{"id":"https://openalex.org/W4301366326","doi":"https://doi.org/10.1145/3552458.3556449","title":"Multi-level Multi-modal Feature Fusion for Action Recognition in Videos","display_name":"Multi-level Multi-modal Feature Fusion for Action Recognition in Videos","publication_year":2022,"publication_date":"2022-10-04","ids":{"openalex":"https://openalex.org/W4301366326","doi":"https://doi.org/10.1145/3552458.3556449"},"language":"en","primary_location":{"id":"doi:10.1145/3552458.3556449","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3552458.3556449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Human-Centric Multimedia Analysis","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/A5037803973","display_name":"Xinghang Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinghang Hu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068950059","display_name":"Yanli Ji","orcid":"https://orcid.org/0000-0001-9122-6141"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanli Ji","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070419252","display_name":"Gedamu Alemu Kumie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gedamu Alemu Kumie","raw_affiliation_strings":["Sichuan Artificial intelligence Research Institute, Yibin, China"],"affiliations":[{"raw_affiliation_string":"Sichuan Artificial intelligence Research Institute, Yibin, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037803973"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.1006,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38600447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"33"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.989300012588501,"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"}},{"id":"https://openalex.org/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.8294926881790161},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7838785648345947},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7713422775268555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7304239869117737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6512628197669983},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5894705653190613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5730739831924438},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5045312643051147},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4931780695915222},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4566757380962372},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.45237573981285095},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44404417276382446}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8294926881790161},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7838785648345947},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7713422775268555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304239869117737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6512628197669983},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5894705653190613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5730739831924438},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5045312643051147},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4931780695915222},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4566757380962372},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.45237573981285095},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44404417276382446},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3552458.3556449","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3552458.3556449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Human-Centric Multimedia Analysis","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":18,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2619383789","https://openalex.org/W2808178187","https://openalex.org/W2912500072","https://openalex.org/W2914304175","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2964045146","https://openalex.org/W2990467045","https://openalex.org/W3034658206","https://openalex.org/W3035333188","https://openalex.org/W3043840704","https://openalex.org/W3173621652","https://openalex.org/W3194397797","https://openalex.org/W3206930349","https://openalex.org/W4312658081"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Several":[0],"multi-modal":[1,28,48],"feature":[2,55,72,92,131,142],"fusion":[3],"approaches":[4,20],"have":[5],"been":[6],"proposed":[7],"in":[8,11,17,30,61,89,122,156,168],"recent":[9],"years":[10],"order":[12],"to":[13,68,75,128],"improve":[14],"action":[15,59,119,135,141,166],"recognition":[16,60,167],"videos.":[18,62,169],"These":[19],"do":[21],"not":[22,100],"take":[23],"full":[24],"advantage":[25],"of":[26,106,165],"the":[27,31,47,76,79,87,90,97,103,107,117,125,157],"information":[29],"videos,":[32],"since":[33],"they":[34],"are":[35],"biased":[36],"towards":[37],"a":[38,52,95],"single":[39],"modality":[40,67],"or":[41],"treat":[42],"modalities":[43],"separately.":[44],"To":[45],"address":[46],"problem,":[49],"we":[50,85],"propose":[51],"Multi-Level":[53],"Multi-modal":[54],"Fusion":[56],"(MLMF)":[57],"for":[58,133],"The":[63,137],"MLMF":[64],"projects":[65],"each":[66],"shared":[69,82],"and":[70,161],"specific":[71,91],"spaces.":[73],"According":[74],"similarity":[77],"between":[78],"two":[80,108],"modal":[81],"features":[83,88,99,148],"space,":[84],"augment":[86],"space.":[93],"As":[94],"result,":[96],"fused":[98],"only":[101],"incorporate":[102],"unique":[104],"characteristics":[105],"modalities,":[109],"but":[110],"also":[111],"explicitly":[112],"emphasize":[113],"their":[114],"similarities.":[115],"Moreover,":[116],"video's":[118],"segments":[120],"differ":[121],"length,":[123],"so":[124],"model":[126],"needs":[127],"consider":[129],"different-level":[130],"ensembling":[132],"fine-grained":[134],"recognition.":[136],"optimal":[138],"multi-level":[139],"unified":[140],"representation":[143],"is":[144,154],"achieved":[145,162],"by":[146],"aggregating":[147],"at":[149],"different":[150],"levels.":[151],"Our":[152],"approach":[153],"evaluated":[155],"EPIC-KITCHEN":[158],"100":[159],"dataset,":[160],"encouraging":[163],"results":[164]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}