{"id":"https://openalex.org/W3120833752","doi":"https://doi.org/10.1609/aaai.v35i2.16256","title":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","display_name":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3120833752","doi":"https://doi.org/10.1609/aaai.v35i2.16256","mag":"3120833752"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v35i2.16256","doi":"https://doi.org/10.1609/aaai.v35i2.16256","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i2.16256","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v35i2.16256","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082493192","display_name":"Ashraful Islam","orcid":"https://orcid.org/0000-0003-2367-2013","observed_orcids":["https://orcid.org/0000-0003-2367-2013"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashraful Islam","raw_affiliation_strings":["Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027540915","display_name":"Chengjiang Long","orcid":"https://orcid.org/0000-0003-1584-7290","observed_orcids":["https://orcid.org/0000-0003-1584-7290"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengjiang Long","raw_affiliation_strings":["JD Digits AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Digits AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049207791","display_name":"Richard J. Radke","orcid":"https://orcid.org/0000-0001-5064-7775","observed_orcids":["https://orcid.org/0000-0001-5064-7775"]},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Radke","raw_affiliation_strings":["Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3058,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87218684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"2","first_page":"1637","last_page":"1645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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":0.9984999895095825,"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":0.00019999999494757503,"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":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/weakly-supervised-temporal-action-localization","display_name":"weakly-supervised temporal action localization","score":0.9570000171661377},{"id":"https://openalex.org/keywords/hybrid-attention-mechanism","display_name":"hybrid attention mechanism","score":0.9390000104904175},{"id":"https://openalex.org/keywords/multiple-instance-learning","display_name":"multiple instance learning","score":0.8230000138282776},{"id":"https://openalex.org/keywords/hard-attention","display_name":"hard attention","score":0.9890000224113464},{"id":"https://openalex.org/keywords/thumos14","display_name":"THUMOS14","score":0.8149999976158142}],"concepts":[{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.9396175146102905},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8626875281333923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841905951499939},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636368036270142},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6150415539741516},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5664774179458618},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5476644039154053},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5044630765914917},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4425320327281952},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.4423210024833679},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4376601576805115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4318247139453888},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35883453488349915},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.10412350296974182},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v35i2.16256","doi":"https://doi.org/10.1609/aaai.v35i2.16256","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i2.16256","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2101.00545","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.00545","pdf_url":"https://arxiv.org/pdf/2101.00545","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2101.00545","doi":"https://doi.org/10.48550/arxiv.2101.00545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.00545","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v35i2.16256","doi":"https://doi.org/10.1609/aaai.v35i2.16256","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i2.16256","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7282745900","display_name":null,"funder_award_id":"2013-ST-061-ED0001","funder_id":"https://openalex.org/F4320306110","funder_display_name":"U.S. Department of Homeland Security"}],"funders":[{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W61928934","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1578285471","https://openalex.org/W1927052826","https://openalex.org/W2105101328","https://openalex.org/W2156303437","https://openalex.org/W2337252826","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2604113307","https://openalex.org/W2606520630","https://openalex.org/W2607644813","https://openalex.org/W2618799552","https://openalex.org/W2619082050","https://openalex.org/W2619947201","https://openalex.org/W2626778328","https://openalex.org/W2751023760","https://openalex.org/W2884293275","https://openalex.org/W2893260909","https://openalex.org/W2895240652","https://openalex.org/W2920182456","https://openalex.org/W2940924736","https://openalex.org/W2948229620","https://openalex.org/W2962677524","https://openalex.org/W2962709777","https://openalex.org/W2962876901","https://openalex.org/W2963155035","https://openalex.org/W2963247196","https://openalex.org/W2964121744","https://openalex.org/W2964216549","https://openalex.org/W2967894811","https://openalex.org/W2984478308","https://openalex.org/W2986407524","https://openalex.org/W2988098865","https://openalex.org/W2989042503","https://openalex.org/W2991396237","https://openalex.org/W2998702159","https://openalex.org/W3003088567","https://openalex.org/W3010087156","https://openalex.org/W3034623254","https://openalex.org/W3034779438","https://openalex.org/W3035585099","https://openalex.org/W6602537450"],"related_works":["https://openalex.org/W4390045285","https://openalex.org/W4309619589","https://openalex.org/W4402048694","https://openalex.org/W3112040205","https://openalex.org/W4402980196","https://openalex.org/W3003088567","https://openalex.org/W4386576797","https://openalex.org/W2962709777","https://openalex.org/W3203848195","https://openalex.org/W3001994861"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"temporal":[2,16,115,126,155],"action":[3,50,179,184],"localization":[4],"is":[5],"a":[6,35,53,61,103,109],"challenging":[7],"vision":[8],"task":[9],"due":[10],"to":[11,41,121,170,180],"the":[12,21,43,56,67,75,137,141,173,182,203,217],"absence":[13],"of":[14,18,48,64,71,78,177],"ground-truth":[15],"locations":[17],"actions":[19],"in":[20,52,94,136],"training":[22],"videos.":[23],"With":[24],"only":[25,65],"video-level":[26],"supervision":[27],"during":[28],"training,":[29],"most":[30,68],"existing":[31,57],"methods":[32,83,192],"rely":[33],"on":[34,172,202,216],"Multiple":[36],"Instance":[37],"Learning":[38],"(MIL)":[39],"framework":[40,105],"predict":[42],"start":[44],"and":[45,118,157,206],"end":[46],"frame":[47],"each":[49,150,166],"category":[51],"video.":[54],"However,":[55],"MIL-based":[58],"approach":[59,188],"has":[60],"major":[62],"limitation":[63],"capturing":[66],"discriminative":[69,175],"frames":[70,176],"an":[72,79,91,132,146,178],"action,":[73],"ignoring":[74],"full":[76,183],"extent":[77],"activity.":[80],"Moreover,":[81,153],"these":[82,123],"cannot":[84],"model":[85],"background":[86,134,142],"activity":[87,143],"effectively,":[88],"which":[89,113],"plays":[90],"important":[92],"role":[93],"localizing":[95],"foreground":[96],"activities.":[97],"In":[98],"this":[99],"paper,":[100],"we":[101],"present":[102],"novel":[104],"named":[106],"HAM-Net":[107],"with":[108],"hybrid":[110],"attention":[111,128,159,163],"mechanism":[112],"includes":[114],"soft,":[116],"semi-soft":[117,156],"hard":[119,158],"attentions":[120],"address":[122],"issues.":[124],"Our":[125,186],"soft":[127],"module,":[129,139],"guided":[130],"by":[131,144,193,207],"auxiliary":[133],"class":[135],"classification":[138],"models":[140],"introducing":[145],"``action-ness''":[147],"score":[148],"for":[149,165],"video":[151,167],"snippet.":[152],"our":[154],"modules,":[160],"calculating":[161],"two":[162],"scores":[164],"snippet,":[168],"help":[169],"focus":[171],"less":[174],"capture":[181],"boundary.":[185],"proposed":[187],"outperforms":[189],"recent":[190],"state-of-the-art":[191],"at":[194,198,208,212],"least":[195,209],"2.2%":[196],"mAP":[197,211],"IoU":[199,213],"threshold":[200,214],"0.5":[201],"THUMOS14":[204],"dataset,":[205],"1.3%":[210],"0.75":[215],"ActivityNet1.2":[218],"dataset.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2021-01-18T00:00:00"}