{"id":"https://openalex.org/W4417051941","doi":"https://doi.org/10.1109/tpami.2025.3640697","title":"Heatmap Pooling Network for Action Recognition From RGB Videos","display_name":"Heatmap Pooling Network for Action Recognition From RGB Videos","publication_year":2025,"publication_date":"2025-12-05","ids":{"openalex":"https://openalex.org/W4417051941","doi":"https://doi.org/10.1109/tpami.2025.3640697","pmid":"https://pubmed.ncbi.nlm.nih.gov/41348797"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3640697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3640697","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100705472","display_name":"Mengyuan Liu","orcid":"https://orcid.org/0000-0002-6332-8316"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengyuan Liu","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, Guangdong, China","State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763629","display_name":"Jinfu Liu","orcid":"https://orcid.org/0000-0002-4590-5343"},"institutions":[{"id":"https://openalex.org/I4210148944","display_name":"D\u00e0-Ji\u0101ng Innovations Science and Technology (China)","ror":"https://ror.org/04fmkfb67","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210148944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfu Liu","raw_affiliation_strings":["Imaging Department, DJI Technology Company Ltd., Shenzhen, Guangdong, China","Imaging Department, DJI Technology Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Imaging Department, DJI Technology Company Ltd., Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210148944"]},{"raw_affiliation_string":"Imaging Department, DJI Technology Co., Ltd, China","institution_ids":["https://openalex.org/I4210148944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102944675","display_name":"Yongkang Jiang","orcid":"https://orcid.org/0000-0002-2768-6159"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkang Jiang","raw_affiliation_strings":["Tongji University, Shanghai, China","TongJi University, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"TongJi University, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049557511","display_name":"Bin He","orcid":"https://orcid.org/0000-0003-3193-6269"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["Tongji University, Shanghai, China","TongJi University, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"TongJi University, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100705472"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42348497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"3","first_page":"3726","last_page":"3743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9878000020980835,"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":0.9878000020980835,"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":0.0017999999690800905,"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/T12290","display_name":"Human Motion and Animation","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.7892000079154968},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7609999775886536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5357999801635742},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4828000068664551},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4544000029563904},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4124000072479248},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.41019999980926514},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3774999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149999976158142},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7892000079154968},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7609999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7595999836921692},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5357999801635742},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4828000068664551},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4124000072479248},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3788999915122986},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2667999863624573}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006802","descriptor_name":"Human Activities","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D006802","descriptor_name":"Human Activities","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3640697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3640697","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41348797","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41348797","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W2054041160","https://openalex.org/W2126579184","https://openalex.org/W2559085405","https://openalex.org/W2593146028","https://openalex.org/W2625366777","https://openalex.org/W2760103357","https://openalex.org/W2765433083","https://openalex.org/W2799211965","https://openalex.org/W2944006115","https://openalex.org/W2948058585","https://openalex.org/W2948246283","https://openalex.org/W2963076818","https://openalex.org/W2963402313","https://openalex.org/W2963524571","https://openalex.org/W2964134613","https://openalex.org/W2981923053","https://openalex.org/W2990503944","https://openalex.org/W3014641072","https://openalex.org/W3035050855","https://openalex.org/W3035180180","https://openalex.org/W3035570025","https://openalex.org/W3097033071","https://openalex.org/W3109306201","https://openalex.org/W3109392981","https://openalex.org/W3174053790","https://openalex.org/W3175624454","https://openalex.org/W3185273257","https://openalex.org/W3195949276","https://openalex.org/W3203634062","https://openalex.org/W3213518743","https://openalex.org/W4200140120","https://openalex.org/W4282943820","https://openalex.org/W4283775680","https://openalex.org/W4312245820","https://openalex.org/W4312614039","https://openalex.org/W4312799843","https://openalex.org/W4312895250","https://openalex.org/W4313127332","https://openalex.org/W4319299930","https://openalex.org/W4319300928","https://openalex.org/W4367663575","https://openalex.org/W4383108418","https://openalex.org/W4385245566","https://openalex.org/W4386065362","https://openalex.org/W4387789756","https://openalex.org/W4387968033","https://openalex.org/W4390327397","https://openalex.org/W4390871806","https://openalex.org/W4390871852","https://openalex.org/W4390874024","https://openalex.org/W4391661486","https://openalex.org/W4393148719","https://openalex.org/W4393170627","https://openalex.org/W4394625712","https://openalex.org/W4401413845","https://openalex.org/W4401655985","https://openalex.org/W4401991041","https://openalex.org/W4402727550","https://openalex.org/W4402775313","https://openalex.org/W4402896749","https://openalex.org/W4403791723","https://openalex.org/W4407690720","https://openalex.org/W4408564948","https://openalex.org/W4409366513","https://openalex.org/W4409640992","https://openalex.org/W4410204490","https://openalex.org/W4413146594","https://openalex.org/W7084098655"],"related_works":[],"abstract_inverted_index":{"Human":[0],"action":[1,62,131,163],"recognition":[2,63,164],"(HAR)":[3],"in":[4,15,51,78],"videos":[5,27,79],"has":[6],"garnered":[7],"widespread":[8],"attention":[9],"due":[10],"to":[11,35,118],"the":[12,48,75,94,120,153,160],"rich":[13],"information":[14,32,50],"RGB":[16,26],"videos.":[17,103],"Nevertheless,":[18],"existing":[19,161],"methods":[20],"for":[21,61],"extracting":[22],"deep":[23],"features":[24,73,88,101,123],"from":[25,64,102],"face":[28],"challenges":[29],"such":[30],"as":[31],"redundancy,":[33],"susceptibility":[34],"noise":[36],"and":[37,45,70,99,112,146],"high":[38],"storage":[39],"costs.":[40],"To":[41],"address":[42],"these":[43],"issues":[44],"fully":[46],"harness":[47],"useful":[49],"videos,":[52,65],"we":[53,106],"propose":[54],"a":[55,81,108,113],"novel":[56],"heatmap":[57,100],"pooling":[58,83],"network":[59],"(HP-Net)":[60],"which":[66,158],"extracts":[67],"information-rich,":[68],"robust":[69,130],"concise":[71],"pooled":[72,87,122],"of":[74,155],"human":[76,162],"body":[77],"through":[80],"feedback":[82],"module.":[84],"The":[85],"extracted":[86,121],"demonstrate":[89],"obvious":[90],"performance":[91],"advantages":[92],"over":[93],"previously":[95],"obtained":[96],"pose":[97],"data":[98],"In":[104],"addition,":[105],"design":[107],"spatial-motion":[109],"co-learning":[110],"module":[111,117],"text":[114],"refinement":[115],"modulation":[116],"integrate":[119],"with":[124],"other":[125],"multimodal":[126],"data,":[127],"enabling":[128],"more":[129],"recognition.":[132],"Extensive":[133],"experiments":[134],"on":[135],"several":[136],"benchmarks":[137],"namely":[138],"NTU":[139,142],"RGB+D":[140,143],"60,":[141],"120,":[144],"Toyota-Smarthome":[145],"uncrewed":[147],"aerial":[148],"vehicles":[149],"(UAV)-Human":[150],"consistently":[151],"verify":[152],"effectiveness":[154],"our":[156],"HP-Net,":[157],"outperforms":[159],"methods.":[165]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-05T00:00:00"}