{"id":"https://openalex.org/W4390097792","doi":"https://doi.org/10.1109/iccd58817.2023.00064","title":"ViTframe: Vision Transformer Acceleration via Informative Frame Selection for Video Recognition","display_name":"ViTframe: Vision Transformer Acceleration via Informative Frame Selection for Video Recognition","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4390097792","doi":"https://doi.org/10.1109/iccd58817.2023.00064"},"language":"en","primary_location":{"id":"doi:10.1109/iccd58817.2023.00064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd58817.2023.00064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 41st International Conference on Computer Design (ICCD)","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/A5051407403","display_name":"Chunyu Qi","orcid":"https://orcid.org/0009-0004-9814-2468"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chunyu Qi","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699768","display_name":"Zilong Li","orcid":"https://orcid.org/0000-0003-3271-1758"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong Li","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067161373","display_name":"Zhuoran Song","orcid":"https://orcid.org/0000-0002-6494-4786"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoran Song","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056632010","display_name":"Xiaoyao Liang","orcid":"https://orcid.org/0000-0002-2790-5884"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyao Liang","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051407403"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.134,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47530187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9984999895095825,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7124736905097961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6275699138641357},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6230936050415039},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5788931846618652},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5008800029754639},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4533114731311798},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33059531450271606},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14585953950881958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124736905097961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6275699138641357},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6230936050415039},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5788931846618652},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5008800029754639},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4533114731311798},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33059531450271606},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14585953950881958},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccd58817.2023.00064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd58817.2023.00064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 41st International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1969369024","https://openalex.org/W2619947201","https://openalex.org/W2807968599","https://openalex.org/W2896457183","https://openalex.org/W2963616706","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3168124404","https://openalex.org/W3169769781","https://openalex.org/W3188427387","https://openalex.org/W4214614183","https://openalex.org/W4292779060","https://openalex.org/W4312769131","https://openalex.org/W4360831786","https://openalex.org/W4360831795","https://openalex.org/W4360832001","https://openalex.org/W4385245566","https://openalex.org/W4386065588","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6778883912","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790307280","https://openalex.org/W6796494063","https://openalex.org/W6797478244","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2565094479","https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W602859758","https://openalex.org/W2006439817","https://openalex.org/W1971289376","https://openalex.org/W2379101322","https://openalex.org/W1992553864","https://openalex.org/W2776207444","https://openalex.org/W2726447019"],"abstract_inverted_index":{"Vision":[0,98],"Transformer":[1,99],"(ViT)":[2],"has":[3],"achieved":[4],"state-of-the-art":[5],"performance":[6],"in":[7,21,33,46,92,110,180],"the":[8,13,22,25,51,57,78,111,136,141,156,161,174,188],"computer":[9],"vision":[10],"field,":[11],"showcasing":[12],"remarkable":[14],"potential":[15],"to":[16,64,84,106,133,153,171],"become":[17],"a":[18,97,144,149,168,181],"dominant":[19],"model":[20],"future.":[23],"However,":[24],"self-attention":[26],"mechanism":[27,152],"within":[28,73],"ViT":[29,120,146],"presents":[30],"significant":[31],"challenges":[32],"terms":[34],"of":[35,59,190],"computational":[36,52],"requirements":[37],"and":[38,148,196],"storage":[39],"demands.":[40],"This":[41],"limitation":[42],"becomes":[43],"particularly":[44],"pronounced":[45],"video":[47,89,112,123,142],"recognition":[48],"tasks,":[49],"where":[50],"complexity":[53],"escalates":[54],"proportionally":[55],"with":[56],"number":[58],"input":[60],"frames.":[61],"Current":[62],"efforts":[63],"enhance":[65],"ViT\u2019s":[66],"efficiency":[67],"mainly":[68],"concentrate":[69],"on":[70,193],"exploiting":[71],"sparsity":[72],"individual":[74],"frames,":[75,82],"which":[76,104],"neglects":[77],"temporal":[79,108],"redundancy":[80,109],"across":[81],"leading":[83],"an":[85,128],"unsatisfactory":[86],"solution":[87],"for":[88,121,143,155],"tasks.":[90],"Alternatively,":[91],"this":[93],"paper,":[94],"we":[95,166],"propose":[96],"acceleration":[100],"framework":[101],"called":[102],"ViTframe,":[103],"aims":[105],"omit":[107],"by":[113,160],"dynamically":[114],"selecting":[115],"informative":[116,129,162],"frames":[117,139],"fed":[118],"into":[119],"fast":[122],"recognition.":[124],"We":[125,177],"first":[126],"introduce":[127],"frame":[130,163],"selection":[131],"algorithm":[132],"pick":[134],"out":[135],"most":[137],"representative":[138],"from":[140],"quick":[145],"inference":[147],"result":[150],"compensation":[151],"compensate":[154],"accuracy":[157],"loss":[158],"incurred":[159],"selection.":[164],"Moreover,":[165],"offer":[167],"customized":[169],"architecture":[170],"efficiently":[172],"implement":[173,178],"ViTframe":[175,179],"algorithm.":[176],"28nm":[182],"technology":[183],"node.":[184],"Extensive":[185],"evaluations":[186],"verify":[187],"effectiveness":[189],"our":[191],"proposal":[192],"speedup,":[194],"energy,":[195],"accuracy.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}