{"id":"https://openalex.org/W4391307060","doi":"https://doi.org/10.1109/vcip59821.2023.10402736","title":"AHFu-Net: Align, Hallucinate, and Fuse Network for Missing Multimodal Action Recognition","display_name":"AHFu-Net: Align, Hallucinate, and Fuse Network for Missing Multimodal Action Recognition","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4391307060","doi":"https://doi.org/10.1109/vcip59821.2023.10402736"},"language":"en","primary_location":{"id":"doi:10.1109/vcip59821.2023.10402736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip59821.2023.10402736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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/A5103037880","display_name":"Muhammad Adi Nugroho","orcid":"https://orcid.org/0000-0002-9360-5441"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Muhammad Adi Nugroho","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058640072","display_name":"Sangmin Woo","orcid":"https://orcid.org/0000-0003-4451-9675"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangmin Woo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726740","display_name":"Sumin Lee","orcid":"https://orcid.org/0000-0001-6782-7457"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sumin Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069759184","display_name":"Changick Kim","orcid":"https://orcid.org/0000-0001-9323-8488"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changick Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103037880"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46163329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9939000010490417,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/hallucinating","display_name":"Hallucinating","score":0.9634884595870972},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.7893883585929871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6359683275222778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5347864627838135},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5020594596862793},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4853195548057556},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.41043388843536377},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3789671063423157},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33738261461257935},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13140606880187988},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08990982174873352},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.07408902049064636},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06645938754081726}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.9634884595870972},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.7893883585929871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6359683275222778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5347864627838135},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5020594596862793},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4853195548057556},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.41043388843536377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3789671063423157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33738261461257935},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13140606880187988},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08990982174873352},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.07408902049064636},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06645938754081726},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip59821.2023.10402736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip59821.2023.10402736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2054041160","https://openalex.org/W2067562626","https://openalex.org/W2194775991","https://openalex.org/W2782057162","https://openalex.org/W2809440904","https://openalex.org/W2883630736","https://openalex.org/W2897611955","https://openalex.org/W2904658540","https://openalex.org/W2944006115","https://openalex.org/W2963155035","https://openalex.org/W2964134613","https://openalex.org/W3002552512","https://openalex.org/W3009812836","https://openalex.org/W3034996364","https://openalex.org/W3082819019","https://openalex.org/W3100993552","https://openalex.org/W3101424466","https://openalex.org/W3118761370","https://openalex.org/W3119171349","https://openalex.org/W3174906557","https://openalex.org/W4282981352","https://openalex.org/W4293390340","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3204676188","https://openalex.org/W4378771713","https://openalex.org/W2992803471","https://openalex.org/W2066036438","https://openalex.org/W2312876277","https://openalex.org/W2930227984","https://openalex.org/W2078454190","https://openalex.org/W2963350370","https://openalex.org/W2108123836","https://openalex.org/W2063248114"],"abstract_inverted_index":{"In":[0],"this":[1,32],"work,":[2],"we":[3,34],"explore":[4],"the":[5,12,22,45,123],"multimodal":[6,129],"action":[7,107],"recognition":[8],"problem,":[9],"specifically":[10],"in":[11,122],"context":[13],"of":[14,21,55,76,125,131],"RGB-Depth":[15,106],"modalities":[16,24],"scenario,":[17],"where":[18],"a":[19,36,95],"subset":[20],"learning":[23],"is":[25],"missing":[26,41,126],"at":[27,48],"inference":[28,49],"time.":[29,50],"To":[30],"address":[31],"issue,":[33],"construct":[35],"hallucination":[37],"network":[38],"to":[39],"generate":[40],"modality":[42,47,127],"information":[43],"from":[44],"available":[46],"We":[51,90],"propose":[52],"key":[53],"components":[54],"an":[56],"effective":[57],"spatio-temporal":[58],"encoder":[59],"for":[60,105],"strong":[61],"unimodal":[62],"performance":[63,117],"with":[64,82],"Local":[65],"Patch":[66],"Temporal":[67],"Transformer":[68,73,86],"(LPTT)":[69],"and":[70,79,102,133],"Spatial":[71],"Encoder":[72],"(SET),":[74],"alignment":[75],"multi-modal":[77],"features,":[78],"fusion":[80],"strategy":[81],"our":[83],"Multimodal":[84],"Bottleneck":[85],"Fusion":[87],"Module":[88],"(MMBTF).":[89],"incorporate":[91],"these":[92],"ideas":[93],"into":[94],"novel":[96],"framework":[97],"named":[98],"AHFu-Net":[99],"(Align,":[100],"Hallucinate,":[101],"Fuse":[103],"network)":[104],"recognition.":[108],"Our":[109],"experiments":[110],"demonstrate":[111],"that":[112],"AHFu":[113],"Net":[114],"achieves":[115],"state-of-the-art":[116],"while":[118],"maintaining":[119],"high":[120],"accuracy":[121],"case":[124],"on":[128],"datasets":[130],"NTU-RGB+D":[132],"NWUCLA.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}