{"id":"https://openalex.org/W7128541684","doi":"https://doi.org/10.1109/lsp.2026.3663047","title":"MFT: Memory-Aware Fine-Tuning of SAM2 for Efficient Long-Sequence Video Object Segmentation","display_name":"MFT: Memory-Aware Fine-Tuning of SAM2 for Efficient Long-Sequence Video Object Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128541684","doi":"https://doi.org/10.1109/lsp.2026.3663047"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3663047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3663047","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Signal Processing Letters","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":"https://openalex.org/A5125559201","display_name":"Guoqiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148850","display_name":"National Science Library","ror":"https://ror.org/04ndjyr10","country_code":"CN","type":"archive","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210148850"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Li","raw_affiliation_strings":["National Science Library, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Science Library, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210148850"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125519260","display_name":"Hao Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Yuan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Moffett Field, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Moffett Field, CA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011123013","display_name":"Suyang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I125687163","display_name":"City College of New York","ror":"https://ror.org/00wmhkr98","country_code":"US","type":"education","lineage":["https://openalex.org/I125687163"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suyang Chen","raw_affiliation_strings":["Department of Computer Science, The City College of New York, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The City College of New York, New York, NY, USA","institution_ids":["https://openalex.org/I125687163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125543711","display_name":"Qi Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Hu","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Vancouver, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Vancouver, ON, Canada","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108047889","display_name":"Yi-Xiang Wang","orcid":"https://orcid.org/0000-0001-5697-0717"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Economics and Management School, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Economics and Management School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102536901","display_name":"Kunming Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunming Jiang","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA"],"raw_orcid":"https://orcid.org/0009-0002-3688-965X","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.13724923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"943","last_page":"947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.4936000108718872,"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":0.4936000108718872,"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":0.451200008392334,"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":0.006300000008195639,"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/robustness","display_name":"Robustness (evolution)","score":0.6172999739646912},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.604200005531311},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5942000150680542},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5676000118255615},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.453900009393692},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.4172999858856201},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.40290001034736633},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.34549999237060547},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.33820000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593999862670898},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6172999739646912},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5942000150680542},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5820000171661377},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5676000118255615},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.4172999858856201},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.33660000562667847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3116999864578247},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.30640000104904175},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.2784000039100647},{"id":"https://openalex.org/C97501218","wikidata":"https://www.wikidata.org/wiki/Q219763","display_name":"MPEG-4","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3663047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3663047","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2470139095","https://openalex.org/W2564998703","https://openalex.org/W2750515003","https://openalex.org/W2799239273","https://openalex.org/W2889986507","https://openalex.org/W2963227409","https://openalex.org/W2963732700","https://openalex.org/W2963823251","https://openalex.org/W2964343881","https://openalex.org/W2990205821","https://openalex.org/W3034538699","https://openalex.org/W3094664776","https://openalex.org/W3126721948","https://openalex.org/W3132368316","https://openalex.org/W3137799923","https://openalex.org/W4312396403","https://openalex.org/W4312443924","https://openalex.org/W4312510454","https://openalex.org/W4313156423","https://openalex.org/W4386066071","https://openalex.org/W4390873799","https://openalex.org/W4390874144","https://openalex.org/W4390874575","https://openalex.org/W4390874670","https://openalex.org/W4402753923","https://openalex.org/W4414271568","https://openalex.org/W4415593584"],"related_works":[],"abstract_inverted_index":{"Adapting":[0],"large":[1],"foundation":[2],"segmentation":[3,11],"models":[4],"such":[5],"as":[6],"SAM2":[7,116],"to":[8],"video":[9],"object":[10],"(VOS),":[12],"especially":[13],"for":[14,49,114],"long":[15],"sequences,":[16,64],"is":[17],"often":[18],"limited":[19],"by":[20],"the":[21,39,86],"high":[22],"training":[23],"cost":[24],"of":[25],"full":[26],"fine-tuning.":[27],"We":[28],"present":[29],"Memory-Aware":[30],"Fine-tuning":[31],"(MFT),":[32],"a":[33,68,81],"parameter-efficient":[34],"adaptation":[35],"strategy":[36],"that":[37,74,97],"freezes":[38],"image":[40],"encoder":[41],"and":[42,56],"selectively":[43],"updates":[44],"only":[45],"memory-related":[46],"modules":[47],"responsible":[48],"temporal":[50],"reasoning":[51],"(memory":[52],"attention,":[53],"mask":[54],"decoder,":[55],"memory":[57,78,87],"encoder).":[58],"To":[59],"improve":[60],"robustness":[61],"on":[62,102,117],"extended":[63],"we":[65],"further":[66],"introduce":[67],"lightweight":[69],"Memory":[70],"Compression":[71],"(MC)":[72],"network":[73],"periodically":[75],"condenses":[76],"short-term":[77],"embeddings":[79],"into":[80],"compact":[82],"long-term":[83],"representation,":[84],"keeping":[85],"bank":[88],"bounded":[89],"while":[90,105],"preserving":[91],"historical":[92],"context.":[93],"Extensive":[94],"experiments":[95],"demonstrate":[96],"MFT":[98],"achieves":[99],"state-of-the-art":[100],"results":[101],"long-sequence":[103],"benchmarks":[104],"maintaining":[106],"efficient":[107],"resource":[108],"utilization,":[109],"offering":[110],"an":[111],"accessible":[112],"approach":[113],"fine-tuning":[115],"resource-constrained":[118],"hardware.":[119]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-11T00:00:00"}