{"id":"https://openalex.org/W4389169640","doi":"https://doi.org/10.1109/tmm.2023.3338082","title":"Gated Multi-Scale Transformer for Temporal Action Localization","display_name":"Gated Multi-Scale Transformer for Temporal Action Localization","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4389169640","doi":"https://doi.org/10.1109/tmm.2023.3338082"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3338082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3338082","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5100602678","display_name":"Jin Yang","orcid":"https://orcid.org/0000-0001-9625-7449"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jin Yang","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, Xi'an Jiaotong University, Xi'an, Shaanxi, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101947241","display_name":"Ping Wei","orcid":"https://orcid.org/0000-0002-8535-9527"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Wei","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, Xi'an Jiaotong University, Xi'an, Shaanxi, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108920560","display_name":"Ziyang Ren","orcid":"https://orcid.org/0009-0008-8159-4096"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ren","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, Xi'an Jiaotong University, Xi'an, Shaanxi, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, Xi'an Jiaotong University, Xi'an, Shaanxi, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center of Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100602678"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.8643,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76245708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"5705","last_page":"5717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.989300012588501,"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":0.8543113470077515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5699772238731384},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5613934993743896},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48470187187194824},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4845685064792633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4553067088127136},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42247533798217773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41845250129699707},{"id":"https://openalex.org/keywords/temporal-database","display_name":"Temporal database","score":0.41187992691993713},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36976879835128784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543113470077515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5699772238731384},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5613934993743896},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48470187187194824},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4845685064792633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4553067088127136},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42247533798217773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41845250129699707},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.41187992691993713},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36976879835128784},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3338082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3338082","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G2482485774","display_name":null,"funder_award_id":"U23B2060","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1498368596","https://openalex.org/W1927052826","https://openalex.org/W1985028918","https://openalex.org/W1988650444","https://openalex.org/W2336403884","https://openalex.org/W2416798379","https://openalex.org/W2471143248","https://openalex.org/W2565639579","https://openalex.org/W2593722617","https://openalex.org/W2755876276","https://openalex.org/W2913397815","https://openalex.org/W2948048211","https://openalex.org/W2952435096","https://openalex.org/W2963524571","https://openalex.org/W2963857746","https://openalex.org/W2964008341","https://openalex.org/W2964121718","https://openalex.org/W2964214371","https://openalex.org/W2964274041","https://openalex.org/W2972073579","https://openalex.org/W2982770724","https://openalex.org/W2983918066","https://openalex.org/W2986407524","https://openalex.org/W2990503944","https://openalex.org/W2990763144","https://openalex.org/W2991089415","https://openalex.org/W2994356318","https://openalex.org/W2997314266","https://openalex.org/W2997706915","https://openalex.org/W3015468748","https://openalex.org/W3034623254","https://openalex.org/W3034971973","https://openalex.org/W3035251589","https://openalex.org/W3042006680","https://openalex.org/W3069380482","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3106041614","https://openalex.org/W3107128832","https://openalex.org/W3110997624","https://openalex.org/W3120494681","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3168101492","https://openalex.org/W3172347581","https://openalex.org/W3173459793","https://openalex.org/W3174569083","https://openalex.org/W3176444885","https://openalex.org/W3197682865","https://openalex.org/W3202076256","https://openalex.org/W3205786327","https://openalex.org/W3207409917","https://openalex.org/W3207758636","https://openalex.org/W4214614183","https://openalex.org/W4230270698","https://openalex.org/W4310015215","https://openalex.org/W4312372834","https://openalex.org/W4312508181","https://openalex.org/W4312658081","https://openalex.org/W4312774595","https://openalex.org/W4312944418","https://openalex.org/W4323065192","https://openalex.org/W4385245566","https://openalex.org/W4387885776","https://openalex.org/W6631190155","https://openalex.org/W6771062828","https://openalex.org/W6776048684","https://openalex.org/W6784094891","https://openalex.org/W6796237581","https://openalex.org/W6841287799","https://openalex.org/W6849990444"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2378211422","https://openalex.org/W2110523656","https://openalex.org/W1482209366"],"abstract_inverted_index":{"Temporal":[0],"action":[1,45],"localization":[2],"(TAL)":[3],"is":[4,51,108,186],"a":[5,36,117],"critical":[6],"task":[7],"in":[8],"video":[9],"understanding.":[10],"Effectively":[11],"utilizing":[12],"multi-scale":[13,39],"information":[14,58],"and":[15,55,105,140,163],"handling":[16],"interactions":[17],"across":[18],"various":[19],"scales":[20,71],"have":[21],"consistently":[22],"posed":[23],"challenging":[24,132],"issues":[25],"within":[26],"the":[27,57,64,77,84,124,170,179,182],"realm":[28],"of":[29,66,151,181],"TAL.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35],"novel":[37],"gated":[38,48],"Transformer":[40],"model":[41],"(TransGMC)":[42],"for":[43,110,122],"temporal":[44,70,82,92,113],"localization.":[46],"A":[47,94],"control":[49],"mechanism":[50],"designed":[52],"to":[53],"filter":[54],"aggregate":[56],"at":[59,68,80,90,188],"different":[60,69],"scales,":[61],"by":[62],"which":[63,167],"contributions":[65],"contexts":[67,87],"are":[72,88],"well":[73],"characterized.":[74],"To":[75],"enhance":[76],"feature":[78],"representation":[79],"each":[81,91],"scale,":[83],"rich":[85],"global-local":[86],"extracted":[89],"scale.":[93],"cascade":[95],"attention":[96,104,107],"module":[97],"that":[98],"contains":[99],"two":[100,136,141],"seamlessly":[101],"integrated":[102],"channel":[103],"moment":[106],"proposed":[109,183],"capturing":[111],"global":[112],"contexts.":[114],"We":[115,127],"utilize":[116],"new":[118],"regression":[119],"loss":[120],"function":[121],"locating":[123],"time":[125],"boundaries.":[126],"conducted":[128],"experiments":[129],"on":[130,153,156,160,165],"four":[131],"benchmark":[133],"datasets,":[134],"including":[135],"third-person":[137],"view":[138,143],"datasets":[139],"first-person":[142],"datasets.":[144],"Our":[145],"method":[146],"achieves":[147],"an":[148],"average":[149],"mAP":[150],"67.5%":[152],"THUMOS14,":[154],"36.1%":[155],"ActivityNet":[157],"v1.3,":[158],"24.9%":[159],"EPIC-Kitchens":[161],"100,":[162],"23.2%":[164],"Ego4D,":[166],"all":[168],"outperform":[169],"previous":[171],"state-of-the-arts":[172],"methods.":[173],"Extensive":[174],"ablation":[175],"studies":[176],"also":[177],"validate":[178],"effectiveness":[180],"method.":[184],"Code":[185],"available":[187],"https://github.com/EdenGabriel/TransGMC.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}