{"id":"https://openalex.org/W7124847638","doi":"https://doi.org/10.1109/tpami.2026.3656169","title":"Momentor++: Advancing Video Large Language Models With Fine-Grained Long Video Reasoning","display_name":"Momentor++: Advancing Video Large Language Models With Fine-Grained Long Video Reasoning","publication_year":2026,"publication_date":"2026-01-20","ids":{"openalex":"https://openalex.org/W7124847638","doi":"https://doi.org/10.1109/tpami.2026.3656169","pmid":"https://pubmed.ncbi.nlm.nih.gov/41557576"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3656169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3656169","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/A5123371907","display_name":"Juncheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2258-1291","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061203331","display_name":"Minghe Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghe Gao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-9705-5398","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080903720","display_name":"Xiangnan He","orcid":"https://orcid.org/0000-0001-7231-594X"},"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":"Xiangnan He","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8472-7992","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055450279","display_name":"S. Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7356-9711","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123389926","display_name":"Weishi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Shi Zheng","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8327-0003","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123447231","display_name":"Jun Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6142-9914","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123431807","display_name":"Meng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123389630","display_name":"Tat-Seng Chua","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":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123438504","display_name":"Yueting Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7361-3084","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.07080671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"6","first_page":"6208","last_page":"6224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9848999977111816,"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":0.9848999977111816,"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":0.00419999985024333,"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":0.0017999999690800905,"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/grasp","display_name":"GRASP","score":0.593500018119812},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5087000131607056},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40389999747276306},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3790000081062317},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.3555999994277954},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3402999937534332},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.328900009393692},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.3237999975681305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569999933242798},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.593500018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3656169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3656169","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:41557576","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41557576","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7867913246154785}],"awards":[{"id":"https://openalex.org/G4881796371","display_name":null,"funder_award_id":"62436007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6689777572","display_name":null,"funder_award_id":"226-2025-00057","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2128728535","https://openalex.org/W2131681506","https://openalex.org/W2461621749","https://openalex.org/W2765137706","https://openalex.org/W2765716052","https://openalex.org/W2897249806","https://openalex.org/W2952132648","https://openalex.org/W2963150697","https://openalex.org/W2964089981","https://openalex.org/W2964220823","https://openalex.org/W2997429269","https://openalex.org/W3034743747","https://openalex.org/W3175961224","https://openalex.org/W3208474254","https://openalex.org/W4312245888","https://openalex.org/W4312322722","https://openalex.org/W4312864639","https://openalex.org/W4312982010","https://openalex.org/W4375928968","https://openalex.org/W4386066385","https://openalex.org/W4386066401","https://openalex.org/W4389519587","https://openalex.org/W4390873341","https://openalex.org/W4402671548","https://openalex.org/W4402702917","https://openalex.org/W4402727142","https://openalex.org/W4402727272","https://openalex.org/W4402727403","https://openalex.org/W4402780269","https://openalex.org/W4403725941","https://openalex.org/W4404612908","https://openalex.org/W4404784276","https://openalex.org/W4407128871","https://openalex.org/W4409367031","https://openalex.org/W4412887841","https://openalex.org/W4413146669","https://openalex.org/W4413157571","https://openalex.org/W4415795316","https://openalex.org/W7108068597","https://openalex.org/W7128429593","https://openalex.org/W7128773051","https://openalex.org/W7160016401","https://openalex.org/W7160098734","https://openalex.org/W7160173378","https://openalex.org/W7160174195"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"exhibit":[4],"remarkable":[5],"proficiency":[6],"in":[7,128,161,170,183],"understanding":[8,68,164],"and":[9,38,104,150,165,173],"managing":[10],"text-based":[11],"tasks.Many":[12],"works":[13],"try":[14],"to":[15,19,26,41,64,83,147],"transfer":[16],"these":[17,56],"capabilities":[18,160],"the":[20,35,46,72,97,100,105],"video":[21,52,88],"domain,":[22],"which":[23,121],"are":[24,39],"referred":[25],"as":[27],"Video-LLMs.":[28],"However,":[29],"current":[30],"Video-LLMs":[31],"can":[32,122],"only":[33],"grasp":[34],"coarse-grained":[36],"semantics":[37],"unable":[40],"efficiently":[42,171],"handle":[43],"tasks":[44],"involving":[45],"comprehension":[47],"or":[48],"localization":[49],"of":[50,74,99],"specific":[51],"segments.":[53],"To":[54,70],"address":[55],"challenges,":[57],"we":[58,76,108],"propose":[59],"Momentor,":[60,75],"a":[61,86,115,129],"Video-LLM":[62],"designed":[63],"perform":[65],"fine-grained":[66,139,162],"temporal":[67,163,186],"tasks.":[69],"facilitate":[71],"training":[73],"develop":[77,148],"an":[78],"automatic":[79],"data":[80],"generation":[81],"engine":[82],"build":[84],"Moment-10M,":[85],"large-scale":[87],"instruction":[89,93],"dataset":[90],"with":[91,145,177],"segment-level":[92],"data.":[94],"Building":[95],"upon":[96],"foundation":[98],"previously":[101],"published":[102],"Momentor":[103,146,157],"Moment-10M":[106],"dataset,":[107],"further":[109],"extend":[110],"this":[111],"work":[112],"by":[113],"introducing":[114],"Spatio-Temporal":[116],"Token":[117],"Consolidation":[118],"(STTC)":[119],"method,":[120],"merge":[123],"redundant":[124],"visual":[125,140],"tokens":[126],"spatio-temporally":[127],"parameter-free":[130],"manner,":[131],"thereby":[132],"significantly":[133],"promoting":[134],"computational":[135],"efficiency":[136],"while":[137],"preserving":[138],"details.":[141],"We":[142],"integrate":[143],"STTC":[144],"Momentor++":[149,168],"validate":[151],"its":[152],"performance":[153],"on":[154],"various":[155],"benchmarks.":[156],"demonstrates":[158],"robust":[159],"localization.":[166],"Further,":[167],"excels":[169],"processing":[172],"analyzing":[174],"extended":[175],"videos":[176],"complex":[178],"events,":[179],"showcasing":[180],"marked":[181],"advancements":[182],"handling":[184],"extensive":[185],"contexts.":[187]},"counts_by_year":[],"updated_date":"2026-05-09T06:09:20.037420","created_date":"2026-01-21T00:00:00"}