{"id":"https://openalex.org/W4298129964","doi":"https://doi.org/10.1145/3552437.3555693","title":"A Transformer-based System for Action Spotting in Soccer Videos","display_name":"A Transformer-based System for Action Spotting in Soccer Videos","publication_year":2022,"publication_date":"2022-09-30","ids":{"openalex":"https://openalex.org/W4298129964","doi":"https://doi.org/10.1145/3552437.3555693"},"language":"en","primary_location":{"id":"doi:10.1145/3552437.3555693","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552437.3555693","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552437.3555693","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3552437.3555693","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044028436","display_name":"He Zhu","orcid":"https://orcid.org/0000-0001-9022-6158"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059207044","display_name":"Junwei Liang","orcid":"https://orcid.org/0000-0003-2219-5569"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Liang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026298162","display_name":"Chengzhi Lin","orcid":"https://orcid.org/0000-0002-8049-3989"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengzhi Lin","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433042","display_name":"Jun Zhang","orcid":"https://orcid.org/0000-0001-5579-7094"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101570773","display_name":"Jianming Hu","orcid":"https://orcid.org/0000-0001-8065-7309"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianming Hu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9796000123023987,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.9210095405578613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.812275767326355},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7794139981269836},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7109698057174683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6117048263549805},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5561620593070984},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.5191173553466797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4601071774959564},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4405346214771271},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3927780091762543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3402629494667053},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.24875083565711975},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08947420120239258}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9210095405578613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812275767326355},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7794139981269836},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7109698057174683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6117048263549805},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5561620593070984},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.5191173553466797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4601071774959564},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4405346214771271},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3927780091762543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3402629494667053},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.24875083565711975},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08947420120239258},{"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/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3552437.3555693","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552437.3555693","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552437.3555693","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3552437.3555693","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552437.3555693","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552437.3555693","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4298129964.pdf","grobid_xml":"https://content.openalex.org/works/W4298129964.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1586730761","https://openalex.org/W1655729963","https://openalex.org/W1969876830","https://openalex.org/W2024868105","https://openalex.org/W2141858776","https://openalex.org/W2156198860","https://openalex.org/W2583815496","https://openalex.org/W2617934722","https://openalex.org/W2672451823","https://openalex.org/W2746441252","https://openalex.org/W2755876276","https://openalex.org/W2766402183","https://openalex.org/W2890013721","https://openalex.org/W2952435096","https://openalex.org/W2962387962","https://openalex.org/W2963446712","https://openalex.org/W2963524571","https://openalex.org/W2986407524","https://openalex.org/W2990503944","https://openalex.org/W3010426832","https://openalex.org/W3034822180","https://openalex.org/W3035251589","https://openalex.org/W3069380482","https://openalex.org/W3094502228","https://openalex.org/W3100481960","https://openalex.org/W3106041614","https://openalex.org/W3186413649","https://openalex.org/W3190009776","https://openalex.org/W3190286596","https://openalex.org/W4214614183","https://openalex.org/W4244248726","https://openalex.org/W4292828059","https://openalex.org/W7074610650"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638","https://openalex.org/W1989658893"],"abstract_inverted_index":{"Action":[0,88],"Spotting":[1,89],"in":[2,29,86],"the":[3,35,43,62,71,87,102],"broadcast":[4],"soccer":[5,30],"game":[6],"is":[7],"important":[8],"to":[9,39,52,66,69],"understand":[10],"salient":[11],"actions":[12],"and":[13,57,83,100,104],"video":[14],"summary":[15],"applications.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20,46],"propose":[21],"an":[22],"efficient":[23],"transformer-based":[24],"system":[25],"for":[26],"action":[27],"spotting":[28],"videos.":[31,44],"We":[32],"first":[33],"use":[34],"multi-scale":[36],"vision":[37],"transformer":[38],"extract":[40],"features":[41,56,63],"from":[42],"Then":[45],"adopt":[47],"a":[48,78],"sliding":[49],"window":[50],"strategy":[51],"further":[53],"utilize":[54],"temporal":[55,59],"enhanced":[58],"understanding.":[60],"Finally,":[61],"are":[64],"input":[65],"NetVLAD++":[67],"model":[68,75],"obtain":[70],"final":[72],"results.":[73],"Our":[74,95],"can":[76],"learn":[77],"hierarchy":[79],"of":[80,91],"robust":[81],"representations":[82],"perform":[84],"well":[85],"Task":[90],"SoccerNet":[92],"Challenge":[93],"2022.":[94],"method":[96],"achieves":[97],"excellent":[98],"results":[99],"outperforms":[101],"baseline":[103],"previous":[105],"published":[106],"works.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}