{"id":"https://openalex.org/W4402980196","doi":"https://doi.org/10.1109/icme57554.2024.10688175","title":"Weakly-Supervised Action Localization by Hierarchical Attention Mechanism with Multi-Scale Fusion Strategies","display_name":"Weakly-Supervised Action Localization by Hierarchical Attention Mechanism with Multi-Scale Fusion Strategies","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980196","doi":"https://doi.org/10.1109/icme57554.2024.10688175"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688175","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5115595839","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-2429-7027"},"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":true,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tongji University,The College of Software Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,The College of Software Engineering,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035948567","display_name":"Shengjie Zhao","orcid":"https://orcid.org/0000-0002-6109-2522"},"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":"Shengjie Zhao","raw_affiliation_strings":["Tongji University,The College of Software Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,The College of Software Engineering,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115595839"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16804284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9876000285148621,"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":0.9876000285148621,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9693999886512756,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9383999705314636,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6791127920150757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5648062825202942},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5564805269241333},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5429610013961792},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5124979019165039},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4842659831047058},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.451641321182251},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3714197874069214},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33882981538772583},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0592399537563324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791127920150757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5648062825202942},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5564805269241333},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5429610013961792},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5124979019165039},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4842659831047058},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.451641321182251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3714197874069214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33882981538772583},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0592399537563324},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/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/icme57554.2024.10688175","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2382997850","https://openalex.org/W2390968135","https://openalex.org/W2382213751","https://openalex.org/W2351750670","https://openalex.org/W1597848696","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2353265673","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Weakly-supervised":[0],"temporal":[1,74],"action":[2,7,107,124],"localization":[3,108],"focuses":[4],"on":[5,20,140],"locating":[6],"intervals":[8],"when":[9,59],"merely":[10],"video-level":[11],"supervised":[12],"signals":[13],"are":[14,67,102],"available.":[15],"Conventional":[16],"methods":[17,49],"mostly":[18],"rely":[19],"the":[21,31,34,39,41,44,53,146,150],"attention":[22,61,83],"framework,":[23],"which":[24],"generates":[25],"a":[26,81],"set":[27],"of":[28,56],"scores":[29],"indicating":[30],"confidence":[32],"that":[33,101,149],"video":[35],"snippet":[36],"belongs":[37],"to":[38,51,90,96,118,129,132],"foreground,":[40],"background,":[42],"and":[43,63,142,145],"context,":[45],"respectively.":[46],"However,":[47],"such":[48,92],"fail":[50],"consider":[52],"structural":[54,65,93],"properties":[55,66],"snippet-level":[57],"features":[58,121],"generating":[60],"scores,":[62],"these":[64],"critical":[68],"for":[69],"capturing":[70],"contextual":[71],"information":[72],"in":[73,105],"tasks.":[75],"To":[76],"this":[77],"end,":[78],"we":[79],"propose":[80],"hierarchical":[82],"generation":[84],"mechanism":[85],"with":[86],"multi-scale":[87],"fusion":[88],"strategies":[89],"model":[91,137],"information.":[94],"Besides,":[95],"resolve":[97],"action-context":[98],"confusion":[99],"issues":[100],"quite":[103],"intractable":[104],"weakly-supervised":[106],"tasks,":[109],"metric":[110],"learning":[111],"is":[112,138],"further":[113],"introduced":[114],"into":[115],"our":[116,136],"framework":[117],"suppress":[119],"context":[120],"from":[122],"approaching":[123],"features,":[125],"while":[126],"encouraging":[127],"them":[128],"be":[130],"close":[131],"background":[133],"features.":[134],"Finally,":[135],"evaluated":[139],"THUMOS14":[141],"ActivityNet1.3":[143],"benchmarks,":[144],"results":[147],"demonstrate":[148],"proposed":[151],"approach":[152],"achieves":[153],"desirable":[154],"performance.":[155]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}