{"id":"https://openalex.org/W4405355418","doi":"https://doi.org/10.1109/iccv51701.2025.01935","title":"Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM","display_name":"Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405355418","doi":"https://doi.org/10.1109/iccv51701.2025.01935"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01935","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/2412.09530","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100452675","display_name":"Han Wang","orcid":"https://orcid.org/0000-0002-1320-0947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Wang","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056540913","display_name":"Yuxiang Nie","orcid":"https://orcid.org/0009-0001-4197-1079"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiang Nie","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103248206","display_name":"Yongjie Ye","orcid":"https://orcid.org/0009-0000-0093-7993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongjie Ye","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115426737","display_name":"Deng GuanYu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanjie Wang","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738102","display_name":"Yanjie Wang","orcid":"https://orcid.org/0000-0002-2305-1041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Li","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101650550","display_name":"Haiyang Yu","orcid":"https://orcid.org/0000-0001-9311-0230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyang Yu","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101650550","display_name":"Haiyang Yu","orcid":"https://orcid.org/0000-0001-9311-0230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinghui Lu","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050212540","display_name":"Jinghui Lu","orcid":"https://orcid.org/0000-0001-7149-6961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Can Huang","raw_affiliation_strings":["Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20812","last_page":"20823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9962000250816345,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9962000250816345,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9872000217437744,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.7317423820495605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6415092349052429},{"id":"https://openalex.org/keywords/dynamic-range-compression","display_name":"Dynamic range compression","score":0.624032199382782},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6228207349777222},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5325383543968201},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.14585232734680176},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13086017966270447},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10438871383666992}],"concepts":[{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7317423820495605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6415092349052429},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.624032199382782},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6228207349777222},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5325383543968201},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.14585232734680176},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13086017966270447},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10438871383666992},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01935","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:2412.09530","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09530","pdf_url":"https://arxiv.org/pdf/2412.09530","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.09530","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.09530","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:2412.09530","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09530","pdf_url":"https://arxiv.org/pdf/2412.09530","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405355418.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1972233422","https://openalex.org/W4385486824","https://openalex.org/W4297695714","https://openalex.org/W2611316230","https://openalex.org/W1528302882","https://openalex.org/W2274026817","https://openalex.org/W2296858511","https://openalex.org/W4403467802","https://openalex.org/W2178166993","https://openalex.org/W2389658797"],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,40,50,60,85,131],"Large":[3],"Vision-Language":[4],"Models":[5],"(LVLMs)":[6],"for":[7,30,43],"analyzing":[8],"images":[9],"and":[10,15,103,115,137],"videos":[11],"is":[12,36],"an":[13,128],"exciting":[14],"rapidly":[16],"evolving":[17],"field.":[18],"In":[19,63],"recent":[20],"years,":[21],"we've":[22],"seen":[23],"significant":[24],"growth":[25],"in":[26,122],"high-quality":[27],"image-text":[28],"datasets":[29,42],"fine-tuning":[31],"image":[32],"understanding,":[33],"but":[34],"there":[35],"still":[37],"a":[38,68,82,90,98],"lack":[39],"comparable":[41],"videos.":[44,62],"Additionally,":[45],"many":[46],"VideoLLMs":[47],"are":[48,142],"extensions":[49],"single-image":[51],"VLMs,":[52],"which":[53],"may":[54],"not":[55],"efficiently":[56],"handle":[57],"the":[58],"complexities":[59],"longer":[61],"this":[64],"study,":[65],"we":[66],"introduce":[67],"large-scale":[69],"synthetic":[70],"dataset":[71],"created":[72],"from":[73],"proprietary":[74],"models,":[75],"using":[76],"carefully":[77],"designed":[78],"prompts":[79],"to":[80],"tackle":[81],"wide":[83],"range":[84],"questions.":[86],"We":[87],"also":[88],"explore":[89],"dynamic":[91],"visual":[92],"token":[93],"compression":[94],"architecture":[95],"that":[96],"strikes":[97],"balance":[99],"between":[100],"computational":[101],"efficiency":[102],"performance.":[104],"Our":[105],"proposed":[106],"\\model{}":[107,126],"achieves":[108],"state-of-the-art":[109],"results":[110],"across":[111],"various":[112],"video":[113],"tasks":[114],"shows":[116],"impressive":[117],"generalization,":[118],"setting":[119],"new":[120],"baselines":[121],"multi-image":[123],"understanding.":[124],"Notably,":[125],"delivers":[127],"absolute":[129],"improvement":[130],"2.7\\%":[132],"over":[133],"LLaVA-OneVision":[134],"on":[135,139],"VideoMME":[136],"10.7\\%":[138],"MuirBench.":[140],"Codes":[141],"available":[143],"at":[144],"https://github.com/Hon-Wong/ByteVideoLLM":[145]},"counts_by_year":[],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}
