{"id":"https://openalex.org/W7135072967","doi":"https://doi.org/10.1109/tpami.2026.3673141","title":"SELongVLM: Empowering Long Video Language Models With Self-Corrective Clip Selection","display_name":"SELongVLM: Empowering Long Video Language Models With Self-Corrective Clip Selection","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135072967","doi":"https://doi.org/10.1109/tpami.2026.3673141","pmid":"https://pubmed.ncbi.nlm.nih.gov/41817966"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3673141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3673141","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":"https://openalex.org/A5030660306","display_name":"Kecheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kecheng Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020316185","display_name":"Zongxin Yang","orcid":"https://orcid.org/0000-0001-8783-8313"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongxin Yang","raw_affiliation_strings":["DBMI, HMS, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8783-8313","affiliations":[{"raw_affiliation_string":"DBMI, HMS, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103127046","display_name":"Mingfei Han","orcid":"https://orcid.org/0000-0003-0040-6177"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingfei Han","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0040-6177","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128818504","display_name":"Yunzhi Zhuge","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhi Zhuge","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-4288-4516","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128716290","display_name":"Haihong Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haihong Hao","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0009-0384-4392","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128843224","display_name":"Changlin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changlin Li","raw_affiliation_strings":["School of Medicine, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8486-7482","affiliations":[{"raw_affiliation_string":"School of Medicine, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072617830","display_name":"Zhisheng Li","orcid":"https://orcid.org/0000-0001-7811-8285"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihui Li","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-9642-8009","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"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":0.24506246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"8694","last_page":"8709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5245000123977661,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5245000123977661,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11500000208616257,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0989999994635582,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/selection","display_name":"Selection (genetic algorithm)","score":0.7192999720573425},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39089998602867126},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.34880000352859497},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.32269999384880066},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.31290000677108765},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.30320000648498535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760999798774719},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7192999720573425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6169999837875366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46459999680519104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3361000120639801},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2547999918460846}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3673141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3673141","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:41817966","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41817966","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":[{"id":"https://openalex.org/G1070641079","display_name":null,"funder_award_id":"U25A20530","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2746168205","display_name":null,"funder_award_id":"62573399","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,44,96],"multimodal":[3],"large":[4],"language":[5,122],"models":[6,224],"(MLLMs)":[7],"have":[8],"enabled":[9],"impressive":[10],"progress":[11],"visual-language":[13],"reasoning,":[14],"yet":[15],"long-video":[16,230],"understanding":[17],"remains":[18],"a":[19,116,129,152,172,200],"formidable":[20],"challenge":[21],"due":[22],"to":[23,49,103,166],"the":[24,37,92,189],"need":[25],"for":[26,41,196,203,242,254,259,267],"coherent":[27],"reasoning":[28,185,262],"over":[29],"ultra-long":[30],"spatiotemporal":[31,94,184,208],"dependencies.":[32],"Existing":[33],"methods":[34],"struggle":[35],"with":[36],"vast":[38],"candidate":[39],"space":[40],"relevant":[42],"information":[43],"long":[45,120,211],"videos,":[46],"often":[47],"failing":[48],"distinguish":[50],"meaningful":[51],"events":[52],"from":[53],"redundant":[54],"content.":[55],"We":[56],"identify":[57],"two":[58,126],"critical":[59],"and":[60,77,151,182,199,228,238,245,263],"previously":[61],"under-explored":[62],"issues:":[63],"absolute":[64,145],"redundancy,":[65,79,169],"where":[66,80],"static":[67],"visual":[68],"content":[69],"inflates":[70],"token":[71],"counts":[72],"without":[73,163],"adding":[74],"narrative":[75],"value,":[76],"relative":[78,168],"task-irrelevant":[81],"segments":[82],"introduce":[83,114],"noise":[84],"that":[85,134,157,219],"impairs":[86],"reasoning.":[87],"Compounding":[88],"these":[89,110],"issues":[90],"is":[91],"weak":[93],"modeling":[95,142],"current":[97],"MLLMs,":[98],"which":[99],"limits":[100],"their":[101],"ability":[102],"capture":[104],"complex":[105],"event":[106],"dynamics.":[107],"To":[108,178],"address":[109],"multifaceted":[111],"challenges,":[112],"we":[113],"SELongVLM,":[115],"dynamically":[117],"lenient-to-stringent":[118],"selection":[119,162],"video":[121],"model.":[123],"SELongVLM":[124,220],"integrates":[125],"coordinated":[127],"branches:":[128],"Residual":[130],"Token":[131],"Pruner":[132],"(RTP)":[133],"removes":[135],"repetitive":[136],"background":[137],"tokens":[138],"via":[139],"inter-frame":[140],"residual":[141],"thus":[143],"mitigating":[144],"redundancy":[146],"while":[147],"preserving":[148],"motion":[149],"cues,":[150],"Semantic-aware":[153],"Self-Correction":[154],"Selector":[155],"(SCSelector)":[156],"progressively":[158],"refines":[159],"query-relevant":[160],"clip":[161],"frame-level":[164],"annotations":[165],"reduce":[167],"guided":[170],"by":[171],"stringent-to-lenient":[173],"self-correcting":[174],"mechanism":[175],"during":[176],"optimization.":[177],"ensure":[179],"causal":[180],"continuity":[181],"bolster":[183],"across":[186,215],"disjoint":[187],"clips,":[188],"framework":[190],"further":[191],"incorporates":[192],"an":[193],"action-aware":[194],"operation":[195],"intra-clip":[197],"dynamics":[198],"temporal":[201,261],"memory":[202],"cross-clip":[204],"context,":[205],"enabling":[206],"robust":[207],"inference":[209],"on":[210,225,236,240,249,257,265],"videos.":[212],"Extensive":[213],"experiments":[214],"eight":[216],"benchmarks":[217,252],"demonstrate":[218],"markedly":[221],"outperforms":[222],"existing":[223],"both":[226],"general":[227,243],"specialized":[229,251],"tasks.":[231],"Specifically,":[232],"it":[233],"achieves":[234],"65.5%":[235],"VideoMME":[237],"69.8%":[239],"MLVU":[241],"benchmarks,":[244],"delivers":[246],"strong":[247],"performance":[248],"four":[250],"-":[253],"example,":[255],"39.2%":[256],"TOMATO":[258],"fine-grained":[260],"69.2%":[264],"EventBench":[266],"event-level":[268],"understanding.":[269]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-03-13T00:00:00"}