{"id":"https://openalex.org/W4294069223","doi":"https://doi.org/10.1109/icce-taiwan55306.2022.9869188","title":"Scene Retrieval in Soccer Videos by Spatial-temporal Attention with Video Vision Transformer","display_name":"Scene Retrieval in Soccer Videos by Spatial-temporal Attention with Video Vision Transformer","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4294069223","doi":"https://doi.org/10.1109/icce-taiwan55306.2022.9869188"},"language":"en","primary_location":{"id":"doi:10.1109/icce-taiwan55306.2022.9869188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-taiwan55306.2022.9869188","pdf_url":null,"source":{"id":"https://openalex.org/S4363607852","display_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","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":["Graduate School of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"453","last_page":"454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8248441815376282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6896206140518188},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6892937421798706},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6628768444061279},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5583253502845764},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5365137457847595},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5163382291793823},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.488094687461853},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37016671895980835},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10282745957374573},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07700416445732117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248441815376282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6896206140518188},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6892937421798706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6628768444061279},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5583253502845764},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5365137457847595},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5163382291793823},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.488094687461853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37016671895980835},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10282745957374573},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07700416445732117},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce-taiwan55306.2022.9869188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-taiwan55306.2022.9869188","pdf_url":null,"source":{"id":"https://openalex.org/S4363607852","display_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2767415038","https://openalex.org/W2980821210","https://openalex.org/W3094502228","https://openalex.org/W3126721948","https://openalex.org/W3157698519","https://openalex.org/W3186413649","https://openalex.org/W4214612132","https://openalex.org/W6784333009","https://openalex.org/W6790307280","https://openalex.org/W6796707148"],"related_works":["https://openalex.org/W2389818373","https://openalex.org/W2220831889","https://openalex.org/W4304700937","https://openalex.org/W4312683641","https://openalex.org/W3027421045","https://openalex.org/W2576320324","https://openalex.org/W2980386803","https://openalex.org/W3215994059","https://openalex.org/W2319823519","https://openalex.org/W4206798987"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,43,82],"scene":[4,60,84],"retrieval":[5,121],"method":[6,118],"in":[7],"soccer":[8,16,36,59,77],"videos":[9],"with":[10,42,103],"video":[11],"vision":[12],"Transformer":[13],"(ViViT).":[14],"In":[15],"coaching,":[17],"it":[18],"is":[19],"difficult":[20],"for":[21],"the":[22,27,32,53,58,62,70,93,98,101,116,125],"training":[23],"staff":[24],"to":[25,124],"find":[26],"required":[28],"scenes":[29,87],"efficiently":[30],"from":[31],"large":[33],"number":[34],"of":[35,57,69,76],"videos.":[37],"We":[38,48,79,106],"tackle":[39],"this":[40],"problem":[41],"simple":[44],"yet":[45],"effective":[46],"method.":[47],"train":[49],"ViViT":[50,64,72,95],"and":[51,85,96],"obtain":[52],"output":[54,67,89],"token":[55,90],"features":[56,91],"by":[61],"pre-trained":[63,71,94],"model.":[65],"The":[66,111],"tokens":[68,102],"contain":[73],"spatio-temporal":[74],"information":[75],"scenes.":[78],"then":[80],"transform":[81],"query":[83],"candidate":[86],"into":[88],"using":[92],"calculate":[97],"similarity":[99],"between":[100],"cosine":[104],"similarity.":[105],"conducted":[107],"experiments":[108],"on":[109],"SoccerNet-V2dataset.":[110],"experimental":[112],"results":[113],"show":[114],"that":[115],"proposed":[117],"achieves":[119],"outstanding":[120],"accuracy":[122],"compared":[123],"previous":[126],"methods.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
