{"id":"https://openalex.org/W4221166276","doi":"https://doi.org/10.1109/tpami.2022.3223955","title":"TransVOD: End-to-End Video Object Detection With Spatial-Temporal Transformers","display_name":"TransVOD: End-to-End Video Object Detection With Spatial-Temporal Transformers","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4221166276","doi":"https://doi.org/10.1109/tpami.2022.3223955","pmid":"https://pubmed.ncbi.nlm.nih.gov/36417746"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3223955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3223955","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.05047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031210225","display_name":"Qianyu Zhou","orcid":"https://orcid.org/0000-0002-5331-050X"},"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":"Qianyu Zhou","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5331-050X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangtai Li","raw_affiliation_strings":["School of Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0550-8247","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015078046","display_name":"Lu H","orcid":"https://orcid.org/0000-0003-1592-0355"},"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":"Lu He","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103072699","display_name":"Yibo Yang","orcid":"https://orcid.org/0000-0003-0530-7231"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Yang","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0530-7231","affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045854934","display_name":"Guangliang Cheng","orcid":"https://orcid.org/0000-0002-1428-8848"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangliang Cheng","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1428-8848","affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024097240","display_name":"Yunhai Tong","orcid":"https://orcid.org/0000-0001-8735-2516"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhai Tong","raw_affiliation_strings":["School of Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8735-2516","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"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":"Lizhuang Ma","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1653-4341","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.0423,"has_fulltext":false,"cited_by_count":191,"citation_normalized_percentile":{"value":0.99418516,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"45","issue":"6","first_page":"7853","last_page":"7869"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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":0.9987000226974487,"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":0.7899175882339478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6201319694519043},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6157814264297485},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5559223890304565},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5204420685768127},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4984095096588135},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42335790395736694},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3372338116168976},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08044302463531494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899175882339478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6201319694519043},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6157814264297485},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5559223890304565},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5204420685768127},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4984095096588135},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42335790395736694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3372338116168976},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08044302463531494},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2022.3223955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3223955","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:36417746","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36417746","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2201.05047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.05047","pdf_url":"https://arxiv.org/pdf/2201.05047","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.05047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.05047","pdf_url":"https://arxiv.org/pdf/2201.05047","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1014109120","display_name":null,"funder_award_id":"72192821","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3087161604","display_name":null,"funder_award_id":"I8ZD22","funder_id":"https://openalex.org/F4320327557","funder_display_name":"National Office for Philosophy and Social Sciences"},{"id":"https://openalex.org/G3429353868","display_name":null,"funder_award_id":"21511101200","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G6165465362","display_name":null,"funder_award_id":"61972157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7685443560","display_name":null,"funder_award_id":"2019YFC1521104","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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320327557","display_name":"National Office for Philosophy and Social