{"id":"https://openalex.org/W4411725806","doi":"https://doi.org/10.1109/iscas56072.2025.11043896","title":"A Unified SpatioTemporal Network with Structural Pruning for Video Action Recognition","display_name":"A Unified SpatioTemporal Network with Structural Pruning for Video Action Recognition","publication_year":2025,"publication_date":"2025-05-25","ids":{"openalex":"https://openalex.org/W4411725806","doi":"https://doi.org/10.1109/iscas56072.2025.11043896"},"language":"en","primary_location":{"id":"doi:10.1109/iscas56072.2025.11043896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11043896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5089318404","display_name":"Yang-Jie Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yang-Jie Chen","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Computer Science,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101014167","display_name":"Rashid Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Rashid Ali","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Computer Science,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019927566","display_name":"Hsu-Feng Hsiao","orcid":"https://orcid.org/0000-0003-3414-5622"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsu-Feng Hsiao","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Computer Science,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089318404"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16868928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9976999759674072,"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":0.9961000084877014,"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":0.7872889041900635},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7420018315315247},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.7301397323608398},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5844349265098572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5792118906974792},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41790980100631714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4128165543079376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3260788321495056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872889041900635},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7420018315315247},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.7301397323608398},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5844349265098572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5792118906974792},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41790980100631714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4128165543079376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3260788321495056},{"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/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas56072.2025.11043896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11043896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1944615693","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2126579184","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2616247523","https://openalex.org/W2625366777","https://openalex.org/W2948048211","https://openalex.org/W2963457877","https://openalex.org/W2981385151","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3168565360","https://openalex.org/W3175528717","https://openalex.org/W4386083031"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Video":[0],"action":[1],"recognition":[2],"poses":[3],"significant":[4],"challenges":[5],"in":[6],"capturing":[7],"and":[8,14,78,90,96,109],"integrating":[9],"the":[10,44,106,119],"complex":[11],"spatiotemporal":[12,55],"patterns":[13],"motion":[15],"dynamics":[16],"necessary":[17],"for":[18],"robust":[19],"understanding.":[20],"Despite":[21],"recent":[22],"advancements,":[23],"existing":[24],"deep":[25],"learning":[26],"approaches":[27],"often":[28],"struggle":[29],"to":[30,88],"efficiently":[31],"model":[32],"these":[33],"interactions":[34],"over":[35],"extended":[36],"temporal":[37,59,79],"ranges.":[38],"To":[39],"address":[40],"this,":[41],"we":[42,82],"propose":[43],"Unified":[45],"SpatioTemporal":[46],"Network":[47],"(USTN),":[48],"a":[49,70,84],"novel":[50],"framework":[51],"that":[52],"fuses":[53],"segment-level":[54],"features":[56],"with":[57,115],"long-range":[58],"difference":[60],"information.":[61],"By":[62],"strategically":[63],"employing":[64],"sparse":[65],"frame":[66],"sampling,":[67],"USTN":[68,113],"constructs":[69],"rich,":[71],"coarse-grained":[72],"representation":[73],"encapsulating":[74],"both":[75],"spatial":[76],"structure":[77],"evolution.":[80],"Furthermore,":[81],"introduce":[83],"structural":[85],"pruning":[86],"technique":[87],"identify":[89],"remove":[91],"redundant":[92],"parameters,":[93],"mitigating":[94],"overfitting":[95],"enhancing":[97],"computational":[98],"efficiency":[99],"without":[100],"compromising":[101],"performance.":[102],"Extensive":[103],"evaluations":[104],"on":[105],"challenging":[107],"UCF101":[108],"HMDB51":[110],"benchmarks,":[111],"using":[112],"instantiated":[114],"ResNet":[116],"backbones,":[117],"demonstrate":[118],"superiority":[120],"of":[121],"our":[122],"approach.":[123]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}