{"id":"https://openalex.org/W4412888584","doi":"https://doi.org/10.18653/v1/2025.findings-acl.283","title":"AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding","display_name":"AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888584","doi":"https://doi.org/10.18653/v1/2025.findings-acl.283"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.283","pdf_url":"https://aclanthology.org/2025.findings-acl.283.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.283.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100411438","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0001-8139-4192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040700005","display_name":"Qi Si","orcid":"https://orcid.org/0000-0001-5946-5193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyi Si","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shiyu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440114","display_name":"Jie Wu","orcid":"https://orcid.org/0000-0002-7211-2816"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723720","display_name":"Cao Li","orcid":"https://orcid.org/0000-0002-9015-6767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5417","last_page":"5432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.983299970626831,"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":0.983299970626831,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9714999794960022,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9678000211715698,"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/redundancy","display_name":"Redundancy (engineering)","score":0.7526700496673584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7454478144645691},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6022939085960388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34962576627731323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3314960300922394},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05813196301460266}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7526700496673584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454478144645691},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6022939085960388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34962576627731323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3314960300922394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05813196301460266},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.283","pdf_url":"https://aclanthology.org/2025.findings-acl.283.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.283","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.283","pdf_url":"https://aclanthology.org/2025.findings-acl.283.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3114819178","display_name":null,"funder_award_id":"2023QNRC001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5630254371","display_name":null,"funder_award_id":"62236003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5954055007","display_name":null,"funder_award_id":"62376069","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/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888584.pdf","grobid_xml":"https://content.openalex.org/works/W4412888584.grobid-xml"},"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":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"revolutionized":[6],"video":[7],"understanding,":[8],"yet":[9],"are":[10],"still":[11],"limited":[12],"by":[13,23,60,108],"context":[14],"length":[15],"when":[16],"processing":[17,84],"long":[18],"videos.Recent":[19],"methods":[20,107],"compress":[21],"videos":[22],"leveraging":[24],"visual":[25,58],"redundancy":[26,36,59],"uniformly,":[27],"yielding":[28],"promising":[29],"results.Nevertheless,":[30],"our":[31],"quantitative":[32],"analysis":[33],"shows":[34],"that":[35,55,103],"varies":[37],"significantly":[38],"across":[39],"time":[40,65],"and":[41,66,99,110,114,124],"model":[42],"layers,":[43],"necessitating":[44],"a":[45,52,79],"more":[46],"flexible":[47],"compression":[48,62],"strategy.We":[49],"propose":[50],"AdaRETAKE,":[51],"training-free":[53],"method":[54],"flexibly":[56],"reduces":[57],"allocating":[61],"ratios":[63],"among":[64],"layers":[67],"with":[68,118],"theoretical":[69],"guarantees.AdaRETAKE":[70],"can":[71],"be":[72],"seamlessly":[73],"integrated":[74],"into":[75],"existing":[76,106],"MLLMs":[77],"as":[78],"plugand-play":[80],"solution,":[81],"extending":[82],"their":[83],"capacity":[85],"from":[86],"256":[87],"to":[88],"2048":[89],"frames":[90],"while":[91],"preserving":[92],"critical":[93],"information.Experiments":[94],"on":[95,126],"VideoMME,":[96],"MLVU,":[97],"LongVideoBench,":[98],"LVBench":[100],"datasets":[101],"demonstrate":[102],"AdaRETAKE":[104],"outperforms":[105],"2.3%":[109],"2.8%":[111],"for":[112],"7B":[113],"72B":[115],"models,":[116],"respectively,":[117],"even":[119],"greater":[120],"improvements":[121],"of":[122],"5.9%":[123],"6.0%":[125],"the":[127],"longest":[128],"LVBench.Our":[129],"code":[130],"is":[131],"available":[132],"at":[133],"https://github.com/":[134],"SCZwangxiao/video-FlexReduc.git.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}