{"id":"https://openalex.org/W4405717503","doi":"https://doi.org/10.1109/tcsvt.2024.3521454","title":"STPM: Spatial-Temporal Token Pruning and Merging for Complex Activity Recognition","display_name":"STPM: Spatial-Temporal Token Pruning and Merging for Complex Activity Recognition","publication_year":2024,"publication_date":"2024-12-23","ids":{"openalex":"https://openalex.org/W4405717503","doi":"https://doi.org/10.1109/tcsvt.2024.3521454"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3521454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3521454","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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":null,"display_name":"Yumeng Su","orcid":"https://orcid.org/0009-0004-3433-9771"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumeng Su","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-3433-9771","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102020945","display_name":"Jiachao Zhang","orcid":"https://orcid.org/0000-0002-3124-9461"},"institutions":[{"id":"https://openalex.org/I2799736854","display_name":"Nanjing Institute of Technology","ror":"https://ror.org/00n6txq60","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799736854"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachao Zhang","raw_affiliation_strings":["Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3124-9461","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology, Nanjing, China","institution_ids":["https://openalex.org/I2799736854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716371","display_name":"Rui Yan","orcid":"https://orcid.org/0000-0002-0694-9458"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":["Department of Computer Science and Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0694-9458","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069405687","display_name":"Pengpeng Li","orcid":"https://orcid.org/0000-0001-7563-601X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengpeng Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7563-601X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084688255","display_name":"Guo-Sen Xie","orcid":"https://orcid.org/0000-0002-5487-9845"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-Sen Xie","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5487-9845","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbo Shu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4902-4663","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22033031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":"6","first_page":"5407","last_page":"5418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9955999851226807,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9955999851226807,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9794999957084656,"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":0.9498999714851379,"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/security-token","display_name":"Security token","score":0.712719202041626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783034205436707},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5906893014907837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.533517062664032},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4710398018360138},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.17536094784736633}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.712719202041626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783034205436707},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5906893014907837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.533517062664032},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4710398018360138},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17536094784736633},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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:10.1109/tcsvt.2024.3521454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3521454","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2425268315","display_name":null,"funder_award_id":"62002160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3938807848","display_name":null,"funder_award_id":"62276134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5512729199","display_name":null,"funder_award_id":"62222207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5558408212","display_name":"\u9762\u5411\u590d\u6742\u573a\u666f\u7684\u7fa4\u4f53\u6d3b\u52a8\u591a\u7c92\u5ea6\u89e3\u6790\u7814\u7a76","funder_award_id":"62072245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5950360714","display_name":null,"funder_award_id":"BK20211520","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8202567050","display_name":"\u4f4e\u8ba1\u7b97\u5f00\u9500\u7684\u9ad8\u901a\u91cf\u56fe\u50cf\u5904\u7406\u7b97\u6cd5\u7814\u7a76","funder_award_id":"62072238","