{"id":"https://openalex.org/W4416241916","doi":"https://doi.org/10.1109/iccv51701.2025.01936","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","display_name":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416241916","doi":"https://doi.org/10.1109/iccv51701.2025.01936"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01936","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.07312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052437722","display_name":"Min Yang","orcid":"https://orcid.org/0000-0001-9714-5545"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Yang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120402660","display_name":"Zihan Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Jia","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhilin Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilin Dai","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077081254","display_name":"Sheng Guo","orcid":"https://orcid.org/0000-0002-4827-8015"},"institutions":[{"id":"https://openalex.org/I4210135679","display_name":"Antea Group (France)","ror":"https://ror.org/03kfw6k71","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210101086","https://openalex.org/I4210135679"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sheng Guo","raw_affiliation_strings":["MyBank, Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MyBank, Ant Group","institution_ids":["https://openalex.org/I4210135679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017986653","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0003-2543-3622"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052437722"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31984132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20824","last_page":"20835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4749999940395355,"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":0.4749999940395355,"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":0.272599995136261,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0851999968290329,"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/mobile-device","display_name":"Mobile device","score":0.7936000227928162},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5942999720573425},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5583000183105469},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48890000581741333},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.46320000290870667},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.460999995470047},{"id":"https://openalex.org/keywords/mobile-computing","display_name":"Mobile computing","score":0.45969998836517334}],"concepts":[{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.7936000227928162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.460999995470047},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01936","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:2508.07312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07312","pdf_url":"https://arxiv.org/pdf/2508.07312","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2508.07312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.07312","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.07312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07312","pdf_url":"https://arxiv.org/pdf/2508.07312","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/G4152983559","display_name":null,"funder_award_id":"2022ZD0160900","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":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"lightweight":[1],"neural":[2],"networks":[3],"are":[4],"with":[5,32,82],"increasing":[6],"attention":[7],"due":[8],"to":[9,39],"their":[10],"faster":[11,107,112],"reasoning":[12],"speed":[13,98],"and":[14,35,61,86,110,128],"easier":[15],"deployment":[16],"on":[17,27,43,64,79,99,134],"mobile":[18,44,80,100],"devices.":[19,45],"However,":[20],"existing":[21],"video":[22],"pre-trained":[23],"models":[24],"still":[25],"focus":[26],"the":[28],"common":[29],"ViT":[30],"architecture":[31,42],"high":[33],"latency,":[34],"few":[36],"works":[37],"attempt":[38],"build":[40],"efficient":[41,58,73],"This":[46],"paper":[47],"bridges":[48],"this":[49],"gap":[50],"by":[51],"introducing":[52],"temporal":[53],"structural":[54],"reparameterization":[55],"into":[56],"an":[57,72],"image-text":[59],"model":[60,75],"training":[62],"it":[63],"a":[65],"large-scale":[66],"high-quality":[67],"video-text":[68,74],"dataset,":[69],"resulting":[70],"in":[71,94],"that":[76],"can":[77],"run":[78],"devices":[81],"strong":[83],"zero-shot":[84,118],"classification":[85],"retrieval":[87,119],"capabilities,":[88],"termed":[89],"as":[90,126],"MobileViCLIP.":[91],"In":[92,115],"particular,":[93],"terms":[95,116],"of":[96,117],"inference":[97],"devices,":[101],"our":[102,121],"MobileViCLIP-Small":[103,122],"is":[104,138],"55.4x":[105],"times":[106],"than":[108,113,132],"InternVideo2-L14":[109,127],"6.7x":[111],"InternVideo2-S14.":[114],"performance,":[120],"obtains":[123,129],"similar":[124],"performance":[125],"6.9\\%":[130],"better":[131],"InternVideo2-S14":[133],"MSR-VTT.":[135],"The":[136],"code":[137],"available":[139],"at":[140],"https://github.com/MCG-NJU/MobileViCLIP.":[141]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}