{"id":"https://openalex.org/W4226380330","doi":"https://doi.org/10.1109/tmm.2022.3166025","title":"Temporal Attention-Pyramid Pooling for Temporal Action Detection","display_name":"Temporal Attention-Pyramid Pooling for Temporal Action Detection","publication_year":2022,"publication_date":"2022-04-08","ids":{"openalex":"https://openalex.org/W4226380330","doi":"https://doi.org/10.1109/tmm.2022.3166025"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3166025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3166025","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":null,"display_name":"Ming-Gang Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming-Gang Gan","raw_affiliation_strings":["State Key Laboratory of Intelligent Control and Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100456335","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-9125-3630"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["State Key Laboratory of Intelligent Control and Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9125-3630","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":2.3469,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89800504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"3799","last_page":"3810"},"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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11439","display_name":"Video Analysis and Summarization","score":0.9865000247955322,"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/computer-science","display_name":"Computer science","score":0.8572182655334473},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.797157883644104},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7646869421005249},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6560755372047424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6507904529571533},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5566502213478088},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4802672863006592},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48011040687561035},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4600505828857422},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4420608580112457},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4153899550437927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8572182655334473},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.797157883644104},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7646869421005249},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6560755372047424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6507904529571533},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5566502213478088},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4802672863006592},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48011040687561035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4600505828857422},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4420608580112457},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4153899550437927},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3166025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3166025","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","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1595717062","https://openalex.org/W1927052826","https://openalex.org/W2016053056","https://openalex.org/W2105101328","https://openalex.org/W2156303437","https://openalex.org/W2161969291","https://openalex.org/W2486996822","https://openalex.org/W2507009361","https://openalex.org/W2593722617","https://openalex.org/W2597958930","https://openalex.org/W2604114396","https://openalex.org/W2619947201","https://openalex.org/W2745461083","https://openalex.org/W2751832138","https://openalex.org/W2884002012","https://openalex.org/W2884969173","https://openalex.org/W2892189026","https://openalex.org/W2904619119","https://openalex.org/W2941239341","https://openalex.org/W2950568498","https://openalex.org/W2950907316","https://openalex.org/W2951033927","https://openalex.org/W2952435096","https://openalex.org/W2962677524","https://openalex.org/W2962709777","https://openalex.org/W2962876901","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2964054038","https://openalex.org/W2964107628","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2964274041","https://openalex.org/W2965102465","https://openalex.org/W2983918066","https://openalex.org/W2984619425","https://openalex.org/W2985557167","https://openalex.org/W2986407524","https://openalex.org/W2992457155","https://openalex.org/W2996173702","https://openalex.org/W2997314266","https://openalex.org/W2997706915","https://openalex.org/W2998486508","https://openalex.org/W2998582438","https://openalex.org/W2999794487","https://openalex.org/W3034623254","https://openalex.org/W3035251589","https://openalex.org/W3037147829","https://openalex.org/W3092820804","https://openalex.org/W3106041614","https://openalex.org/W3110589170","https://openalex.org/W3128636476","https://openalex.org/W3173229911","https://openalex.org/W3174569083","https://openalex.org/W3176444885","https://openalex.org/W3210279979","https://openalex.org/W4288091276","https://openalex.org/W6682864246","https://openalex.org/W6722654596","https://openalex.org/W6724944384","https://openalex.org/W6736356174","https://openalex.org/W6769600802","https://openalex.org/W6770206098","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2022849497","https://openalex.org/W2407190427","https://openalex.org/W3081299480","https://openalex.org/W2919210741","https://openalex.org/W2907584218","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W2797752778","https://openalex.org/W4322096758","https://openalex.org/W4206776094"],"abstract_inverted_index":{"Temporal":[0,60],"action":[1,43,72,148,154,168,174,178],"detection":[2,169,179],"is":[3,11,24],"a":[4,25,58,97,123,146],"challenging":[5],"task":[6],"in":[7,45],"video":[8],"understanding,":[9],"which":[10],"usually":[12],"divided":[13],"into":[14],"two":[15,165],"stages:":[16],"proposal":[17,22,51,67,93,105,137,149,155,175],"generation":[18,150],"and":[19,39,42,127,152,158,176],"classification.":[20],"Learning":[21],"features":[23,68],"crucial":[26],"step":[27],"for":[28,171,201],"both":[29,202],"stages.":[30],"However,":[31],"most":[32],"methods":[33,200],"ignore":[34],"temporal":[35,98,115,125,132,147,167,173,177],"information":[36],"of":[37,69,87],"proposals":[38,46],"consider":[40],"background":[41,90],"frames":[44],"equally,":[47],"leading":[48],"to":[49,65,81,101,108,130,134,181],"poor":[50],"features.":[52,94,138],"In":[53,117],"this":[54],"paper,":[55],"we":[56,121,144,160],"propose":[57],"novel":[59],"Attention-Pyramid":[61],"Pooling":[62],"(TAPP)":[63],"method":[64,76],"learn":[66],"arbitrary":[70,103],"length":[71,104],"proposals.":[73],"The":[74],"TAPP":[75,119,142,194],"exploits":[77],"the":[78,84,114,118,131,141,172,186,193,197],"attention":[79],"mechanism":[80],"focus":[82],"on":[83,92,140,164,192],"discriminative":[85],"part":[86],"proposals,":[88],"suppressing":[89],"influence":[91],"It":[95],"constructs":[96],"pyramid":[99,133],"structure":[100],"convert":[102],"feature":[106],"sequences":[107,111],"multiple":[109],"fixed-length":[110],"while":[112],"retaining":[113],"information.":[116],"method,":[120,143],"design":[122],"multi-scale":[124],"function":[126],"apply":[128],"it":[129],"generate":[135],"final":[136],"Based":[139],"construct":[145],"model":[151],"an":[153],"classification":[156],"model,":[157],"then":[159],"perform":[161],"extensive":[162],"experiments":[163],"mainstream":[166],"datasets":[170],"tasks":[180],"verify":[182],"our":[183,189],"models.":[184],"On":[185],"THUMOS\u201914":[187],"dataset,":[188],"models":[190],"based":[191],"significantly":[195],"outperform":[196],"previous":[198],"state-of-the-art":[199],"tasks.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}