{"id":"https://openalex.org/W4394698843","doi":"https://doi.org/10.1109/tpami.2024.3387127","title":"STMixer: A One-Stage Sparse Action Detector","display_name":"STMixer: A One-Stage Sparse Action Detector","publication_year":2024,"publication_date":"2024-04-10","ids":{"openalex":"https://openalex.org/W4394698843","doi":"https://doi.org/10.1109/tpami.2024.3387127","pmid":"https://pubmed.ncbi.nlm.nih.gov/38598384"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3387127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3387127","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5101546460","display_name":"Wu Tao","orcid":"https://orcid.org/0009-0004-1028-6919"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107809156","display_name":"Mengqi Cao","orcid":"https://orcid.org/0009-0006-8108-0664"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Cao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808441","display_name":"Ziteng Gao","orcid":"https://orcid.org/0009-0005-6815-6209"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziteng Gao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436505","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0002-3674-7718"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101546460"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6207369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"46","issue":"10","first_page":"6842","last_page":"6857"},"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":0.9991000294685364,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7745488882064819},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6628245711326599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6457958221435547},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5501547455787659},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5270310044288635},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5243761539459229},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5211784243583679},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.49938058853149414},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49069011211395264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4818623960018158},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4302999973297119},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4238077700138092},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.42360007762908936},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3978058993816376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3200952708721161},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11973398923873901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745488882064819},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6628245711326599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6457958221435547},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5501547455787659},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5270310044288635},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5243761539459229},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5211784243583679},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49938058853149414},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49069011211395264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4818623960018158},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4238077700138092},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.42360007762908936},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3978058993816376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3200952708721161},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11973398923873901},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3387127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3387127","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38598384","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38598384","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1829964333","display_name":null,"funder_award_id":"020214380099","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G528746023","display_name":null,"funder_award_id":"61921006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6791897338","display_name":null,"funder_award_id":"62076119","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":100,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1536680647","https://openalex.org/W1797109199","https://openalex.org/W1861492603","https://openalex.org/W1923332106","https://openalex.org/W2034014085","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2519080876","https://openalex.org/W2549139847","https://openalex.org/W2565639579","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2622263826","https://openalex.org/W2883275382","https://openalex.org/W2883429621","https://openalex.org/W2884561390","https://openalex.org/W2895738954","https://openalex.org/W2908510526","https://openalex.org/W2949343965","https://openalex.org/W2955874753","https://openalex.org/W2962722947","https://openalex.org/W2962