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W2126579184","https://openalex.org/W2507009361","https://openalex.org/W2963091558","https://openalex.org/W2990152177","https://openalex.org/W2998776895","https://openalex.org/W3034572008","https://openalex.org/W3035303837","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3126195189","https://openalex.org/W3126721948","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3160694286","https://openalex.org/W3163465952","https://openalex.org/W3177141386","https://openalex.org/W3177500196","https://openalex.org/W3183430956","https://openalex.org/W3194557739","https://openalex.org/W3203925315","https://openalex.org/W3205497712","https://openalex.org/W3214466318","https://openalex.org/W4214508443","https://openalex.org/W4214516465","https://openalex.org/W4214588794","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4214893857","https://openalex.org/W4221167396","https://openalex.org/W4224293326","https://openalex.org/W4226294111","https://openalex.org/W4226407477","https://openalex.org/W4283825932","https://openalex.org/W4290717053","https://openalex.org/W4292347911","https://openalex.org/W4295308583","https://openalex.org/W4296437558","https://openalex.org/W4297697565","https://openalex.org/W4302275239","https://openalex.org/W4312349914","https://openalex.org/W4312509967","https://openalex.org/W4312530435","https://openalex.org/W4312560592","https://openalex.org/W4312594468","https://openalex.org/W4312947882","https://openalex.org/W4362014679","https://openalex.org/W4379382445","https://openalex.org/W4380032357","https://openalex.org/W4380303582","https://openalex.org/W4381233075","https://openalex.org/W4381886216","https://openalex.org/W4385245566","https://openalex.org/W4385259380","https://openalex.org/W4387682352","https://openalex.org/W4390872092","https://openalex.org/W4393906060","https://openalex.org/W4394625520","https://openalex.org/W4402716428","https://openalex.org/W4402727186","https://openalex.org/W4402916234","https://openalex.org/W6776048684","https://openalex.org/W6784094891","https://openalex.org/W6791705549","https://openalex.org/W6796494063","https://openalex.org/W6797399245","https://openalex.org/W6846577953","https://openalex.org/W6869080426"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Lightweight":[0],"video":[1,111,187],"representation":[2],"techniques":[3],"have":[4],"advanced":[5],"significantly":[6],"for":[7,36,98],"simple":[8],"activity":[9,21],"recognition,":[10],"but":[11],"they":[12],"still":[13],"encounter":[14],"several":[15],"issues":[16],"when":[17],"applied":[18],"to":[19,41,67,71,124,144,159],"complex":[20,99],"recognition:":[22],"1)":[23],"The":[24],"presence":[25],"of":[26,54],"numerous":[27],"individuals":[28],"and":[29,87,92,121,156,162,168,175,192],"varying":[30],"spatial":[31,108,161],"positions":[32],"makes":[33],"it":[34],"difficult":[35],"traditional":[37],"token":[38,146,164],"pruning":[39,65],"methods":[40],"maintain":[42,59],"accuracy.":[43],"2)":[44],"Simply":[45],"discarding":[46],"entire":[47],"frames":[48,75],"may":[49],"result":[50],"in":[51,74],"the":[52,63,142],"loss":[53],"crucial":[55],"clues.":[56],"3)":[57],"To":[58,80],"parallel":[60],"computing,":[61],"applying":[62],"same":[64],"rate":[66],"every":[68],"frame":[69],"leads":[70],"significant":[72],"redundancy":[73],"with":[76],"low":[77],"information":[78],"content.":[79],"this":[81],"end,":[82],"we":[83],"propose":[84],"a":[85,106],"lightweight":[86],"novel":[88],"Spatial-Temporal":[89],"Token":[90],"Pruning":[91],"Merging":[93],"(STPM)":[94],"framework,":[95],"specifically":[96],"designed":[97],"action":[100],"videos":[101],"where":[102],"human":[103],"actors":[104],"occupy":[105],"small":[107],"resolution":[109],"within":[110,141],"frames.":[112],"Our":[113,194],"framework":[114,195],"considers":[115],"two":[116],"critical":[117],"factors:":[118],"semantic":[119,129,173],"importance":[120],"spatial-temporal":[122,149],"redundancy,":[123,150],"further":[125],"reduce":[126],"overhead.":[127],"For":[128,148],"importance,":[130],"STPM":[131,151],"captures":[132],"class-specific":[133],"attention":[134,158],"scores":[135],"by":[136],"learning":[137],"multiple":[138],"class":[139],"tokens":[140],"transformer":[143,188],"guide":[145],"pruning.":[147],"employs":[152],"an":[153],"anchor":[154],"graph":[155],"temporal":[157,163,169],"perform":[160],"merging,":[165],"preserving":[166],"appearance":[167],"cues":[170],"while":[171,199],"eliminating":[172],"duplication":[174],"redundancy.":[176],"We":[177],"conduct":[178],"extensive":[179],"experiments":[180],"on":[181],"JRDB-PAR":[182],"primarily":[183],"using":[184],"recently":[185],"introduced":[186],"backbones,":[189],"e.g.,":[190],"MViT":[191],"ViT.":[193],"achieves":[196],"similar":[197],"results":[198],"requiring":[200],"40%":[201],"less":[202],"computation.":[203]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
