{"id":"https://openalex.org/W3208245486","doi":null,"title":"Deep Feature Fusion for Video-Based Action Recognition","display_name":"Deep Feature Fusion for Video-Based Action Recognition","publication_year":2020,"publication_date":"2020-04-10","ids":{"openalex":"https://openalex.org/W3208245486","mag":"3208245486"},"language":"en","primary_location":{"id":"pmh:oai:oaktrust.library.tamu.edu:1969.1/191594","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1969.1/191594","pdf_url":"https://hdl.handle.net/1969.1/191594","source":{"id":"https://openalex.org/S4306400291","display_name":"OakTrust (Texas A&M University Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I91045830","host_organization_name":"Texas A&M University","host_organization_lineage":["https://openalex.org/I91045830"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1969.1/191594","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100349429","display_name":"Cheng Cheng","orcid":"https://orcid.org/0009-0000-1671-0363","observed_orcids":["https://orcid.org/0009-0000-1671-0363","https://orcid.org/0000-0002-8271-3367","https://orcid.org/0009-0009-9070-870X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cheng Cheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0000-1671-0363","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100349429"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/video-action-recognition","display_name":"video action recognition","score":0.8659999966621399},{"id":"https://openalex.org/keywords/3d-convolutional-neural-networks","display_name":"3D convolutional neural networks","score":0.9169999957084656},{"id":"https://openalex.org/keywords/feature-fusion","display_name":"feature fusion","score":0.734000027179718},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.6600000262260437},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.5540000200271606},{"id":"https://openalex.org/keywords/two-stage-framework","display_name":"two-stage framework","score":0.7860000133514404},{"id":"https://openalex.org/keywords/video-representation-learning","display_name":"video representation learning","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6925199627876282},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5679901838302612},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5615783333778381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.560771107673645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.507654070854187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47690534591674805},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4483930170536041},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:oaktrust.library.tamu.edu:1969.1/191594","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1969.1/191594","pdf_url":"https://hdl.handle.net/1969.1/191594","source":{"id":"https://openalex.org/S4306400291","display_name":"OakTrust (Texas A&M University Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I91045830","host_organization_name":"Texas A&M University","host_organization_lineage":["https://openalex.org/I91045830"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"mag:3208245486","doi":null,"is_oa":false,"landing_page_url":"https://oaktrust.library.tamu.edu/handle/1969.1/191594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:oaktrust.library.tamu.edu:1969.1/191594","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1969.1/191594","pdf_url":"https://hdl.handle.net/1969.1/191594","source":{"id":"https://openalex.org/S4306400291","display_name":"OakTrust (Texas A&M University Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I91045830","host_organization_name":"Texas A&M University","host_organization_lineage":["https://openalex.org/I91045830"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3208245486.pdf","grobid_xml":"https://content.openalex.org/works/W3208245486.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1686810756","https://openalex.org/W2619947201","https://openalex.org/W2745519816"],"related_works":["https://openalex.org/W2751445731","https://openalex.org/W2909814735","https://openalex.org/W7125900779","https://openalex.org/W2978283562","https://openalex.org/W2986702709","https://openalex.org/W3082283937","https://openalex.org/W4399610585","https://openalex.org/W2581582378","https://openalex.org/W237546731","https://openalex.org/W4366085748"],"abstract_inverted_index":{"3-Dimensional":[0],"Convolutional":[1],"Neural":[2],"Networks":[3],"(3D":[4],"ConvNets)":[5],"have":[6,34],"been":[7,35],"adopted":[8],"for":[9,156],"videobased":[10],"action":[11,167,196],"recognition":[12,197],"task":[13],"recently.":[14],"Many":[15],"3D":[16,59,109,127,180],"ConvNets,":[17],"such":[18],"as":[19,62,111],"C3D,":[20],"I3D,":[21],"and":[22,26,136,186],"Res3D,":[23],"have\\nbeen":[24],"proposed":[25],"achieved":[27],"great":[28],"success.":[29],"The":[30],"model":[31,47,61,193],"ensemble":[32,48],"techniques":[33],"very":[36],"successful":[37],"in":[38,52,146],"achieving":[39],"better":[40,76],"performance":[41,77,189],"over":[42],"a":[43,63,89,112,139,183],"single":[44,58,179],"model.":[45],"But":[46],"could":[49],"not":[50],"be\\nadopted":[51],"this":[53],"case":[54],"given":[55],"that":[56,174],"the":[57,85,98,102,123,132,142,147,191],"ConvNets":[60,95,128],"base":[64],"learner":[65],"is":[66],"unrealistic.":[67],"It\\nremains":[68],"an":[69],"open":[70],"question":[71],"about":[72],"how":[73],"to":[74,92,115,130,163,190],"achieve":[75],"by":[78,182],"leveraging":[79],"multiple":[80],"3D\\nConvNets":[81],"models.":[82],"To":[83],"solve":[84],"problem,":[86],"we":[87,105],"present":[88],"two-stage":[90],"framework":[91,176],"combine":[93],"multiple\\n3D":[94],"models":[96,129],"at":[97],"feature":[99,113],"level.":[100],"In":[101],"first":[103],"stage,":[104],"treat":[106],"each":[107],"pretrained":[108],"ConvNets\\nmodel":[110,181],"extractor":[114],"extract":[116],"features":[117,158],"from":[118,160,169],"raw":[119,170],"videos.":[120,171],"We":[121,150,172],"fuse":[122],"extracted":[124],"features\\nof":[125],"different":[126,161],"form":[131],"new":[133,143],"video":[134,144],"representation":[135,145],"then":[137],"train":[138],"classifier\\nbased":[140],"on":[141,194],"second":[148],"stage.":[149],"explore":[151],"several":[152],"widely-used":[153],"feature\\nfusion":[154],"methods":[155],"deep":[157],"learned":[159],"models,":[162],"learn":[164],"more":[165],"robust":[166],"representations":[168],"show":[173],"our":[175],"outperforms":[177],"any":[178],"large":[184],"margin":[185],"exhibits":[187],"comparable":[188],"state-of-the-art":[192],"two\\nvideo":[195],"benchmarks.":[198]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-08T00:00:00"}