{"id":"https://openalex.org/W4414359944","doi":"https://doi.org/10.24963/ijcai.2025/204","title":"Q-MiniSAM2: A Quantization-based Benchmark for Resource-Efficient Video Segmentation","display_name":"Q-MiniSAM2: A Quantization-based Benchmark for Resource-Efficient Video Segmentation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359944","doi":"https://doi.org/10.24963/ijcai.2025/204"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/204","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/204","pdf_url":"https://www.ijcai.org/proceedings/2025/0204.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0204.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xuanxuan Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanxuan Ren","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114626714","display_name":"Xiangyu Li","orcid":"https://orcid.org/0009-0004-1410-6217"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Li","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649111","display_name":"Kun Wei","orcid":"https://orcid.org/0000-0001-7228-5322"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wei","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729478","display_name":"Xu Yang","orcid":"https://orcid.org/0000-0002-0405-6816"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035747364","display_name":"Yanhua Yang","orcid":"https://orcid.org/0000-0002-7916-3683"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Yang","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26344898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1829","last_page":"1837"},"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":0.9944000244140625,"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":0.9944000244140625,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9922999739646912,"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":0.9840999841690063,"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":0.6205000281333923},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6169999837875366},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5637000203132629},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5428000092506409},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5286999940872192},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4887000024318695},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.38449999690055847},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.36480000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213000297546387},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6205000281333923},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5541999936103821},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39239999651908875},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.38449999690055847},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.36480000615119934},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C2780502288","wikidata":"https://www.wikidata.org/wiki/Q28838156","display_name":"Expansive","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/204","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/204","pdf_url":"https://www.ijcai.org/proceedings/2025/0204.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/204","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/204","pdf_url":"https://www.ijcai.org/proceedings/2025/0204.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G105305236","display_name":null,"funder_award_id":"8091B02072404","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"},{"id":"https://openalex.org/G1372603746","display_name":null,"funder_award_id":"62171343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G300900913","display_name":null,"funder_award_id":"8091B02072404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5519567226","display_name":null,"funder_award_id":"62201436","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5540677682","display_name":null,"funder_award_id":"2023YFC3305600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G986958842","display_name":null,"funder_award_id":"62132016","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"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320328373","display_name":"National Key Laboratory Foundation of China","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359944.pdf","grobid_xml":"https://content.openalex.org/works/W4414359944.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Segment":[0],"Anything":[1],"Model":[2],"2":[3],"(SAM2)":[4],"is":[5,120,159],"a":[6,26,73,92],"new-generation,":[7],"high-precision":[8],"model":[9],"for":[10,39,77,84,186],"image":[11],"and":[12,33,59,106,127,135,188],"video":[13,104,190],"segmentation,":[14],"offering":[15],"extensive":[16],"application":[17],"prospects":[18],"across":[19,109],"numerous":[20],"computer":[21],"vision":[22],"fields.":[23],"However,":[24],"as":[25],"large-scale":[27],"model,":[28],"its":[29,184],"huge":[30],"memory":[31,57,118,134],"demands":[32],"expansive":[34],"computing":[35],"costs":[36,137],"pose":[37],"challenges":[38],"practical":[40],"deployment.":[41],"This":[42],"paper":[43],"presents":[44],"Q-MiniSAM2,":[45],"an":[46,155],"efficient":[47,187],"Quantization-based":[48],"segmentation":[49],"benchmark":[50],"tailored":[51],"to":[52,69,97,102,139,161,180],"optimize":[53],"SAM2":[54],"by":[55,165],"Minimizing":[56],"consumption":[58],"accelerating":[60],"computations.":[61],"We":[62],"begin":[63],"with":[64],"applying":[65],"Post-Training":[66],"Quantization":[67,95],"(PTQ)":[68],"SAM2,":[70],"requiring":[71],"only":[72],"relatively":[74],"small":[75],"dataset":[76],"network":[78],"calibration,":[79],"thereby":[80],"eliminating":[81],"the":[82,99,128,140,144,173],"need":[83],"retraining.":[85],"Building":[86],"upon":[87],"PTQ,":[88],"we":[89,114],"further":[90],"introduce":[91],"Hierarchy-based":[93],"Video":[94],"method":[96],"enhance":[98],"model\u2019s":[100],"capacity":[101],"capture":[103],"semantics":[105],"temporal":[107],"correlations":[108],"different":[110],"time":[111,146],"scales.":[112],"Furthermore,":[113],"observe":[115],"that":[116,172],"SAM2\u2019s":[117],"overhead":[119],"predominantly":[121],"concentrated":[122],"on":[123],"processing":[124],"historical":[125],"frames,":[126],"redundant":[129],"cross-attention":[130,164],"computations":[131],"significantly":[132],"increase":[133],"computational":[136],"due":[138],"imperceptible":[141],"change":[142],"of":[143],"short":[145],"intervals":[147],"between":[148],"these":[149],"frames.":[150],"To":[151],"tackle":[152],"this":[153],"issue,":[154],"Adaptive":[156],"Mutual-KV":[157],"mechanism":[158],"proposed":[160,174],"mitigate":[162],"excessive":[163],"leveraging":[166],"inter-frame":[167],"similarities.":[168],"Comprehensive":[169],"experiments":[170],"demonstrate":[171],"approach":[175],"achieves":[176],"superior":[177],"performance":[178],"compared":[179],"state-of-the-art":[181],"methods,":[182],"underscoring":[183],"potential":[185],"scalable":[189],"segmentation.":[191]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}