{"id":"https://openalex.org/W4392904150","doi":"https://doi.org/10.1109/icassp48485.2024.10447413","title":"Spatio-Temporal Action Detection with a Motion Sense and Semantic Correction Framework","display_name":"Spatio-Temporal Action Detection with a Motion Sense and Semantic Correction Framework","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904150","doi":"https://doi.org/10.1109/icassp48485.2024.10447413"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447413","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100419847","display_name":"Yong Zhang","orcid":"https://orcid.org/0000-0003-1024-5741"},"institutions":[{"id":"https://openalex.org/I3018263800","display_name":"Huzhou University","ror":"https://ror.org/04mvpxy20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3018263800"]},{"id":"https://openalex.org/I153374732","display_name":"Liaoning Normal University","ror":"https://ror.org/04c3cgg32","country_code":"CN","type":"education","lineage":["https://openalex.org/I153374732"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yong Zhang","raw_affiliation_strings":["Huzhou University,School of Information Engineering,China","School of Computer and Information Technology, Liaoning Normal University, China","School of Information Engineering, Huzhou University, China"],"affiliations":[{"raw_affiliation_string":"Huzhou University,School of Information Engineering,China","institution_ids":["https://openalex.org/I3018263800"]},{"raw_affiliation_string":"School of Computer and Information Technology, Liaoning Normal University, China","institution_ids":["https://openalex.org/I153374732"]},{"raw_affiliation_string":"School of Information Engineering, Huzhou University, China","institution_ids":["https://openalex.org/I3018263800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111286439","display_name":"Chunan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I3018263800","display_name":"Huzhou University","ror":"https://ror.org/04mvpxy20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3018263800"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunan Yu","raw_affiliation_strings":["Huzhou University,School of Information Engineering,China","School of Information Engineering, Huzhou University, China"],"affiliations":[{"raw_affiliation_string":"Huzhou University,School of Information Engineering,China","institution_ids":["https://openalex.org/I3018263800"]},{"raw_affiliation_string":"School of Information Engineering, Huzhou University, China","institution_ids":["https://openalex.org/I3018263800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062229422","display_name":"Chenglong Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I3018263800","display_name":"Huzhou University","ror":"https://ror.org/04mvpxy20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3018263800"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Fu","raw_affiliation_strings":["Huzhou University,School of Information Engineering,China","School of Information Engineering, Huzhou University, China"],"affiliations":[{"raw_affiliation_string":"Huzhou University,School of Information Engineering,China","institution_ids":["https://openalex.org/I3018263800"]},{"raw_affiliation_string":"School of Information Engineering, Huzhou University, China","institution_ids":["https://openalex.org/I3018263800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698140","display_name":"Yuanqi Hu","orcid":"https://orcid.org/0000-0001-9179-6603"},"institutions":[{"id":"https://openalex.org/I3018263800","display_name":"Huzhou University","ror":"https://ror.org/04mvpxy20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3018263800"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqi Hu","raw_affiliation_strings":["Huzhou University,School of Information Engineering,China","School of Information Engineering, Huzhou University, China"],"affiliations":[{"raw_affiliation_string":"Huzhou University,School of Information Engineering,China","institution_ids":["https://openalex.org/I3018263800"]},{"raw_affiliation_string":"School of Information Engineering, Huzhou University, China","institution_ids":["https://openalex.org/I3018263800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057492564","display_name":"Ying Zang","orcid":"https://orcid.org/0000-0002-1361-1500"},"institutions":[{"id":"https://openalex.org/I3018263800","display_name":"Huzhou University","ror":"https://ror.org/04mvpxy20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3018263800"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zang","raw_affiliation_strings":["Huzhou University,School of Information Engineering,China","School of Information Engineering, Huzhou University, China"],"affiliations":[{"raw_affiliation_string":"Huzhou University,School of Information Engineering,China","institution_ids":["https://openalex.org/I3018263800"]},{"raw_affiliation_string":"School of Information Engineering, Huzhou