{"id":"https://openalex.org/W4404649407","doi":"https://doi.org/10.1109/iccv51701.2025.02047","title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","display_name":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404649407","doi":"https://doi.org/10.1109/iccv51701.2025.02047"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02047","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.14401","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100395391","display_name":"Yiming Zhang","orcid":"https://orcid.org/0009-0000-9289-6227"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhang","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776767","display_name":"Zhuokai Zhao","orcid":"https://orcid.org/0000-0001-8201-2977"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuokai Zhao","raw_affiliation_strings":["University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032213685","display_name":"Zhaorun Chen","orcid":"https://orcid.org/0000-0002-2668-6587"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaorun Chen","raw_affiliation_strings":["University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112102159","display_name":"Zenghui Ding","orcid":"https://orcid.org/0000-0002-6787-9318"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zenghui Ding","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052468576","display_name":"Xianjun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianjun Yang","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101515037","display_name":"Yining Sun","orcid":"https://orcid.org/0000-0001-9851-7611"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yining Sun","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00077995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22046","last_page":"22055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9970999956130981,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9970999956130981,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9905999898910522,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/security-token","display_name":"Security token","score":0.8655158281326294},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7613229751586914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6813724040985107},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6751091480255127},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6321702003479004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3405149579048157},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.22303825616836548},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07070660591125488}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8655158281326294},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7613229751586914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6813724040985107},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6751091480255127},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6321702003479004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3405149579048157},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.22303825616836548},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07070660591125488},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02047","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:2411.14401","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14401","pdf_url":"https://arxiv.org/pdf/2411.14401","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.14401","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.14401","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.14401","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14401","pdf_url":"https://arxiv.org/pdf/2411.14401","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G425254596","display_name":null,"funder_award_id":"2024YFF0507603","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404649407.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W2366718574"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,19,54],"multimodal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"have":[8],"opened":[9],"new":[10,142],"avenues":[11],"for":[12,74,144],"video":[13,21,26,60,76,146],"understanding.":[14,147],"However,":[15],"achieving":[16,129],"high":[17],"fidelity":[18],"zero-shot":[20,75,145],"tasks":[22],"remains":[23],"challenging.":[24],"Traditional":[25],"processing":[27],"methods":[28,138],"rely":[29],"heavily":[30],"on":[31],"fine-tuning":[32],"to":[33,100,133],"capture":[34],"nuanced":[35],"spatial-temporal":[36],"details,":[37],"which":[38],"incurs":[39],"significant":[40],"data":[41],"and":[42,94,105,136,139],"computation":[43],"costs.":[44],"In":[45],"contrast,":[46],"training-free":[47,137],"approaches,":[48],"though":[49],"efficient,":[50],"often":[51],"lack":[52],"robustness":[53],"preserving":[55,84],"context-rich":[56],"features":[57],"across":[58,121],"complex":[59],"content.":[61],"To":[62],"this":[63],"end,":[64],"we":[65],"propose":[66],"DYTO,":[67,128],"a":[68,90,95,111,141],"novel":[69],"dynamic":[70],"token":[71,81,97,108],"merging":[72,98],"framework":[73],"understanding":[77],"that":[78],"adaptively":[79],"optimizes":[80],"efficiency":[82,115],"while":[83],"crucial":[85],"scene":[86],"details.":[87],"DYTO":[88],"integrates":[89],"hierarchical":[91],"frame":[92],"selection":[93],"bipartite":[96],"strategy":[99],"dynamically":[101],"cluster":[102],"key":[103],"frames":[104],"selectively":[106],"compress":[107],"sequences,":[109],"striking":[110],"balance":[112],"between":[113],"computational":[114],"with":[116],"semantic":[117],"richness.":[118],"Extensive":[119],"experiments":[120],"multiple":[122],"benchmarks":[123],"demonstrate":[124],"the":[125],"effectiveness":[126],"of":[127],"superior":[130],"performance":[131],"compared":[132],"both":[134],"fine-tuned":[135],"setting":[140],"state-of-the-art":[143]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}