{"id":"https://openalex.org/W4285110782","doi":"https://doi.org/10.1109/access.2022.3184031","title":"Video Sparse Transformer With Attention-Guided Memory for Video Object Detection","display_name":"Video Sparse Transformer With Attention-Guided Memory for Video Object Detection","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285110782","doi":"https://doi.org/10.1109/access.2022.3184031"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3184031","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3184031","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09798833.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09798833.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051026262","display_name":"Masato Fujitake","orcid":"https://orcid.org/0000-0001-7702-499X"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Fujitake","raw_affiliation_strings":["Department of Informatics, The Graduate University for Advanced Studies, SOKENDAI, Miura-gun, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7702-499X","affiliations":[{"raw_affiliation_string":"Department of Informatics, The Graduate University for Advanced Studies, SOKENDAI, Miura-gun, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101463320","display_name":"Akihiro Sugimoto","orcid":"https://orcid.org/0000-0001-9148-9822"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Sugimoto","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9148-9822","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.523,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83669601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"65886","last_page":"65900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8569654226303101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6566231846809387},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6371234059333801},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.608207106590271},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5516871809959412},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5404850244522095},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5134166479110718},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32767820358276367},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07690224051475525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569654226303101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6566231846809387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6371234059333801},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.608207106590271},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5516871809959412},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5404850244522095},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5134166479110718},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32767820358276367},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07690224051475525},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3184031","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3184031","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09798833.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1b39d2fed81e48279d388fdde19c550d","is_oa":false,"landing_page_url":"https://doaj.org/article/1b39d2fed81e48279d388fdde19c550d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"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":"IEEE Access, Vol 10, Pp 65886-65900 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3184031","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3184031","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09798833.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285110782.pdf","grobid_xml":"https://content.openalex.org/works/W4285110782.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2336589871","https://openalex.org/W2549139847","https://openalex.org/W2565639579","https://openalex.org/W2590174509","https://openalex.org/W2622263826","https://openalex.org/W2898044248","https://openalex.org/W2911653429","https://openalex.org/W2950418233","https://openalex.org/W2962855257","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963212638","https://openalex.org/W2963625188","https://openalex.org/W2963653352","https://openalex.org/W2964086649","https://openalex.org/W2964286567","https://openalex.org/W2969727121","https://openalex.org/W2982723417","https://openalex.org/W2983827899","https://openalex.org/W2989604896","https://openalex.org/W2990578161","https://openalex.org/W2991391304","https://openalex.org/W2994810768","https://openalex.org/W2997753998","https://openalex.org/W3003490096","https://openalex.org/W3010594275","https://openalex.org/W3033613646","https://openalex.org/W3034467781","https://openalex.org/W3074270321","https://openalex.org/W3084874594","https://openalex.org/W3092900809","https://openalex.org/W3096609285","https://openalex.org/W3097550038","https://openalex.org/W3103358580","https://openalex.org/W3104010045","https://openalex.org/W3108457314","https://openalex.org/W3116271762","https://openalex.org/W3138516171","https://openalex.org/W3160833223","https://openalex.org/W3162188794","https://openalex.org/W3170630188","https://openalex.org/W3174156594","https://openalex.org/W3188394685","https://openalex.org/W3201476065","https://openalex.org/W3206836360","https://openalex.org/W4221166276","https://openalex.org/W4323654151","https://openalex.org/W6695799263","https://openalex.org/W6696085341","https://openalex.org/W6714138976","https://openalex.org/W6739622702","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6761628794","https://openalex.org/W6772230799","https://openalex.org/W6781533629","https://openalex.org/W6784094891","https://openalex.org/W6790307280","https://openalex.org/W6810509922"],"related_works":["https://openalex.org/W2737719445","https://openalex.org/W4239098401","https://openalex.org/W2898210368","https://openalex.org/W2382480268","https://openalex.org/W1976518449","https://openalex.org/W2732837990","https://openalex.org/W2363366881","https://openalex.org/W4206198161","https://openalex.org/W2363276194","https://openalex.org/W4292830139"],"abstract_inverted_index":{"Detecting":[0],"objects":[1,17],"in":[2],"a":[3,41,66],"video,":[4],"known":[5],"as":[6],"Video":[7,115],"Object":[8],"Detection":[9],"(VOD),":[10],"is":[11,47],"challenging":[12],"since":[13],"appearance":[14],"changes":[15],"of":[16,40,73,149],"over":[18,55],"time":[19,132],"may":[20,62],"bring":[21],"detection":[22,92],"errors.":[23],"Recent":[24],"research":[25],"has":[26],"focused":[27],"on":[28,81,88,146,168,182],"aggregating":[29,125],"features":[30,72,106,127],"from":[31,165],"adjacent":[32],"frames":[33,46],"to":[34,50,129,152],"compensate":[35],"for":[36,98],"the":[37,109,147,150,166],"deteriorated":[38,53,99],"appearances":[39,54],"frame.":[42],"Moreover,":[43],"using":[44],"distant":[45,67],"also":[48],"proposed":[49],"deal":[51],"with":[52,118],"several":[56],"frames.":[57],"Since":[58],"an":[59,140],"object’s":[60],"position":[61],"change":[63],"significantly":[64],"at":[65],"frame,":[68],"they":[69],"only":[70],"use":[71],"object":[74,89,110],"candidate":[75,90,111],"regions,":[76],"which":[77],"do":[78],"not":[79,96],"depend":[80],"their":[82],"position.":[83],"However,":[84],"such":[85],"methods":[86],"rely":[87],"regions’":[91],"performance":[93,178],"and":[94,133,161,171],"are":[95],"practical":[97],"appearances.":[100],"In":[101,136],"this":[102],"paper,":[103],"we":[104,123,138],"enhance":[105],"element-wisely":[107],"before":[108],"region":[112],"detection,":[113],"proposing":[114],"Sparse":[116],"Transformer":[117],"Attention-guided":[119],"Memory":[120],"(VSTAM).":[121],"Furthermore,":[122],"propose":[124],"element-wise":[126],"sparsely":[128],"reduce":[130],"processing":[131],"memory":[134,142],"cost.":[135],"addition,":[137],"introduce":[139],"external":[141],"update":[143],"strategy":[144],"based":[145],"utilization":[148],"aggregation":[151],"hold":[153],"long-term":[154],"information":[155],"effectively.":[156],"Our":[157,174],"method":[158,175],"achieved":[159],"8.3%":[160],"11.1%":[162],"accuracy":[163],"gain":[164],"baseline":[167],"ImageNet":[169],"VID":[170],"UA-DETRAC":[172],"datasets.":[173,186],"demonstrates":[176],"superior":[177],"against":[179],"state-of-the-art":[180],"results":[181],"widely":[183],"used":[184],"VOD":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}