS)":[89],"model.":[90],"Our":[91,198],"approach":[92],"strategically":[93],"upgrades":[94],"pre-trained":[96],"support":[99],"PVS,":[100,205],"reducing":[102],"complexity":[104],"resource":[106],"requirements.":[107],"To":[108],"achieve":[109],"this,":[110],"three":[113],"key":[114],"innovations:":[115],"(i)":[116],"an":[117],"feature":[119],"extraction":[120],"upgrader":[121],"built":[122],"upon":[123],"SAM's":[124],"static":[125],"encoder":[127],"enable":[129],"perception,":[132],"(ii)":[133],"memory":[135,155,168],"selective":[136],"associator":[137],"retrieves":[139],"most":[141],"relevant":[142],"past":[143],"frames":[144],"via":[145],"similarity-driven":[146],"selection":[147],"uses":[149],"multiscale-enhanced":[150],"cross-attention":[151],"associate":[153],"selected":[154],"features":[156],"with":[157],"current":[159],"frame,":[160],"(iii)":[162],"memory-as-prompt":[164],"mechanism":[165],"leveraging":[166],"object":[167],"ensure":[170],"Comprehensive":[178],"experiments":[179],"demonstrate":[180],"our":[182],"achieves":[184],"93%":[185],"of":[186,194],"2's":[188],"performance":[189],"while":[190],"using":[191],"only":[192],"0.2%":[193],"its":[195],"cost.":[197],"work":[199],"resource-efficient":[202],"pathway":[203],"lowering":[206],"barriers":[207],"further":[209],"PVS":[212],"design":[214],"enabling":[216],"broader":[217],"applications":[218],"advancements":[220],"field.":[223]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-12-26T00:00:00"}