{"id":"https://openalex.org/W4387967959","doi":"https://doi.org/10.1145/3581783.3611903","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","display_name":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967959","doi":"https://doi.org/10.1145/3581783.3611903"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611903","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103224219","display_name":"Yan Zhu","orcid":"https://orcid.org/0000-0002-9224-1797"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Zhu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9224-1797","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001393670","display_name":"Junbao Zhuo","orcid":"https://orcid.org/0000-0001-9587-498X"},"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"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbao Zhuo","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9587-498X","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080757156","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0001-8371-0590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8371-0590","affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037124497","display_name":"Jiajia Geng","orcid":"https://orcid.org/0009-0000-4438-9976"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajia Geng","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4438-9976","affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069204507","display_name":"Xiaoming Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoming Wei","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7471-8344","affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009222019","display_name":"Xiaolin Wei","orcid":"https://orcid.org/0000-0002-3983-047X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolin Wei","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3983-047X","affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"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"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5931-0527","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103224219"],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5887,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69487876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7491","last_page":"7501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.7430931925773621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7163897156715393},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7152167558670044},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5651644468307495},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5515718460083008},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46060115098953247},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4230909049510956},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1774798333644867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430931925773621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7163897156715393},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7152167558670044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5651644468307495},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5515718460083008},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46060115098953247},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4230909049510956},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1774798333644867},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611903","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4199693610","display_name":null,"funder_award_id":"62236008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4789637049","display_name":null,"funder_award_id":"62022083,62236008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5327851226","display_name":null,"funder_award_id":"62022083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6286933758","display_name":null,"funder_award_id":"2018AAA0102000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2064851185","https://openalex.org/W2126579184","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2610467942","https://openalex.org/W2897550429","https://openalex.org/W2904378456","https://openalex.org/W2937614441","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963689837","https://openalex.org/W2963820951","https://openalex.org/W2965373098","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2996901793","https://openalex.org/W3004319625","https://openalex.org/W3016459781","https://openalex.org/W3035254087","https://openalex.org/W3035303837","https://openalex.org/W3188851454","https://openalex.org/W3210279979","https://openalex.org/W4214555767","https://openalex.org/W4214612132","https://openalex.org/W4214727094","https://openalex.org/W4214746887","https://openalex.org/W4255556797","https://openalex.org/W4295046474","https://openalex.org/W4304091699","https://openalex.org/W4312818263"],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W2811390910","https://openalex.org/W4312376745","https://openalex.org/W2082269393","https://openalex.org/W2043960970"],"abstract_inverted_index":{"Zero-shot":[0],"video":[1,11,44,65,69,108,132,184,228],"recognition":[2],"(ZSVR)":[3],"is":[4,176,192],"a":[5,180,189,205,244],"task":[6],"that":[7,13,81,91,103,236],"aims":[8],"to":[9,42,59,124,136,178,194],"recognize":[10],"categories":[12],"have":[14,32],"not":[15],"been":[16],"seen":[17],"during":[18,186],"the":[19,43,56,61,79,89,110,114,126,131,151,159,162,167,196,199,217,239],"model":[20,80,90,142,206],"training":[21],"process.":[22],"Recently,":[23],"vision-language":[24],"models":[25],"(VLMs)":[26],"pre-trained":[27],"on":[28,107,221,226],"large-scale":[29],"image-text":[30],"pairs":[31],"demonstrated":[33],"impressive":[34],"transferability":[35],"for":[36,68,166,209],"ZSVR.":[37],"To":[38,116],"make":[39],"VLMs":[40],"applicable":[41],"domain,":[45],"existing":[46],"methods":[47],"often":[48],"use":[49,134],"an":[50,75,171],"additional":[51],"temporal":[52,62,93,105,128,164,201,214],"learning":[53,94],"module":[54,95,175],"after":[55],"image-level":[57],"encoder":[58],"learn":[60,179],"relationships":[63],"among":[64],"frames.":[66],"Unfortunately,":[67],"from":[70],"unseen":[71],"categories,":[72],"we":[73,120],"observe":[74],"abnormal":[76],"phenomenon":[77],"where":[78],"uses":[82,97],"spatial-temporal":[83,139,146,183],"feature":[84,112,129,147,165,185],"performs":[85,148],"much":[86],"worse":[87],"than":[88,150],"removes":[92],"and":[96,133,216,233],"only":[98,154],"spatial":[99,111,155],"feature.":[100,140,202],"We":[101,203],"conjecture":[102],"improper":[104],"modeling":[106],"disrupts":[109],"of":[113,130,161,198],"video.":[115],"verify":[117],"our":[118],"hypothesis,":[119],"propose":[121,204],"Feature":[122],"Factorization":[123],"retain":[125],"orthogonal":[127,163,200,213],"interpolation":[135,215],"construct":[137],"refined":[138,145,182],"The":[141,223],"using":[143,153],"appropriately":[144],"better":[149,181],"one":[152],"feature,":[156],"which":[157],"verifies":[158],"effectiveness":[160],"ZSVR":[168,210,224],"task.":[169],"Therefore,":[170],"Orthogonal":[172],"Temporal":[173],"Interpolation":[174],"designed":[177],"training.":[187],"Additionally,":[188],"Matching":[190],"Loss":[191],"introduced":[193],"improve":[195],"quality":[197],"called":[207],"OTI":[208,237],"by":[211,243],"employing":[212],"matching":[218],"loss":[219],"based":[220],"VLMs.":[222],"accuracies":[225],"popular":[227],"datasets":[229],"(i.e.,":[230],"Kinetics-600,":[231],"UCF101":[232],"HMDB51)":[234],"show":[235],"outperforms":[238],"previous":[240],"state-of-the-art":[241],"method":[242],"clear":[245],"margin.Our":[246],"codes":[247],"are":[248],"publicly":[249],"available":[250],"at":[251],"https://github.com/yanzhu/mm2023_oti.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}