{"id":"https://openalex.org/W4379653494","doi":"https://doi.org/10.1117/12.2679426","title":"Adaptive spatial and temporal aggregation for table tennis shot recognition","display_name":"Adaptive spatial and temporal aggregation for table tennis shot recognition","publication_year":2023,"publication_date":"2023-06-07","ids":{"openalex":"https://openalex.org/W4379653494","doi":"https://doi.org/10.1117/12.2679426"},"language":"en","primary_location":{"id":"doi:10.1117/12.2679426","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.2679426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth International Conference on Machine Vision (ICMV 2022)","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/A5058255642","display_name":"Sravani Yenduri","orcid":"https://orcid.org/0000-0001-6651-4360"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sravani Yenduri","raw_affiliation_strings":["Indian Institute of Technology Hyderabad (India)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad (India)","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113387174","display_name":"Vishnu Chalavadi","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vishnu Chalavadi","raw_affiliation_strings":["Indian Institute of Technology Hyderabad (India)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad (India)","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012566120","display_name":"C. Krishna Mohan","orcid":"https://orcid.org/0000-0002-7316-0836"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishna Mohan C","raw_affiliation_strings":["Indian Institute of Technology Hyderabad (India)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad (India)","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65181880"],"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":"23","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9921000003814697,"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":0.9921000003814697,"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/T11246","display_name":"Sports injuries and prevention","score":0.9491000175476074,"subfield":{"id":"https://openalex.org/subfields/2732","display_name":"Orthopedics and Sports Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9449999928474426,"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/computer-science","display_name":"Computer science","score":0.8482087850570679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6334633827209473},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5919798612594604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5724496841430664},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5562602281570435},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49504581093788147},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46566227078437805},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4175989627838135},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4151257574558258},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3342322111129761},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22959545254707336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482087850570679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6334633827209473},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5919798612594604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5724496841430664},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5562602281570435},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49504581093788147},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46566227078437805},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4175989627838135},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4151257574558258},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3342322111129761},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22959545254707336},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2679426","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.2679426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth International Conference on Machine Vision (ICMV 2022)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W2810679507"],"abstract_inverted_index":{"Action":[0],"recognition":[1,314],"is":[2,182],"one":[3],"of":[4,22,49,85,102,105,118,127,161,196,209,248,254,265,291,308],"the":[5,20,42,116,143,149,191,204,207,210,223,232,240,246,262,274,279,289,298,306],"challenging":[6],"video":[7],"understanding":[8],"tasks":[9],"in":[10,19,31,77,110],"computer":[11],"vision.":[12],"Although":[13],"there":[14],"has":[15],"been":[16,64],"extensive":[17],"research":[18],"task":[21],"classifying":[23],"coarse-grained":[24],"actions,":[25],"existing":[26,292],"methods":[27,294],"are":[28,74],"still":[29],"limited":[30],"differentiating":[32],"actions":[33,108],"with":[34,81,239],"low":[35,155],"inter-class":[36,51,156],"and":[37,56,69,136,145,154,173,193,318],"high":[38,50],"intra-class":[39],"variation.":[40],"Particularly,":[41],"table":[43,128,197],"tennis":[44,97,129,198,300],"sport":[45],"that":[46,140,189,284],"involves":[47],"shots":[48,86,98,153,280,301],"similarity,":[52],"subtle":[53,150],"variations,":[54],"occlusion,":[55],"view-point":[57],"variations.":[58,157],"While":[59],"a":[60,78,82,95,183],"few":[61],"datasets":[62],"have":[63],"available":[65],"for":[66],"event":[67],"spotting":[68],"shot":[70],"recognition,":[71],"these":[72,124],"benchmarks":[73],"mostly":[75],"recorded":[76],"constrained":[79],"environment":[80],"clear":[83],"view/perception":[84],"executed":[87],"by":[88,295],"players.":[89,120],"In":[90,200],"this":[91],"paper,":[92],"we":[93,131,216,228],"introduce":[94],"Table":[96,299],"1.0":[99,302],"dataset":[100],"consisting":[101],"9000":[103],"videos":[104],"6":[106],"fine-grained":[107],"collected":[109],"an":[111,133],"unconstrained":[112],"manner":[113],"to":[114,202,221,230,244,252,272],"analyze":[115],"performance":[117,290,307],"both":[119],"To":[121],"effectively":[122],"recognise":[123],"different":[125],"types":[126],"shots,":[130],"propose":[132,229],"adaptive":[134],"spatial":[135,144,170,192,218,225],"temporal":[137,146,175,194,241,255,258,276],"aggregation":[138,171,176,219,242,259],"method":[139,159],"can":[141],"handle":[142],"interactions":[147,277],"concerning":[148],"variations":[151],"among":[152,206,278],"Our":[158],"consists":[160],"three":[162],"components,":[163],"namely,":[164,316],"(i)":[165],"feature":[166,179,213],"extraction":[167,180],"module,":[168],"(ii)":[169],"network,":[172],"(iii)":[174],"network.":[177],"The":[178],"module":[181],"3D":[184],"convolutional":[185],"neural":[186],"network":[187,220,243,260],"(3D-CNN)":[188],"captures":[190],"characteristics":[195],"shots.":[199],"order":[201],"capture":[203],"interaction":[205],"elements":[208],"extracted":[211],"3D-CNN":[212,293],"maps":[214],"efficiently,":[215],"employ":[217],"obtain":[222],"compact":[224],"representation.":[226],"Later,":[227],"replace":[231],"final":[233],"global":[234],"average":[235],"pooling":[236],"layer":[237],"(GAP)":[238],"overcome":[245],"loss":[247],"motion":[249],"information":[250],"due":[251],"averaging":[253],"features.":[256],"This":[257],"utilizes":[261],"attention":[263],"mechanism":[264],"bidirectional":[266],"encoder":[267],"representations":[268],"from":[269],"Transformers":[270],"(BERT)":[271],"model":[273],"significant":[275],"effectively.":[281],"We":[282],"demonstrate":[283],"our":[285,309],"proposed":[286],"approach":[287,310],"improves":[288],"~10%":[296],"on":[297,311],"dataset.We":[303],"also":[304],"show":[305],"other":[312],"action":[313],"datasets,":[315],"UCF-101":[317],"HMDB-51.":[319]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}