{"id":"https://openalex.org/W2769563757","doi":null,"title":"Multi-Level ResNets with Stacked SRUs for Action Recognition.","display_name":"Multi-Level ResNets with Stacked SRUs for Action Recognition.","publication_year":2017,"publication_date":"2017-11-22","ids":{"openalex":"https://openalex.org/W2769563757","mag":"2769563757"},"language":"en","primary_location":{"id":"mag:2769563757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1711.08238.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.08238.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052963418","display_name":"Zhenxing Zheng","orcid":"https://orcid.org/0000-0002-6749-4952","observed_orcids":["https://orcid.org/0000-0002-6749-4952"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenxing Zheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6749-4952","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054342134","display_name":"Gaoyun An","orcid":"https://orcid.org/0000-0002-2843-843X","observed_orcids":["https://orcid.org/0000-0002-2843-843X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaoyun An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112109951","display_name":"Qiuqi Ruan","orcid":"https://orcid.org/0000-0001-8107-7365","observed_orcids":["https://orcid.org/0000-0001-8107-7365"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuqi Ruan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8107-7365","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.9700000286102295},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.8109999895095825},{"id":"https://openalex.org/keywords/simple-recurrent-unit","display_name":"simple recurrent unit","score":0.8999999761581421},{"id":"https://openalex.org/keywords/multilevel-feature-fusion","display_name":"multi-level feature fusion","score":0.8550000190734863},{"id":"https://openalex.org/keywords/temporal-dynamics","display_name":"temporal dynamics","score":0.578000009059906},{"id":"https://openalex.org/keywords/rgb-video","display_name":"RGB video","score":0.43299999833106995},{"id":"https://openalex.org/keywords/hmdb51","display_name":"HMDB51","score":0.9620000123977661},{"id":"https://openalex.org/keywords/ucf101","display_name":"UCF101","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050987720489502},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7203984260559082},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6480342149734497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6090987324714661},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5531896948814392},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.538449764251709},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5069546699523926},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5027809143066406},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.462137371301651},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44337329268455505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3946114480495453},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18096080422401428},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07502013444900513},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2769563757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1711.08238.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2769563757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1711.08238.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1598796236","https://openalex.org/W1686810756","https://openalex.org/W1871385855","https://openalex.org/W1920196880","https://openalex.org/W1947481528","https://openalex.org/W1993991024","https://openalex.org/W2020163092","https://openalex.org/W2050964073","https://openalex.org/W2064675550","https://openalex.org/W2105101328","https://openalex.org/W2106996050","https://openalex.org/W2108598243","https://openalex.org/W2111308925","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2125930537","https://openalex.org/W2126574503","https://openalex.org/W2126579184","https://openalex.org/W2128715914","https://openalex.org/W2147625498","https://openalex.org/W2156303437","https://openalex.org/W2161969291","https://openalex.org/W2163292664","https://openalex.org/W2194775991","https://openalex.org/W2284126738","https://openalex.org/W2342662179","https://openalex.org/W2545924794","https://openalex.org/W2561238782","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2783883100","https://openalex.org/W2912879506","https://openalex.org/W7062178729","https://openalex.org/W2729122095","https://openalex.org/W3201756401","https://openalex.org/W2553594924","https://openalex.org/W2510318047","https://openalex.org/W4206913723","https://openalex.org/W2997180306","https://openalex.org/W4226056201"],"abstract_inverted_index":{"Inspiring":[0],"by":[1,92],"the":[2,5,66,76,112,126,155,171],"fact":[3],"that":[4,41,152],"enormous":[6],"breakthrough":[7],"convolutional":[8],"networks":[9,32],"consistently":[10],"make":[11],"in":[12,60],"image":[13],"classification":[14],"while":[15],"most":[16],"existing":[17],"works":[18],"are":[19,125],"either":[20],"low":[21],"efficiency":[22],"or":[23],"hard":[24],"to":[25,98,120,128,131],"optimized,":[26],"we":[27,85,124],"propose":[28],"multiple":[29],"level":[30,118],"residual":[31],"with":[33,103,170],"stacked":[34,50],"simple":[35],"recurrent":[36],"units(R-SRU)":[37],"model":[38],"trained":[39],"end-to-end":[40],"ResNets":[42,93],"learn":[43,52],"spatial":[44,61],"information":[45],"from":[46,55],"frame":[47],"appearances":[48],"and":[49,62,94,146,166,177],"SRUs":[51,102],"temporal":[53],"dynamics":[54],"video":[56],"sequences,":[57],"both":[58],"deep":[59],"temporal.":[63],"We":[64],"investigate":[65],"effect":[67],"of":[68,79,114,116,136,157],"diverse":[69],"hyper-parameter":[70],"settings":[71],"aiming":[72],"at":[73],"recommending":[74],"researchers":[75],"better":[77],"choice":[78],"hyper-parameters":[80],"for":[81],"using":[82],"SRUs.":[83],"Additionally,":[84],"compare":[86],"low-,":[87],"mid-,":[88],"high-level":[89],"features":[90,97,119],"produced":[91],"combine":[95],"multi-level":[96],"pass":[99],"it":[100],"through":[101],"various":[104],"time":[105],"pooling":[106],"manners":[107],"after":[108],"that,":[109],"experimentally":[110],"demonstrating":[111],"extent":[113],"contribution":[115],"each":[117],"action":[121],"recognition.":[122],"Specifically,":[123],"first":[127],"apply":[129],"SRU":[130],"distinguish":[132],"actions.":[133],"A":[134],"series":[135],"experiments":[137],"is":[138],"carried":[139],"out":[140],"on":[141,175,179],"two":[142],"standard":[143],"benchmarks:":[144],"HMDB-51":[145,176],"UCF-101":[147],"dataset.":[148],"Experimental":[149],"results":[150],"illustrate":[151],"R-SRU":[153],"outperforms":[154],"majority":[156],"methods":[158],"which":[159],"only":[160],"take":[161],"RGB":[162],"data":[163],"as":[164],"input":[165],"obtain":[167],"competitive":[168],"performances":[169],"state-of-the-art,":[172],"achieving":[173],"51.31%":[174],"81.38%":[178],"UCF-101.":[180]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2017-12-04T00:00:00"}