{"id":"https://openalex.org/W4405433119","doi":"https://doi.org/10.1109/iccv51701.2025.02276","title":"B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens","display_name":"B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405433119","doi":"https://doi.org/10.1109/iccv51701.2025.02276"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02276","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.09919","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102154571","display_name":"Zhuqiang Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhuqiang Lu","raw_affiliation_strings":["School of Computer Science, The University of Sydney,NSW,Australia,2006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney,NSW,Australia,2006","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063953932","display_name":"Zhenfei Yin","orcid":"https://orcid.org/0000-0002-8666-1103"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhenfei Yin","raw_affiliation_strings":["School of Computer Science, The University of Sydney,NSW,Australia,2006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney,NSW,Australia,2006","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044332886","display_name":"Meilin He","orcid":"https://orcid.org/0000-0002-1615-8924"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mengwei He","raw_affiliation_strings":["School of Computer Science, The University of Sydney,NSW,Australia,2006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney,NSW,Australia,2006","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043228501","display_name":"Zhihui Wang","orcid":"https://orcid.org/0000-0002-8024-7753"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"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"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Zhihui Wang","raw_affiliation_strings":["International School of Information Science and Engineering, Dalian University of Technology,Dalian,China,116081","School of Computer Science, The University of Sydney,NSW,Australia,2006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International School of Information Science and Engineering, Dalian University of Technology,Dalian,China,116081","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Computer Science, The University of Sydney,NSW,Australia,2006","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048295582","display_name":"Zicheng Liu","orcid":"https://orcid.org/0000-0002-2342-2340"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zicheng Liu","raw_affiliation_strings":["Advanced Micro Devices,WA,USA,98007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices,WA,USA,98007","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058809518","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0009-0003-4834-2333"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"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"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["International School of Information Science and Engineering, Dalian University of Technology,Dalian,China,116081","School of Computer Science, The University of Sydney,NSW,Australia,2006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International School of Information Science and Engineering, Dalian University of Technology,Dalian,China,116081","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Computer Science, The University of Sydney,NSW,Australia,2006","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028673475","display_name":"Kun Hu","orcid":"https://orcid.org/0000-0003-0350-3132"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kun Hu","raw_affiliation_strings":["School of Science, Edith Cowan University,WA,Australia,6027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Edith Cowan University,WA,Australia,6027","institution_ids":["https://openalex.org/I12079687"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24549","last_page":"24559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9936000108718872,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.97079998254776,"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/computer-science","display_name":"Computer science","score":0.5696151256561279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34398213028907776},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.32093188166618347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5696151256561279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34398213028907776},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32093188166618347}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02276","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:2412.09919","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09919","pdf_url":"https://arxiv.org/pdf/2412.09919","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.2412.09919","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.09919","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.09919","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09919","pdf_url":"https://arxiv.org/pdf/2412.09919","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":[],"funders":[{"id":"https://openalex.org/F4320320988","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405433119.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recently,":[0],"Vision":[1],"Large":[2],"Language":[3],"Models":[4],"(VLLMs)":[5],"integrated":[6],"with":[7],"vision":[8,15],"encoders":[9],"have":[10],"shown":[11],"promising":[12],"performance":[13,253],"in":[14,64,121,130,239,248],"understanding.":[16],"The":[17,189,202],"key":[18],"of":[19,28,55,67,72,83,97,104,157,169,205,243],"VLLMs":[20,32,51,73,87],"is":[21,237,261],"to":[22,33,50,146,180,184,224],"encode":[23],"visual":[24,29,37,56,84,105,158,186,203,246],"content":[25],"into":[26,93],"sequences":[27],"tokens,":[30,85],"enabling":[31],"simultaneously":[34],"process":[35],"both":[36],"and":[38,74,123,217,245],"textual":[39],"content.":[40],"However,":[41],"understanding":[42,187,257],"videos,":[43,46,62],"especially":[44],"long":[45],"remain":[47],"a":[48,94,140,174,196,212],"challenge":[49],"as":[52],"the":[53,65,69,81,102,113,117,124,127,155,161,167,185,206,229,241],"number":[54,82,96,103,156,242],"tokens":[57,106,159,204,247],"grows":[58],"rapidly":[59],"when":[60],"encoding":[61],"resulting":[63],"risk":[66],"exceeding":[68],"context":[70,163],"window":[71,164],"introducing":[75],"heavy":[76],"computation":[77],"burden.":[78],"To":[79],"restrict":[80],"existing":[86],"either:":[88],"(1)":[89],"uniformly":[90],"downsample":[91],"videos":[92,122],"fixed":[95],"frames":[98,182,191,208,244],"or":[99],"(2)":[100],"reducing":[101],"encoded":[107],"from":[108],"each":[109,131],"frame.":[110,132],"We":[111],"argue":[112],"former":[114],"solution":[115],"neglects":[116],"rich":[118],"temporal":[119,197],"cue":[120],"later":[125],"overlooks":[126],"spatial":[128,213,220],"details":[129],"In":[133],"this":[134],"work,":[135],"we":[136,172],"present":[137],"Balanced-VLLM":[138],"(B-VLLM):":[139],"novel":[141],"VLLM":[142,162],"framework":[143],"that":[144,235],"aims":[145],"effectively":[147],"leverage":[148],"task":[149],"relevant":[150,183],"spatio-temporal":[151],"cues":[152],"while":[153],"restricting":[154],"under":[160],"length.":[165],"At":[166],"core":[168],"our":[170],"method,":[171],"devise":[173],"text-conditioned":[175],"adaptive":[176],"frame":[177,198],"selection":[178],"module":[179,216],"identify":[181],"task.":[188],"selected":[190,207],"are":[192,209],"then":[193],"de-duplicated":[194],"using":[195],"token":[199,214,221,230],"merging":[200,222],"technique.":[201],"processed":[210],"through":[211],"sampling":[215],"an":[218],"optional":[219],"strategy":[223],"achieve":[225],"precise":[226],"control":[227],"over":[228],"count.":[231],"Experimental":[232],"results":[233],"show":[234],"B-VLLM":[236],"effective":[238],"balancing":[240],"video":[249,256],"understanding,":[250],"yielding":[251],"superior":[252],"on":[254],"various":[255],"benchmarks.":[258],"Our":[259],"code":[260],"available":[262],"at":[263],"https://github.com/zhuqiangLu/B-VLLM.":[264]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}