{"id":"https://openalex.org/W4292794185","doi":"https://doi.org/10.1109/icmew56448.2022.9859304","title":"Transformer Based Multimodal Scene Recognition in Soccer Videos","display_name":"Transformer Based Multimodal Scene Recognition in Soccer Videos","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4292794185","doi":"https://doi.org/10.1109/icmew56448.2022.9859304"},"language":"en","primary_location":{"id":"doi:10.1109/icmew56448.2022.9859304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew56448.2022.9859304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038719961","display_name":"Yaozong Gan","orcid":"https://orcid.org/0009-0001-8813-3400"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yaozong Gan","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology","Graduate School of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology","Faculty of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology","Faculty of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology","Faculty of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9936000108718872,"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/T11309","display_name":"Music and Audio Processing","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.787445068359375},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7234285473823547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6697264909744263},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6438597440719604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6159802079200745},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5029470324516296},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4399247467517853},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.434100478887558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42817503213882446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34148621559143066},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1470959484577179},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10690271854400635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787445068359375},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7234285473823547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6697264909744263},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6438597440719604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6159802079200745},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5029470324516296},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4399247467517853},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.434100478887558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42817503213882446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34148621559143066},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1470959484577179},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10690271854400635},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew56448.2022.9859304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew56448.2022.9859304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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":29,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1999956262","https://openalex.org/W2141858776","https://openalex.org/W2594779473","https://openalex.org/W2890013721","https://openalex.org/W2962387962","https://openalex.org/W2964308564","https://openalex.org/W2980858082","https://openalex.org/W3034822180","https://openalex.org/W3094502228","https://openalex.org/W3117450517","https://openalex.org/W3126721948","https://openalex.org/W3154596443","https://openalex.org/W3157698519","https://openalex.org/W3161686435","https://openalex.org/W3186413649","https://openalex.org/W3190286596","https://openalex.org/W3196974791","https://openalex.org/W4214612132","https://openalex.org/W4385245566","https://openalex.org/W6631456553","https://openalex.org/W6650430342","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6788071488","https://openalex.org/W6790307280","https://openalex.org/W6793736971"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W4283332100"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,48,92,106],"transformer-based":[4],"multimodal":[5],"soccer":[6,29,60,86,107],"scene":[7],"recognition":[8],"method":[9,113,121],"for":[10],"both":[11,64],"visual":[12,96],"and":[13,24,50,67,97,117,130],"audio":[14,25,68,98],"modalities.":[15],"Our":[16],"approach":[17],"directly":[18],"uses":[19],"the":[20,28,32,35,41,45,51,59,73,111,123,128],"original":[21],"video":[22,30,65],"frames":[23,66],"spectrogram":[26,69],"from":[27,72],"as":[31],"input":[33],"of":[34,44,95,105],"transformer":[36,74],"model,":[37],"which":[38],"can":[39],"capture":[40],"spatial":[42],"information":[43,54,70,104],"action":[46],"at":[47],"moment":[49],"contextual":[52],"temporal":[53],"between":[55],"different":[56],"actions":[57],"in":[58,76,84],"videos.":[61],"We":[62,109],"fuse":[63],"output":[71],"model":[75],"order":[77],"to":[78,101],"better":[79],"identify":[80],"scenes":[81],"that":[82,119],"occur":[83],"real":[85],"matches.":[87],"The":[88],"late":[89],"fusion":[90],"performs":[91],"weighted":[93],"average":[94],"estimation":[99],"results":[100],"obtain":[102],"complete":[103],"scene.":[108],"evaluate":[110],"proposed":[112],"on":[114],"SoccerNet-V2":[115],"dataset":[116],"confirm":[118],"our":[120],"achieves":[122],"best":[124],"performance":[125],"compared":[126],"with":[127],"recent":[129],"state-of-the-art":[131],"methods.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}
