{"id":"https://openalex.org/W3128138976","doi":"https://doi.org/10.1109/tmm.2021.3058050","title":"Human Action Recognition by Discriminative Feature Pooling and Video Segment Attention Model","display_name":"Human Action Recognition by Discriminative Feature Pooling and Video Segment Attention Model","publication_year":2021,"publication_date":"2021-02-10","ids":{"openalex":"https://openalex.org/W3128138976","doi":"https://doi.org/10.1109/tmm.2021.3058050","mag":"3128138976"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3058050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3058050","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":"https://openalex.org/A5004221027","display_name":"Md Moniruzzaman","orcid":"https://orcid.org/0000-0003-3217-5094"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Moniruzzaman","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, New York, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, New York, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080054465","display_name":"Zhaozheng Yin","orcid":"https://orcid.org/0000-0002-9602-6488"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaozheng Yin","raw_affiliation_strings":["Department of Computer Science and Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252153","display_name":"Zhihai He","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihai He","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113932966","display_name":"Ruwen Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruwen Qin","raw_affiliation_strings":["Department of Civil Engineering, Stony Brook University, Stony Brook, New York, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil Engineering, Stony Brook University, Stony Brook, New York, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082067008","display_name":"Ming C. Leu","orcid":"https://orcid.org/0000-0002-5056-3907"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming C Leu","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, Missouri University of Science and Technology, Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Missouri University of Science and Technology, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004221027"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":1.9378,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.87843576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"24","issue":null,"first_page":"689","last_page":"701"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9947999715805054,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9894000291824341,"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":0.8488050699234009},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8465932011604309},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.8222421407699585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7392154335975647},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6370680332183838},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6160614490509033},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.571496844291687},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5135110020637512},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.45072296261787415},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4276966452598572},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32431232929229736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8488050699234009},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8465932011604309},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8222421407699585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7392154335975647},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6370680332183838},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6160614490509033},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.571496844291687},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5135110020637512},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.45072296261787415},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4276966452598572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32431232929229736},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3058050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3058050","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1578985305","https://openalex.org/W1586730761","https://openalex.org/W1586939924","https://openalex.org/W1926645898","https://openalex.org/W1927052826","https://openalex.org/W1945209586","https://openalex.org/W1947481528","https://openalex.org/W1967320926","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2046589395","https://openalex.org/W2105101328","https://openalex.org/W2109875425","https://openalex.org/W2114701396","https://openalex.org/W2119031011","https://openalex.org/W2126574503","https://openalex.org/W2126579184","https://openalex.org/W2142194269","https://openalex.org/W2155351433","https://openalex.org/W2163292664","https://openalex.org/W2194775991","https://openalex.org/W2235034809","https://openalex.org/W2336403884","https://openalex.org/W2342662179","https://openalex.org/W2342776425","https://openalex.org/W2469228190","https://openalex.org/W2471775118","https://openalex.org/W2477205648","https://openalex.org/W2507009361","https://openalex.org/W2519750370","https://openalex.org/W2553594924","https://openalex.org/W2556685112","https://openalex.org/W2604113307","https://openalex.org/W2736596806","https://openalex.org/W2751445731","https://openalex.org/W2752782242","https://openalex.org/W2770446450","https://openalex.org/W2792345332","https://openalex.org/W2807742018","https://openalex.org/W2884293275","https://openalex.org/W2891969803","https://openalex.org/W2913950831","https://openalex.org/W2918745114","https://openalex.org/W2920582597","https://openalex.org/W2948048211","https://openalex.org/W2950568498","https://openalex.org/W2951906878","https://openalex.org/W2953461088","https://openalex.org/W2962710043","https://openalex.org/W2962852931","https://openalex.org/W2963603913","https://openalex.org/W2963731876","https://openalex.org/W2964094092","https://openalex.org/W2964316443","https://openalex.org/W2964350391","https://openalex.org/W2968553732","https://openalex.org/W2977470591","https://openalex.org/W2990503944","https://openalex.org/W2992457155","https://openalex.org/W3106129208","https://openalex.org/W6600983433","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6682864246","https://openalex.org/W6684983439","https://openalex.org/W6743837088","https://openalex.org/W6891831295"],"related_works":["https://openalex.org/W2514274290","https://openalex.org/W2406522397","https://openalex.org/W2970216048","https://openalex.org/W2285052147","https://openalex.org/W2043075591","https://openalex.org/W2725397116","https://openalex.org/W2806866760","https://openalex.org/W2546942002","https://openalex.org/W2990052897","https://openalex.org/W2579154055"],"abstract_inverted_index":{"We":[0],"Introduce":[1],"a":[2,9,17,70,131,138],"simple":[3],"yet":[4],"effective":[5],"network":[6,122,148,184],"that":[7,48],"embeds":[8],"novel":[10,18],"Discriminative":[11],"Feature":[12],"Pooling":[13],"(DFP)":[14],"mechanism":[15,42],"and":[16,32,62,85,101,134,172,174,181],"Video":[19],"Segment":[20],"Attention":[21],"Model":[22],"(VSAM),":[23],"for":[24,43],"video-based":[25],"human":[26],"action":[27,99,117,120,160],"recognition":[28,121],"from":[29,81,126],"both":[30,127],"trimmed":[31,128,175],"untrimmed":[33,135,142,167],"videos.":[34,163],"Our":[35,119],"DFP":[36],"module":[37],"introduces":[38],"an":[39],"attentional":[40],"pooling":[41],"3D":[44,51],"Convolutional":[45],"Neural":[46],"Networks":[47],"attentionally":[49],"pools":[50],"convolutional":[52],"feature":[53],"maps":[54],"to":[55,66,91,106,115,189],"emphasize":[56],"the":[57,67,93,97,108,116,153,166,190],"most":[58,78],"critical":[59,79],"spatial,":[60],"temporal,":[61],"channel-wise":[63],"features":[64,80],"related":[65],"actions":[68],"within":[69],"video":[71,83,94,109,168,176],"segment,":[72],"while":[73],"our":[74,147,183],"VSAM":[75],"ensembles":[76],"these":[77],"all":[82],"segments":[84,95,110],"learns":[86,149],"(1)":[87],"class-specific":[88],"attention":[89,104,150],"weights":[90,105,151],"classify":[92],"into":[96],"corresponding":[98],"categories,":[100],"(2)":[102],"class-agnostic":[103],"rank":[107],"based":[111],"on":[112,165],"their":[113],"relevance":[114],"class.":[118],"can":[123],"be":[124],"trained":[125],"videos":[129,136,143],"in":[130,137,162],"fully-supervised":[132],"way":[133],"weakly-supervised":[139],"way.":[140],"For":[141],"with":[144],"weak":[145],"labels,":[146],"without":[152],"requirement":[154],"of":[155,159,170,178],"precise":[156],"temporal":[157],"annotations":[158],"occurrences":[161],"Evaluated":[164],"datasets":[169,177],"THUMOS14":[171],"ActivityNet1.2,":[173],"HMDB51,":[179],"UCF101,":[180],"HOLLYWOOD2,":[182],"achieves":[185],"promising":[186],"performance,":[187],"compared":[188],"latest":[191],"state-of-the-art":[192],"method.":[193],"The":[194],"implementation":[195],"code":[196],"is":[197],"available":[198],"at":[199],"<uri":[200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/MoniruzzamanMd/DFP-VSAM-Networks</uri>":[202],".":[203]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}