{"id":"https://openalex.org/W4404089453","doi":"https://doi.org/10.1109/iccv51701.2025.01264","title":"SAM2LONG: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","display_name":"SAM2LONG: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404089453","doi":"https://doi.org/10.1109/iccv51701.2025.01264"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.16268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013238521","display_name":"Shuangrui Ding","orcid":"https://orcid.org/0000-0001-7033-774X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Shuangrui Ding","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003750064","display_name":"Rui Qian","orcid":"https://orcid.org/0000-0002-0378-6438"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rui Qian","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055238399","display_name":"Xiaoyi Dong","orcid":"https://orcid.org/0000-0002-4654-835X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaoyi Dong","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027620525","display_name":"Pan Zhang","orcid":"https://orcid.org/0000-0002-8415-567X"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005200501","display_name":"Yuhang Zang","orcid":"https://orcid.org/0000-0003-1110-5062"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Zang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010183483","display_name":"Yuhang Cao","orcid":"https://orcid.org/0009-0008-3627-590X"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Cao","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025572029","display_name":"Yuwei Guo","orcid":"https://orcid.org/0009-0007-0582-6206"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuwei Guo","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365340","display_name":"Jiaqi Wang","orcid":"https://orcid.org/0000-0001-6877-5353"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5013238521"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.0652,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73233709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"13614","last_page":"13624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.991599977016449,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.991599977016449,"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":0.9878000020980835,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9735000133514404,"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/training","display_name":"Training (meteorology)","score":0.7030138969421387},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6919071078300476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6286122798919678},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.617195188999176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3672252893447876},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3372589647769928},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1459912359714508},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11174246668815613},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.053066372871398926}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7030138969421387},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6919071078300476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6286122798919678},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.617195188999176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3672252893447876},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3372589647769928},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1459912359714508},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11174246668815613},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.053066372871398926},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.16268","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.16268","pdf_url":"https://arxiv.org/pdf/2410.16268","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.16268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.16268","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.16268","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.16268","pdf_url":"https://arxiv.org/pdf/2410.16268","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1428996349","display_name":null,"funder_award_id":"2022ZD0161600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8094218613","display_name":null,"funder_award_id":"T41-603/20-R","funder_id":"https://openalex.org/F4320321920","funder_display_name":"Innovation and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4806748151","display_name":"Centre for Perceptual and Interactive Intelligence","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404089453.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"The":[0,30,257],"Segment":[1],"Anything":[2],"Model":[3],"2":[4,35,87],"(SAM":[5],"2)":[6],"has":[7],"emerged":[8],"as":[9,171,193,253],"a":[10,124,133],"powerful":[11],"foundation":[12],"model":[13],"for":[14,25,36,50,175,219],"object":[15,102,210,249],"segmentation":[16,38,76,103,108,121,137,196,250],"in":[17,123,244],"both":[18],"images":[19],"and":[20,73,113,209,212,216,255],"videos,":[21],"paving":[22],"the":[23,61,75,78,83,107,115,140,151,161,172,176,181,184,187,194],"way":[24],"various":[26,155],"downstream":[27],"video":[28,37,101,248],"applications.":[29],"crucial":[31],"design":[32,58],"of":[33,77,85,136,165,229,239],"SAM":[34,86],"is":[39,191,205,259],"its":[40,55,200],"memory":[41,57],"module,":[42],"which":[43,81,105],"prompts":[44],"object-aware":[45],"memories":[46],"from":[47,60,119,199],"previous":[48],"frames":[49],"current":[51],"frame":[52,112],"prediction.":[53],"However,":[54],"greedy-selection":[56],"suffers":[59],"\"error":[62],"accumulation\"":[63],"problem,":[64],"where":[65],"an":[66,98,226],"errored":[67],"or":[68],"missed":[69],"mask":[70],"will":[71],"cascade":[72],"influence":[74],"subsequent":[79],"frames,":[80],"limits":[82],"performance":[84],"toward":[88,207],"complex":[89,220],"long-term":[90,221,247],"videos.":[91,222],"To":[92],"this":[93],"end,":[94],"we":[95,131],"introduce":[96],"SAM2Long,":[97],"improved":[99],"training-free":[100],"strategy,":[104],"considers":[106],"uncertainty":[109],"within":[110],"each":[111,143],"chooses":[114],"video-level":[116],"optimal":[117],"results":[118],"multiple":[120,145],"pathways":[122,138,174],"constrained":[125],"tree":[126],"search":[127,202],"manner.":[128],"In":[129],"practice,":[130],"maintain":[132],"fixed":[134,163],"number":[135,164],"throughout":[139],"video.":[141],"For":[142],"frame,":[144,183],"masks":[146],"are":[147],"proposed":[148],"based":[149],"on":[150,246],"existing":[152],"pathways,":[153],"creating":[154],"candidate":[156],"branches.":[157],"We":[158],"then":[159],"select":[160],"same":[162],"branches":[166],"with":[167,186,237],"higher":[168],"cumulative":[169,189],"scores":[170],"new":[173],"next":[177],"frame.":[178],"After":[179],"processing":[180],"final":[182,195],"pathway":[185],"highest":[188],"score":[190],"chosen":[192],"result.":[197],"Benefiting":[198],"heuristic":[201],"design,":[203],"SAM2Long":[204,224],"robust":[206],"occlusions":[208],"reappearances,":[211],"can":[213],"effectively":[214],"segment":[215],"track":[217],"objects":[218],"Notably,":[223],"achieves":[225],"average":[227],"improvement":[228],"3.0":[230],"points":[231,243],"across":[232],"all":[233],"24":[234],"head-to-head":[235],"comparisons,":[236],"gains":[238],"up":[240],"to":[241],"5.3":[242],"J&F":[245],"benchmarks":[251],"such":[252],"SA-V":[254],"LVOS.":[256],"code":[258],"released":[260],"at":[261],"https://github.com/Mark12Ding/SAM2Long.":[262]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}