{"id":"https://openalex.org/W4387967991","doi":"https://doi.org/10.1145/3581783.3612455","title":"MTSN: Multiscale Temporal Similarity Network for Temporal Action Localization","display_name":"MTSN: Multiscale Temporal Similarity Network for Temporal Action Localization","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967991","doi":"https://doi.org/10.1145/3581783.3612455"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103227629","display_name":"Jin Xiao-dong","orcid":"https://orcid.org/0000-0002-0910-045X"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Jin","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-0910-045X","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101664915","display_name":"Taiping Zhang","orcid":"https://orcid.org/0000-0001-9891-4203"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiping Zhang","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-9891-4203","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2573","last_page":"2581"},"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":0.9983999729156494,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9829000234603882,"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":0.7564506530761719},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5917810797691345},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5742028951644897},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5623234510421753},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5423105955123901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384931564331055},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5030376315116882},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48573094606399536},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4602445960044861},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.43418553471565247},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42631298303604126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13725823163986206},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13107401132583618},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12539511919021606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564506530761719},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5917810797691345},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5742028951644897},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5623234510421753},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5423105955123901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384931564331055},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5030376315116882},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48573094606399536},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4602445960044861},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.43418553471565247},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42631298303604126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13725823163986206},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13107401132583618},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12539511919021606},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials 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},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5656631925","display_name":null,"funder_award_id":"62076043","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2193145675","https://openalex.org/W2336403884","https://openalex.org/W2529163075","https://openalex.org/W2597958930","https://openalex.org/W2604113307","https://openalex.org/W2766402183","https://openalex.org/W2884969173","https://openalex.org/W2955874753","https://openalex.org/W2962677524","https://openalex.org/W2962876901","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963951032","https://openalex.org/W2964121718","https://openalex.org/W2964214371","https://openalex.org/W2964274041","https://openalex.org/W2983918066","https://openalex.org/W2986407524","https://openalex.org/W2997706915","https://openalex.org/W2998582438","https://openalex.org/W3034623254","https://openalex.org/W3069380482","https://openalex.org/W3100481960","https://openalex.org/W3106250896","https://openalex.org/W3128626728","https://openalex.org/W3172347581","https://openalex.org/W3173459793","https://openalex.org/W3174569083","https://openalex.org/W3176641851","https://openalex.org/W3202076256","https://openalex.org/W3208474254","https://openalex.org/W4200630755","https://openalex.org/W4214589115","https://openalex.org/W4214736059","https://openalex.org/W4307922156","https://openalex.org/W4308529544","https://openalex.org/W4312300737","https://openalex.org/W4312349930","https://openalex.org/W4312508181","https://openalex.org/W4312560592","https://openalex.org/W4312658081","https://openalex.org/W4313050661"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W3203142394","https://openalex.org/W4390516098","https://openalex.org/W2788972299","https://openalex.org/W2498789492","https://openalex.org/W2521347458","https://openalex.org/W2161474341","https://openalex.org/W4249847449","https://openalex.org/W4302615923"],"abstract_inverted_index":{"Temporal":[0,59,130],"Action":[1],"Localization":[2],"(TAL)":[3],"aims":[4],"to":[5,40,136,156],"predict":[6],"the":[7,27,41,182,212,217],"categories":[8],"and":[9,23,48,76,96,150,170,179,188],"temporal":[10,46,77,98],"segments":[11],"of":[12,33,43,105,197,207],"all":[13],"action":[14,50,158],"instances":[15],"in":[16,26,125],"untrimmed":[17],"videos,":[18],"which":[19,69,154,210],"is":[20,134],"a":[21,63,89,126,176],"critical":[22],"challenging":[24],"task":[25],"video":[28],"understanding":[29],"field.":[30],"The":[31],"performances":[32],"existing":[34],"TAL":[35,167],"methods":[36],"remain":[37],"unsatisfactory,":[38],"due":[39],"lack":[42],"highly":[44],"effective":[45],"modeling":[47,75,99],"refined":[49],"proposal":[51],"decoding.":[52,79],"In":[53],"this":[54],"paper,":[55],"we":[56,81],"propose":[57],"Multiscale":[58],"Similarity":[60,131],"Network":[61],"(MTSN),":[62],"novel":[64],"one-stage":[65],"method":[66,174],"for":[67,216],"TAL,":[68],"mainly":[70],"benefits":[71],"from":[72],"dynamic":[73,127],"complementary":[74],"similarity":[78,146],"Specifically,":[80],"first":[82,218],"design":[83],"Dynamic":[84],"Complementary":[85],"Context":[86],"Aggregation":[87],"(DCCA),":[88],"Transformer-based":[90],"encoder.":[91],"DCCA":[92],"performs":[93],"both":[94],"long-range":[95],"short-range":[97,122],"through":[100,139],"different":[101],"interaction":[102],"range":[103],"types":[104],"attention":[106],"heads":[107],"at":[108],"each":[109],"feature":[110],"pyramid":[111],"level,":[112],"while":[113],"higher-level":[114],"semantic":[115],"representations":[116],"are":[117],"effectively":[118],"complemented":[119],"with":[120],"more":[121],"detail":[123],"information":[124],"fashion.":[128],"Moreover,":[129],"Mask":[132],"(TSM)":[133],"designed":[135],"generate":[137],"masks":[138],"an":[140,194,204],"optimized":[141],"globally-aware":[142],"decoding":[143],"process,":[144],"including":[145],"cross-modeling,":[147],"region-aware":[148],"optimization":[149],"multiscale":[151],"aggregated":[152],"residual,":[153],"leads":[155],"high-quality":[157],"proposals.":[159],"We":[160],"conduct":[161],"extensive":[162],"experiments":[163],"on":[164,190],"two":[165],"major":[166],"benchmarks:":[168],"THUMOS14":[169],"ActivityNet-1.3,":[171,201],"where":[172],"our":[173],"establishes":[175],"new":[177],"state-of-the-art":[178],"significantly":[180],"outperforms":[181],"previous":[183],"best":[184],"methods.":[185],"Without":[186],"bells":[187],"whistles,":[189],"THUMOS14,":[191],"MTSN":[192,202],"achieves":[193],"average":[195,205,214],"mAP":[196,206,215],"72.1%":[198],"(+5.3%).":[199],"On":[200],"reaches":[203],"40.7%":[208],"(+3.1%),":[209],"crosses":[211],"40%":[213],"time.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}