University, China","institution_ids":["https://openalex.org/I3018263800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100419847"],"corresponding_institution_ids":["https://openalex.org/I153374732","https://openalex.org/I3018263800"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02702534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3645","last_page":"3649"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541683912277222},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6477616429328918},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6418100595474243},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6417815685272217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6337866187095642},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5900471806526184},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5889856219291687},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.49967098236083984},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.49290990829467773},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4557986855506897},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41932862997055054},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38594338297843933},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1066802442073822},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.08708345890045166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541683912277222},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6477616429328918},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6418100595474243},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6417815685272217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6337866187095642},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5900471806526184},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5889856219291687},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.49967098236083984},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.49290990829467773},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4557986855506897},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41932862997055054},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38594338297843933},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1066802442073822},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.08708345890045166},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447413","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[],"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":26,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2947454602","https://openalex.org/W2949343965","https://openalex.org/W2962790054","https://openalex.org/W2963820951","https://openalex.org/W2981808500","https://openalex.org/W2985693775","https://openalex.org/W2990503944","https://openalex.org/W3034572008","https://openalex.org/W3096824106","https://openalex.org/W3108226879","https://openalex.org/W3109173645","https://openalex.org/W3173407577","https://openalex.org/W3201233545","https://openalex.org/W3204116406","https://openalex.org/W4312509322","https://openalex.org/W4319299890","https://openalex.org/W4321012180","https://openalex.org/W4385815585","https://openalex.org/W4386076325","https://openalex.org/W4402753877","https://openalex.org/W6600983433","https://openalex.org/W6849456419","https://openalex.org/W6851858537"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Accurately":[0],"distinguishing":[1],"between":[2,73,106],"action-related":[3],"features":[4,7,51,77,107],"and":[5,18,34,56,75,111,134],"non-action-related":[6],"is":[8,65,101],"crucial":[9],"in":[10,78,145],"spatio-temporal":[11,147],"action":[12,74,148],"detection":[13,48,149],"tasks.":[14,150],"Additionally,":[15],"the":[16,70,79,86,119,122,139,142],"calibration":[17],"fusion":[19],"of":[20,89,108,121,141],"information":[21,90,115],"across":[22,91],"different":[23,92],"modalities":[24,110],"remain":[25],"challenging.":[26],"This":[27],"paper":[28],"proposes":[29],"a":[30],"novel":[31],"Motion":[32,61],"Sense":[33,62],"Semantic":[35,96],"Correction":[36,97],"framework":[37,45,144],"(MS-SC)":[38],"to":[39,67,103],"address":[40],"these":[41],"issues.":[42],"The":[43,136],"MS-SC":[44,123,143],"achieves":[46],"accurate":[47],"by":[49],"fusing":[50],"from":[52],"images":[53],"(spatial":[54],"dimension)":[55],"videos":[57],"(spatio-temporal":[58],"dimension).":[59],"A":[60],"Module":[63,99],"(MSM)":[64],"proposed":[66],"significantly":[68],"increase":[69],"feature":[71,83],"distance":[72],"non-action":[76],"semantic":[80],"space,":[81],"enhancing":[82],"discriminability.":[84],"Considering":[85],"complementary":[87,114],"nature":[88],"modalities,":[93],"an":[94],"efficient":[95],"Fusion":[98],"(SFM)":[100],"introduced":[102],"facilitate":[104],"interaction":[105],"distinct":[109],"maximize":[112],"their":[113],"integration.":[116],"To":[117],"evaluate":[118],"performance":[120],"framework,":[124],"extensive":[125],"experiments":[126],"were":[127],"conducted":[128],"on":[129],"two":[130],"challenging":[131],"datasets,":[132],"UCF101-24":[133],"AVA.":[135],"results":[137],"demonstrate":[138],"effectiveness":[140],"handling":[146]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