Sciences","ror":"https://ror.org/04m0ms912"},{"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":107,"referenced_works":["https://openalex.org/W607748843","https://openalex.org/W639708223","https://openalex.org/W764651262","https://openalex.org/W1533861849","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2336589871","https://openalex.org/W2552900565","https://openalex.org/W2601564443","https://openalex.org/W2793130599","https://openalex.org/W2884561390","https://openalex.org/W2898044248","https://openalex.org/W2904617485","https://openalex.org/W2908510526","https://openalex.org/W2919935710","https://openalex.org/W2921015377","https://openalex.org/W2950800384","https://openalex.org/W2957958490","https://openalex.org/W2962766617","https://openalex.org/W2962855257","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963212638","https://openalex.org/W2963351448","https://openalex.org/W2963516811","https://openalex.org/W2963585656","https://openalex.org/W2963653352","https://openalex.org/W2964080601","https://openalex.org/W2964086649","https://openalex.org/W2964286567","https://openalex.org/W2969727121","https://openalex.org/W2981858655","https://openalex.org/W2982723417","https://openalex.org/W2982770724","https://openalex.org/W2983827899","https://openalex.org/W2990578161","https://openalex.org/W2994810768","https://openalex.org/W2996794639","https://openalex.org/W3010594275","https://openalex.org/W3016536541","https://openalex.org/W3028265921","https://openalex.org/W3034467781","https://openalex.org/W3084874594","https://openalex.org/W3092462694","https://openalex.org/W3092900809","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3097550038","https://openalex.org/W3100094580","https://openalex.org/W3103358580","https://openalex.org/W3104010045","https://openalex.org/W3104340075","https://openalex.org/W3106643287","https://openalex.org/W3108457314","https://openalex.org/W3115390238","https://openalex.org/W3119686997","https://openalex.org/W3133275180","https://openalex.org/W3138516171","https://openalex.org/W3170874841","https://openalex.org/W3171516518","https://openalex.org/W3172752666","https://openalex.org/W3174156594","https://openalex.org/W3186193138","https://openalex.org/W3188394685","https://openalex.org/W3200157107","https://openalex.org/W3204023867","https://openalex.org/W3206836360","https://openalex.org/W4283311214","https://openalex.org/W4288408844","https://openalex.org/W4292692470","https://openalex.org/W4293437100","https://openalex.org/W4299603580","https://openalex.org/W4302275081","https://openalex.org/W4312511177","https://openalex.org/W4312598093","https://openalex.org/W4312844845","https://openalex.org/W4376626065","https://openalex.org/W4385245566","https://openalex.org/W4394657967","https://openalex.org/W6631943919","https://openalex.org/W6639102338","https://openalex.org/W6695799263","https://openalex.org/W6703733040","https://openalex.org/W6714138976","https://openalex.org/W6739901393","https://openalex.org/W6746472748","https://openalex.org/W6748516020","https://openalex.org/W6749530778","https://openalex.org/W6755600014","https://openalex.org/W6757817989","https://openalex.org/W6760166208","https://openalex.org/W6760424586","https://openalex.org/W6761178061","https://openalex.org/W6765764431","https://openalex.org/W6778485988","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6785762920","https://openalex.org/W6786708909","https://openalex.org/W6787985011","https://openalex.org/W6788023325","https://openalex.org/W6788135285","https://openalex.org/W6799191659","https://openalex.org/W6838809002"],"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/W2136016640","https://openalex.org/W2082269393"],"abstract_inverted_index":{"Detection":[0,35],"Transformer":[1,61,119,152],"(DETR)":[2],"and":[3,127,149,202,275,295],"Deformable":[4,151],"DETR":[5,168],"have":[6],"been":[7,39],"proposed":[8,248,267],"to":[9,70,120,145,155,227],"eliminate":[10],"the":[11,48,72,79,97,123,128,164,178,187,217,220,225,230,242,272],"need":[12,80,107],"for":[13,81,85],"many":[14,82],"hand-designed":[15],"components":[16,84],"in":[17,101,241,255],"object":[18,52,98,125,147,211],"detection":[19,53,159],"while":[20,216,282],"demonstrating":[21],"good":[22],"performance":[23,31],"as":[24,111,224],"previous":[25],"complex":[26],"hand-crafted":[27,83],"detectors.":[28],"However,":[29],"their":[30],"on":[32,56,177,186,259,288],"Video":[33],"Object":[34],"(VOD)":[36],"has":[37],"not":[38,106],"well":[40],"explored.":[41],"In":[42,113,245],"this":[43,67],"paper,":[44],"we":[45,115,193],"present":[46,116,194],"TransVOD,":[47],"first":[49,64],"end-to-end":[50],"video":[51,222],"system":[54],"based":[55],"simple":[57],"yet":[58],"effective":[59],"spatial-temporal":[60],"architectures.":[62],"The":[63,205],"goal":[65],"of":[66,74,131,138,189,198,237,257],"paper":[68],"is":[69],"streamline":[71],"pipeline":[73],"current":[75,157],"VOD,":[76],"effectively":[77],"removing":[78],"feature":[86,129],"aggregation,":[87],"e.g.,":[88],"optical":[89],"flow":[90],"model,":[91],"relation":[92],"networks.":[93],"Besides,":[94],"benefited":[95],"from":[96],"query":[99,212],"design":[100],"DETR,":[102],"our":[103,247],"method":[104],"does":[105],"post-processing":[108],"methods":[109],"such":[110],"Seq-NMS.":[112],"particular,":[114,246],"a":[117,170,251,289],"temporal":[118,135],"aggregate":[121],"both":[122],"spatial":[124],"queries":[126],"memories":[130],"each":[132],"frame.":[133],"Our":[134,266],"transformer":[136],"consists":[137],"two":[139,195],"components:":[140],"Temporal":[141,150],"Query":[142],"Encoder":[143],"(TQE)":[144],"fuse":[146],"queries,":[148],"Decoder":[153],"(TDTD)":[154],"obtain":[156],"frame":[158],"results.":[160],"These":[161],"designs":[162],"boost":[163],"strong":[165],"baseline":[166],"deformable":[167],"by":[169],"significant":[171],"margin":[172],"(3":[173],"%-4":[174],"%":[175,264,280],"mAP)":[176],"ImageNet":[179,190,260],"VID":[180,261],"dataset.":[181],"TransVOD":[182,199,203,268],"yields":[183],"comparable":[184],"performances":[185],"benchmark":[188],"VID.":[191],"Then,":[192],"improved":[196],"versions":[197],"including":[200],"TransVOD++":[201,249],"Lite.":[204],"former":[206],"fuses":[207],"object-level":[208],"information":[209],"into":[210],"via":[213],"dynamic":[214],"convolution":[215],"latter":[218],"models":[219,240,296],"entire":[221],"clips":[223],"output":[226],"speed":[228,274],"up":[229],"inference":[231],"time.":[232],"We":[233],"give":[234],"detailed":[235],"analysis":[236],"all":[238],"three":[239],"experiment":[243],"part.":[244],"sets":[250],"new":[252],"state-of-the-art":[253],"record":[254],"terms":[256],"accuracy":[258,276],"with":[262,278],"90.0":[263],"mAP.":[265],"Lite":[269],"also":[270],"achieves":[271],"best":[273],"trade-off":[277],"83.7":[279],"mAP":[281],"running":[283],"at":[284,299],"around":[285],"30":[286],"FPS":[287],"single":[290],"V100":[291],"GPU":[292],"device.":[293],"Code":[294],"are":[297],"available":[298],"https://github.com/SJTU-LuHe/TransVOD.":[300]},"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":62},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2022-04-03T00:00:00"}