790054","https://openalex.org/W2962803561","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963529931","https://openalex.org/W2963563276","https://openalex.org/W2964072322","https://openalex.org/W2964207322","https://openalex.org/W2964241181","https://openalex.org/W2984287396","https://openalex.org/W2985693775","https://openalex.org/W2990503944","https://openalex.org/W3000279895","https://openalex.org/W3021385015","https://openalex.org/W3034572008","https://openalex.org/W3094702047","https://openalex.org/W3096609285","https://openalex.org/W3096824106","https://openalex.org/W3108226879","https://openalex.org/W3109173645","https://openalex.org/W3128626728","https://openalex.org/W3146455718","https://openalex.org/W3171169846","https://openalex.org/W3172752666","https://openalex.org/W3173407577","https://openalex.org/W3173459793","https://openalex.org/W3174480456","https://openalex.org/W3199093552","https://openalex.org/W3203086442","https://openalex.org/W3204116406","https://openalex.org/W3216270236","https://openalex.org/W4214516465","https://openalex.org/W4214589115","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4214627427","https://openalex.org/W4285028122","https://openalex.org/W4312241193","https://openalex.org/W4312343844","https://openalex.org/W4312446817","https://openalex.org/W4312508181","https://openalex.org/W4312509322","https://openalex.org/W4312560592","https://openalex.org/W4312593602","https://openalex.org/W4312692509","https://openalex.org/W4312769131","https://openalex.org/W4312770707","https://openalex.org/W4312772544","https://openalex.org/W4312848112","https://openalex.org/W4313057390","https://openalex.org/W4313155487","https://openalex.org/W4313169234","https://openalex.org/W4319299890","https://openalex.org/W4319300031","https://openalex.org/W4385245566","https://openalex.org/W4386057769","https://openalex.org/W4386076295","https://openalex.org/W6600983433","https://openalex.org/W6620707391","https://openalex.org/W6739622702","https://openalex.org/W6757817989","https://openalex.org/W6760424586","https://openalex.org/W6766978945","https://openalex.org/W6773433808","https://openalex.org/W6776881853","https://openalex.org/W6780226713","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6793267612","https://openalex.org/W6795140394","https://openalex.org/W6798038150","https://openalex.org/W6809665764","https://openalex.org/W6810265253","https://openalex.org/W6838845381"],"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/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Traditional":[0],"video":[1,154],"action":[2,31,62,69,110,181,186,204,209,212],"detectors":[3,63,195],"typically":[4],"adopt":[5],"the":[6,42,49,88,123,126,136,157,197],"two-stage":[7],"pipeline,":[8],"where":[9],"a":[10,105,115,130,143],"person":[11],"detector":[12,124],"is":[13,24,45],"first":[14],"employed":[15],"to":[16,26,52,67,151],"generate":[17],"actor":[18],"boxes":[19],"and":[20,39,41,83,152,159,183,191],"then":[21],"3D":[22],"RoIAlign":[23],"used":[25],"extract":[27],"actor-specific":[28],"features":[29,134,155],"for":[30,104,163,179,185,207],"recognition.":[32],"This":[33],"detection":[34,174,182,205,210],"paradigm":[35],"requires":[36],"multi-stage":[37],"training":[38],"inference,":[40],"feature":[43,81,118,145,165],"sampling":[44,82,119],"only":[46],"constrained":[47],"inside":[48],"box,":[50],"failing":[51],"effectively":[53],"leverage":[54],"richer":[55],"context":[56],"information":[57],"outside.":[58],"Recently,":[59],"several":[60],"query-based":[61,116],"have":[64],"been":[65],"proposed":[66],"predict":[68],"instances":[70],"in":[71,80],"an":[72],"end-to-end":[73],"manner.":[74],"However,":[75],"they":[76],"still":[77],"lack":[78],"adaptability":[79],"decoding,":[84],"thus":[85],"suffering":[86],"from":[87,135],"issues":[89],"of":[90,128,132],"inferior":[91],"performance":[92],"or":[93,211],"slower":[94],"convergence.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99,113,141,171],"propose":[100],"two":[101,173],"core":[102],"designs":[103],"more":[106],"flexible":[107],"one-stage":[108],"sparse":[109],"detector.":[111],"First,":[112],"present":[114],"adaptive":[117],"module,":[120,147],"which":[121,148],"endows":[122],"with":[125],"flexibility":[127],"mining":[129],"group":[131],"discriminative":[133],"entire":[137],"spatio-temporal":[138,203],"domain.":[139],"Second,":[140],"devise":[142],"decoupled":[144],"mixing":[146],"dynamically":[149],"attends":[150],"mixes":[153],"along":[156],"spatial":[158],"temporal":[160],"dimensions":[161],"respectively":[162],"better":[164],"decoding.":[166],"Based":[167],"on":[168,200],"these":[169],"designs,":[170],"instantiate":[172],"pipelines,":[175],"that":[176],"is,":[177],"STMixer-K":[178],"keyframe":[180,208],"STMixer-T":[184],"tubelet":[187],"detection.":[188,214],"Without":[189],"bells":[190],"whistles,":[192],"our":[193],"STMixer":[194],"obtain":[196],"state-of-the-art":[198],"results":[199],"five":[201],"challenging":[202],"benchmarks":[206],"tube":[213]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}