{"id":"https://openalex.org/W3166712493","doi":"https://doi.org/10.1109/tcsvt.2021.3085907","title":"Human-Centric Spatio-Temporal Video Grounding With Visual Transformers","display_name":"Human-Centric Spatio-Temporal Video Grounding With Visual Transformers","publication_year":2021,"publication_date":"2021-06-04","ids":{"openalex":"https://openalex.org/W3166712493","doi":"https://doi.org/10.1109/tcsvt.2021.3085907","mag":"3166712493"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2021.3085907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3085907","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5075863583","display_name":"Zongheng Tang","orcid":"https://orcid.org/0000-0002-9903-802X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zongheng Tang","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002061412","display_name":"Yue Liao","orcid":"https://orcid.org/0000-0002-2671-0655"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Liao","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042965510","display_name":"Guanbin Li","orcid":"https://orcid.org/0000-0002-4805-0926"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanbin Li","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","Pazhou Lab, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Pazhou Lab, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101828825","display_name":"Xiaojie Jin","orcid":"https://orcid.org/0000-0003-2789-0923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojie Jin","raw_affiliation_strings":["ByteDance AI Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048928060","display_name":"Hongxu Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxu Jiang","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101600341","display_name":"Qian Yu","orcid":"https://orcid.org/0000-0002-0538-7940"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Yu","raw_affiliation_strings":["School of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082181536","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0003-2775-9730"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5075863583"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":6.2011,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.97421561,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"32","issue":"12","first_page":"8238","last_page":"8249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9932000041007996,"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":0.8027631044387817},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6682754755020142},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5789329409599304},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.567041277885437},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5565375089645386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5508671402931213},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44353994727134705},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38691839575767517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027631044387817},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6682754755020142},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5789329409599304},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.567041277885437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5565375089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5508671402931213},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44353994727134705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38691839575767517},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2021.3085907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3085907","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G1260346414","display_name":null,"funder_award_id":"2019KD0AB04","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2952538351","display_name":null,"funder_award_id":"2020B1515020048","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G3953516272","display_name":null,"funder_award_id":"4202034","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G7834498664","display_name":null,"funder_award_id":"61876177","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1596841185","https://openalex.org/W2111078031","https://openalex.org/W2146502635","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2571175805","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2798354744","https://openalex.org/W2799058067","https://openalex.org/W2886641317","https://openalex.org/W2890502146","https://openalex.org/W2894280539","https://openalex.org/W2896457183","https://openalex.org/W2897628926","https://openalex.org/W2903901502","https://openalex.org/W2904824998","https://openalex.org/W2951323451","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2963109634","https://openalex.org/W2963521717","https://openalex.org/W2963662190","https://openalex.org/W2963843782","https://openalex.org/W2963916161","https://openalex.org/W2964015378","https://openalex.org/W2964089981","https://openalex.org/W2964345792","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2968356596","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2970401629","https://openalex.org/W2970869018","https://openalex.org/W2997429269","https://openalex.org/W2998356391","https://openalex.org/W3034325957","https://openalex.org/W3034772468","https://openalex.org/W3035590142","https://openalex.org/W3035598501","https://openalex.org/W3047922927","https://openalex.org/W3090449556","https://openalex.org/W3108748824","https://openalex.org/W6620707391","https://openalex.org/W6681435938","https://openalex.org/W6726873649","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6768156624","https://openalex.org/W6770883170","https://openalex.org/W6776721752"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2043093291","https://openalex.org/W2101155126","https://openalex.org/W2363545964"],"abstract_inverted_index":{"In":[0],"this":[1,101,106,137,187],"work,":[2],"we":[3,139],"introduce":[4],"a":[5,32,45,70,74,81,172],"novel":[6],"task":[7,50,84,102,107],"\u2013":[8],"Human-centric":[9],"Spatio-Temporal":[10,115],"Video":[11],"Grounding":[12,116],"(HC-STVG).":[13],"Unlike":[14],"the":[15,36,61,95,191,195],"existing":[16,96,196],"referring":[17],"expression":[18],"tasks":[19],"in":[20],"images":[21],"or":[22],"videos,":[23],"by":[24,108],"focusing":[25],"on":[26,44,159,186],"humans,":[27],"HC-STVG":[28,79,143],"aims":[29],"to":[30,125],"localize":[31],"spatio-temporal":[33],"tube":[34],"of":[35,155,179],"target":[37],"person":[38,72],"from":[39],"an":[40,110,142,177],"untrimmed":[41],"video":[42,82,165],"based":[43],"given":[46],"textural":[47],"description.":[48],"This":[49],"is":[51,77,80,147],"useful,":[52],"especially":[53],"for":[54,129,167],"healthcare":[55],"and":[56,90,132],"security":[57],"related":[58],"applications,":[59],"where":[60],"surveillance":[62],"videos":[63],"can":[64],"be":[65],"extremely":[66],"long":[67],"but":[68],"only":[69],"specific":[71,75],"during":[73],"period":[76],"concerned.":[78],"grounding":[83,97],"that":[85,190],"requires":[86],"both":[87],"spatial":[88],"(where)":[89],"temporal":[91,133],"(when)":[92],"localization.":[93,134],"Unfortunately,":[94],"methods":[98],"cannot":[99],"handle":[100],"well.":[103],"We":[104],"tackle":[105],"proposing":[109],"effective":[111],"baseline":[112,197],"method":[113,193],"named":[114],"with":[117,171,176],"Visual":[118,123],"Transformers":[119,124],"(STGVT),":[120],"which":[121],"utilizes":[122],"extract":[126],"cross-modal":[127],"representations":[128],"video-sentence":[130,157],"matching":[131],"To":[135],"facilitate":[136],"task,":[138],"also":[140],"contribute":[141],"datasetThe":[144],"new":[145],"dataset":[146],"available":[148],"at":[149],"<uri":[150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/tzhhhh123/HC-STVG</uri>":[152],".":[153],"consisting":[154],"5,660":[156],"pairs":[158],"complex":[160],"multi-person":[161],"scenes.":[162],"Specifically,":[163],"each":[164],"lasts":[166],"20":[168],"seconds,":[169],"pairing":[170],"natural":[173],"query":[174],"sentence":[175],"average":[178],"17.25":[180],"words.":[181],"Extensive":[182],"experiments":[183],"are":[184],"conducted":[185],"dataset,":[188],"demonstrating":[189],"newly-proposed":[192],"outperforms":[194],"methods.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}