{"id":"https://openalex.org/W7140296184","doi":"https://doi.org/10.48550/arxiv.2603.22953","title":"Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining","display_name":"Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140296184","doi":"https://doi.org/10.48550/arxiv.2603.22953"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.22953","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22953","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.22953","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130615039","display_name":"Weijun Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhuang, Weijun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130577679","display_name":"Yuqing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yuqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130563820","display_name":"Weikang Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Weikang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130593230","display_name":"Xin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130623579","display_name":"Ming Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130574544","display_name":"Xiaopeng Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Xiaopeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130572131","display_name":"Yaowei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yaowei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130558091","display_name":"Wangmeng Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Wangmeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5130615039"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9919000267982483,"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":0.9919000267982483,"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":0.0019000000320374966,"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":0.00139999995008111,"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/masking","display_name":"Masking (illustration)","score":0.7156999707221985},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6326000094413757},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.47620001435279846},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4747999906539917},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4478999972343445},{"id":"https://openalex.org/keywords/visual-masking","display_name":"Visual masking","score":0.43880000710487366},{"id":"https://openalex.org/keywords/backward-masking","display_name":"Backward masking","score":0.436599999666214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753999829292297},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7156999707221985},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6326000094413757},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.47620001435279846},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724999964237213},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C2779200073","wikidata":"https://www.wikidata.org/wiki/Q18395575","display_name":"Visual masking","level":4,"score":0.43880000710487366},{"id":"https://openalex.org/C2776817677","wikidata":"https://www.wikidata.org/wiki/Q4839818","display_name":"Backward masking","level":3,"score":0.436599999666214},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4097000062465668},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.22953","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22953","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":"doi:10.48550/arxiv.2603.22953","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22953","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"video-language":[1,63,156],"pretraining":[2],"enables":[3],"strong":[4,109],"generalization":[5],"across":[6,131],"multimodal":[7,123],"tasks":[8],"but":[9],"often":[10],"incurs":[11],"prohibitive":[12],"computational":[13],"costs.":[14],"Although":[15],"recent":[16],"advances":[17],"in":[18],"masked":[19],"visual":[20,34,72,127],"modeling":[21],"help":[22],"mitigate":[23],"this":[24],"issue,":[25],"they":[26],"still":[27],"suffer":[28],"from":[29],"two":[30],"fundamental":[31],"limitations:":[32],"severe":[33],"information":[35,43],"loss":[36],"under":[37],"high":[38],"masking":[39,82,96],"ratios":[40],"and":[41,146],"temporal":[42,90,110],"leakage":[44],"caused":[45],"by":[46,83],"inter-frame":[47],"correlations.":[48],"To":[49],"address":[50],"these":[51],"challenges,":[52],"we":[53,113],"propose":[54],"ClusterSTM,":[55],"a":[56,115,151],"Cluster-Wise":[57],"Spatio-Temporal":[58],"Masking":[59],"strategy":[60,97],"for":[61],"efficient":[62,155],"pretraining.":[64],"ClusterSTM":[65,136],"first":[66],"performs":[67],"intra-frame":[68],"clustering":[69],"to":[70],"partition":[71],"tokens":[73,102],"into":[74],"multiple":[75,132],"semantically":[76],"independent":[77],"clusters,":[78],"then":[79],"conducts":[80],"cluster-wise":[81],"retaining":[84],"the":[85,88,100],"token":[86],"with":[87],"highest":[89],"density":[91],"within":[92],"each":[93],"cluster.":[94],"Our":[95],"ensure":[98],"that":[99,120,135],"retained":[101],"capture":[103],"holistic":[104],"video":[105,143,147],"content":[106],"while":[107],"exhibit":[108],"correlation.":[111],"Additionally,":[112],"introduce":[114],"video-text":[116,141],"relevance":[117],"reconstruction":[118],"objective":[119],"aligns":[121],"high-level":[122],"semantics":[124],"beyond":[125],"conventional":[126],"reconstruction.":[128],"Extensive":[129],"experiments":[130],"benchmarks":[133],"demonstrate":[134],"achieves":[137],"superior":[138],"performance":[139],"on":[140],"retrieval,":[142],"question":[144],"answering,":[145],"captioning":[148],"tasks,":[149],"establishing":[150],"new":[152],"state-of-the-art":[153],"among":[154],"models.":[157]},"counts_by_year":[],"updated_date":"2026-03-26T06:10:45.909354","created_date":"2026-03-26T00:00:00"}