{"id":"https://openalex.org/W4320713023","doi":"https://doi.org/10.1109/tip.2023.3243525","title":"Sequence as a Whole: A Unified Framework for Video Action Localization With Long-Range Text Query","display_name":"Sequence as a Whole: A Unified Framework for Video Action Localization With Long-Range Text Query","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4320713023","doi":"https://doi.org/10.1109/tip.2023.3243525","pmid":"https://pubmed.ncbi.nlm.nih.gov/37022864"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3243525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3243525","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5033713097","display_name":"Yuting Su","orcid":"https://orcid.org/0000-0001-5165-204X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuting Su","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663684","display_name":"Weikang Wang","orcid":"https://orcid.org/0000-0001-9591-8559"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weikang Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021059","display_name":"Shuang Ma","orcid":"https://orcid.org/0000-0002-9870-5492"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang Ma","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"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":"Xiaokang Yang","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033713097"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.4443,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83610995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"1403","last_page":"1418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.992900013923645,"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":0.8142490386962891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5643610954284668},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.54449462890625},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.44720733165740967},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41505166888237},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41374915838241577},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32480570673942566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8142490386962891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5643610954284668},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.54449462890625},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44720733165740967},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41505166888237},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41374915838241577},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32480570673942566},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3243525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3243525","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37022864","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37022864","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G173205433","display_name":null,"funder_award_id":"U21B2024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G539172918","display_name":null,"funder_award_id":"62372337","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8785356685","display_name":null,"funder_award_id":"2021YJSB147","funder_id":"https://openalex.org/F4320336754","funder_display_name":"Tianjin Research Innovation Project for Postgraduate Students"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336754","display_name":"Tianjin Research Innovation Project for Postgraduate Students","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1905722737","https://openalex.org/W2031489346","https://openalex.org/W2034014085","https://openalex.org/W2250539671","https://openalex.org/W2412782625","https://openalex.org/W2519091744","https://openalex.org/W2605127024","https://openalex.org/W2798354744","https://openalex.org/W2799262584","https://openalex.org/W2876852810","https://openalex.org/W2890502146","https://openalex.org/W2894280539","https://openalex.org/W2894964039","https://openalex.org/W2904824998","https://openalex.org/W2948958195","https://openalex.org/W2961348656","https://openalex.org/W2963017553","https://openalex.org/W2963155035","https://openalex.org/W2963227409","https://openalex.org/W2963354481","https://openalex.org/W2963393391","https://openalex.org/W2963518342","https://openalex.org/W2963524571","https://openalex.org/W2963717374","https://openalex.org/W2964089981","https://openalex.org/W2965373594","https://openalex.org/W2970898753","https://openalex.org/W2976669726","https://openalex.org/W2981851019","https://openalex.org/W2983693499","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2997063389","https://openalex.org/W2997429269","https://openalex.org/W2998495542","https://openalex.org/W2998841681","https://openalex.org/W3003991937","https://openalex.org/W3034298080","https://openalex.org/W3034777757","https://openalex.org/W3034804856","https://openalex.org/W3035339529","https://openalex.org/W3035590142","https://openalex.org/W3035640828","https://openalex.org/W3035709993","https://openalex.org/W3096609285","https://openalex.org/W3101429639","https://openalex.org/W3105232955","https://openalex.org/W3110761028","https://openalex.org/W3121052081","https://openalex.org/W3127393268","https://openalex.org/W3159619744","https://openalex.org/W3166712493","https://openalex.org/W3174364033","https://openalex.org/W3175817778","https://openalex.org/W3177892185","https://openalex.org/W3178075329","https://openalex.org/W3199576129","https://openalex.org/W3204090293","https://openalex.org/W4205432963","https://openalex.org/W4221166385","https://openalex.org/W4226024706","https://openalex.org/W4250482878","https://openalex.org/W4294170691","https://openalex.org/W4312544061","https://openalex.org/W4312784228","https://openalex.org/W4313011746","https://openalex.org/W4385245566","https://openalex.org/W6760424586"],"related_works":["https://openalex.org/W2517104666","https://openalex.org/W2005437358","https://openalex.org/W1669643531","https://openalex.org/W2008656436","https://openalex.org/W2134924024","https://openalex.org/W2023558673","https://openalex.org/W2110230079","https://openalex.org/W1982826852","https://openalex.org/W2613186388","https://openalex.org/W1967061043"],"abstract_inverted_index":{"Comprehensive":[0],"understanding":[1],"of":[2,25,41,110,154],"video":[3,16,83,127,142,156,161,168,182],"content":[4],"requires":[5],"both":[6],"spatial":[7,121],"and":[8,34,89,115,123,136,166],"temporal":[9,54,124,163],"localization.":[10],"However,":[11],"there":[12],"lacks":[13],"a":[14,76,98],"unified":[15,77],"action":[17,157,183],"localization":[18,184],"framework,":[19],"which":[20,79,107],"hinders":[21],"the":[22,39,48,81,133,140,145,172,176],"coordinated":[23],"development":[24],"this":[26,69,72],"field.":[27],"Existing":[28],"3D":[29],"CNN":[30],"methods":[31,58],"take":[32],"fixed":[33],"limited":[35],"input":[36],"length":[37],"at":[38,191],"cost":[40],"ignoring":[42],"temporally":[43,116,146],"long-range":[44,88],"cross-modal":[45,62],"interaction.":[46],"On":[47],"other":[49],"hand,":[50],"despite":[51],"having":[52],"large":[53],"context,":[55],"existing":[56],"sequential":[57,85],"often":[59],"avoid":[60],"dense":[61,90],"interactions":[63],"for":[64],"complexity":[65],"reasons.":[66],"To":[67],"address":[68],"issue,":[70],"in":[71,84,93,126,179],"paper,":[73],"we":[74],"propose":[75],"framework":[78,174],"handles":[80],"whole":[82,141],"manner":[86],"with":[87,144],"visual-linguistic":[91],"interaction":[92],"an":[94],"end-to-end":[95],"manner.":[96],"Specifically,":[97],"lightweight":[99],"relevance":[100,111,134],"filtering":[101,112,135],"based":[102,113],"transformer":[103],"(Ref-Transformer)":[104],"is":[105,108],"designed,":[106],"composed":[109],"attention":[114],"expanded":[117,147],"MLP.":[118,148],"The":[119,186],"text-relevant":[120],"regions":[122],"clips":[125],"can":[128],"be":[129],"efficiently":[130],"highlighted":[131],"through":[132],"then":[137],"propagated":[138],"among":[139],"sequence":[143],"Extensive":[149],"experiments":[150],"on":[151],"three":[152],"sub-tasks":[153],"referring":[155,160,181],"localization,":[158],"i.e.,":[159],"segmentation,":[162],"sentence":[164],"grounding,":[165,169],"spatiotemporal":[167],"show":[170],"that":[171],"proposed":[173],"achieves":[175],"state-of-the-art":[177],"performance":[178],"all":[180],"tasks.":[185],"code":[187],"has":[188],"been":[189],"available":[190],"https://github.com/TJUMMG/SAW.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}