{"id":"https:\/\/openalex.org\/W3164894587","doi":"https:\/\/doi.org\/10.1145\/3463944.3469097","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","display_name":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","publication_year":2021,"publication_date":"2021-08-20","ids":{"openalex":"https:\/\/openalex.org\/W3164894587","doi":"https:\/\/doi.org\/10.1145\/3463944.3469097","mag":"3164894587"},"language":"en","primary_location":{"id":"doi:10.1145\/3463944.3469097","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.1145\/3463944.3469097","pdf_url":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3463944.3469097","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 2021 ACM Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3463944.3469097","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https:\/\/openalex.org\/A5087719377","display_name":"Meng-Jiun Chiou","orcid":"https:\/\/orcid.org\/0000-0003-0312-9136"},"institutions":[{"id":"https:\/\/openalex.org\/I165932596","display_name":"National University of Singapore","ror":"https:\/\/ror.org\/01tgyzw49","country_code":"SG","type":"education","lineage":["https:\/\/openalex.org\/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Meng-Jiun Chiou","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https:\/\/openalex.org\/I165932596"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5040690418","display_name":"Chun-Yu Liao","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I3020783763","display_name":"Asus (Taiwan)","ror":"https:\/\/ror.org\/00bxkz165","country_code":"TW","type":"company","lineage":["https:\/\/openalex.org\/I3020783763"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Yu Liao","raw_affiliation_strings":["ASUS Intelligent Cloud Services, Taipei, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"ASUS Intelligent Cloud Services, Taipei, Taiwan Roc","institution_ids":["https:\/\/openalex.org\/I3020783763"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5100406725","display_name":"Liwei Wang","orcid":"https:\/\/orcid.org\/0000-0003-3264-1294"},"institutions":[{"id":"https:\/\/openalex.org\/I3020783763","display_name":"Asus (Taiwan)","ror":"https:\/\/ror.org\/00bxkz165","country_code":"TW","type":"company","lineage":["https:\/\/openalex.org\/I3020783763"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Wei Wang","raw_affiliation_strings":["ASUS Intelligent Cloud Services, Taipei, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"ASUS Intelligent Cloud Services, Taipei, Taiwan Roc","institution_ids":["https:\/\/openalex.org\/I3020783763"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5058575315","display_name":"Roger Zimmermann","orcid":"https:\/\/orcid.org\/0000-0002-7410-2590"},"institutions":[{"id":"https:\/\/openalex.org\/I165932596","display_name":"National University of Singapore","ror":"https:\/\/ror.org\/01tgyzw49","country_code":"SG","type":"education","lineage":["https:\/\/openalex.org\/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Roger Zimmermann","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https:\/\/openalex.org\/I165932596"]}]},{"author_position":"last","author":{"id":"https:\/\/openalex.org\/A5100668696","display_name":"Jiashi Feng","orcid":"https:\/\/orcid.org\/0000-0001-6843-0064"},"institutions":[{"id":"https:\/\/openalex.org\/I165932596","display_name":"National University of Singapore","ror":"https:\/\/ror.org\/01tgyzw49","country_code":"SG","type":"education","lineage":["https:\/\/openalex.org\/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiashi Feng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https:\/\/openalex.org\/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https:\/\/openalex.org\/A5087719377"],"corresponding_institution_ids":["https:\/\/openalex.org\/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.744,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.86606477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"17"},"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,"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,"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\/T11714","display_name":"Multimodal Machine Learning Applications","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\/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9993000030517578,"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":0.8070682287216187},{"id":"https:\/\/openalex.org\/keywords\/benchmark","display_name":"Benchmark (surveying)","score":0.6620348691940308},{"id":"https:\/\/openalex.org\/keywords\/artificial-intelligence","display_name":"Artificial intelligence","score":0.6198756098747253},{"id":"https:\/\/openalex.org\/keywords\/object","display_name":"Object (grammar)","score":0.5165706872940063},{"id":"https:\/\/openalex.org\/keywords\/masking","display_name":"Masking (illustration)","score":0.49879026412963867},{"id":"https:\/\/openalex.org\/keywords\/baseline","display_name":"Baseline (sea)","score":0.49412086606025696},{"id":"https:\/\/openalex.org\/keywords\/visualization","display_name":"Visualization","score":0.49282601475715637},{"id":"https:\/\/openalex.org\/keywords\/feature","display_name":"Feature (linguistics)","score":0.48001593351364136},{"id":"https:\/\/openalex.org\/keywords\/computer-vision","display_name":"Computer vision","score":0.4365624487400055},{"id":"https:\/\/openalex.org\/keywords\/frame","display_name":"Frame (networking)","score":0.4170319437980652},{"id":"https:\/\/openalex.org\/keywords\/construct","display_name":"Construct (python library)","score":0.4160965085029602},{"id":"https:\/\/openalex.org\/keywords\/bridge","display_name":"Bridge (graph theory)","score":0.4148534834384918},{"id":"https:\/\/openalex.org\/keywords\/object-detection","display_name":"Object detection","score":0.4146076440811157},{"id":"https:\/\/openalex.org\/keywords\/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3630219101905823}],"concepts":[{"id":"https:\/\/openalex.org\/C41008148","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q21198","display_name":"Computer science","level":0,"score":0.8070682287216187},{"id":"https:\/\/openalex.org\/C185798385","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6620348691940308},{"id":"https:\/\/openalex.org\/C154945302","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6198756098747253},{"id":"https:\/\/openalex.org\/C2781238097","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q175026","display_name":"Object (grammar)","level":2,"score":0.5165706872940063},{"id":"https:\/\/openalex.org\/C2777402240","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.49879026412963867},{"id":"https:\/\/openalex.org\/C12725497","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49412086606025696},{"id":"https:\/\/openalex.org\/C36464697","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q451553","display_name":"Visualization","level":2,"score":0.49282601475715637},{"id":"https:\/\/openalex.org\/C2776401178","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48001593351364136},{"id":"https:\/\/openalex.org\/C31972630","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q844240","display_name":"Computer vision","level":1,"score":0.4365624487400055},{"id":"https:\/\/openalex.org\/C126042441","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4170319437980652},{"id":"https:\/\/openalex.org\/C2780801425","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4160965085029602},{"id":"https:\/\/openalex.org\/C100776233","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4148534834384918},{"id":"https:\/\/openalex.org\/C2776151529","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q3045304","display_name":"Object detection","level":3,"score":0.4146076440811157},{"id":"https:\/\/openalex.org\/C153180895","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3630219101905823},{"id":"https:\/\/openalex.org\/C126322002","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11180","display_name":"Internal medicine","level":1,"score":0},{"id":"https:\/\/openalex.org\/C142362112","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q735","display_name":"Art","level":0,"score":0},{"id":"https:\/\/openalex.org\/C41895202","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q8162","display_name":"Linguistics","level":1,"score":0},{"id":"https:\/\/openalex.org\/C13280743","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q131089","display_name":"Geodesy","level":1,"score":0},{"id":"https:\/\/openalex.org\/C153349607","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q36649","display_name":"Visual arts","level":1,"score":0},{"id":"https:\/\/openalex.org\/C76155785","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q418","display_name":"Telecommunications","level":1,"score":0},{"id":"https:\/\/openalex.org\/C127313418","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1069","display_name":"Geology","level":0,"score":0},{"id":"https:\/\/openalex.org\/C71924100","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11190","display_name":"Medicine","level":0,"score":0},{"id":"https:\/\/openalex.org\/C199360897","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q9143","display_name":"Programming language","level":1,"score":0},{"id":"https:\/\/openalex.org\/C111368507","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q43518","display_name":"Oceanography","level":1,"score":0},{"id":"https:\/\/openalex.org\/C205649164","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1071","display_name":"Geography","level":0,"score":0},{"id":"https:\/\/openalex.org\/C138885662","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q5891","display_name":"Philosophy","level":0,"score":0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145\/3463944.3469097","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.1145\/3463944.3469097","pdf_url":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3463944.3469097","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 2021 ACM Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.11731","is_oa":true,"landing_page_url":"http:\/\/arxiv.org\/abs\/2105.11731","pdf_url":"https:\/\/arxiv.org\/pdf\/2105.11731","source":{"id":"https:\/\/openalex.org\/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https:\/\/openalex.org\/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https:\/\/openalex.org\/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145\/3463944.3469097","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.1145\/3463944.3469097","pdf_url":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3463944.3469097","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 2021 ACM Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https:\/\/openalex.org\/G4031921105","display_name":null,"funder_award_id":"251RES2029","funder_id":"https:\/\/openalex.org\/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https:\/\/openalex.org\/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https:\/\/ror.org\/01kcva023"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https:\/\/content.openalex.org\/works\/W3164894587.pdf","grobid_xml":"https:\/\/content.openalex.org\/works\/W3164894587.grobid-xml"},"referenced_works_count":53,"referenced_works":["https:\/\/openalex.org\/W1483019628","https:\/\/openalex.org\/W1522734439","https:\/\/openalex.org\/W1551928752","https:\/\/openalex.org\/W1677182931","https:\/\/openalex.org\/W1895577753","https:\/\/openalex.org\/W1933349210","https:\/\/openalex.org\/W1988798713","https:\/\/openalex.org\/W2146055337","https:\/\/openalex.org\/W2151103935","https:\/\/openalex.org\/W2194775991","https:\/\/openalex.org\/W2337252826","https:\/\/openalex.org\/W2479423890","https:\/\/openalex.org\/W2525778437","https:\/\/openalex.org\/W2557283755","https:\/\/openalex.org\/W2579549467","https:\/\/openalex.org\/W2610165754","https:\/\/openalex.org\/W2618799552","https:\/\/openalex.org\/W2765137706","https:\/\/openalex.org\/W2888096830","https:\/\/openalex.org\/W2888814092","https:\/\/openalex.org\/W2950761309","https:\/\/openalex.org\/W2951323451","https:\/\/openalex.org\/W2955874753","https:\/\/openalex.org\/W2962790054","https:\/\/openalex.org\/W2962844592","https:\/\/openalex.org\/W2963091558","https:\/\/openalex.org\/W2963097937","https:\/\/openalex.org\/W2963150697","https:\/\/openalex.org\/W2963165299","https:\/\/openalex.org\/W2963480047","https:\/\/openalex.org\/W2963524571","https:\/\/openalex.org\/W2963781481","https:\/\/openalex.org\/W2964225075","https:\/\/openalex.org\/W2972947807","https:\/\/openalex.org\/W2981895973","https:\/\/openalex.org\/W2982106364","https:\/\/openalex.org\/W2984933298","https:\/\/openalex.org\/W2990503944","https:\/\/openalex.org\/W2990599624","https:\/\/openalex.org\/W3009811369","https:\/\/openalex.org\/W3034679267","https:\/\/openalex.org\/W3034934229","https:\/\/openalex.org\/W3034951775","https:\/\/openalex.org\/W3035047011","https:\/\/openalex.org\/W3035598501","https:\/\/openalex.org\/W3047291707","https:\/\/openalex.org\/W3093124244","https:\/\/openalex.org\/W3096057444","https:\/\/openalex.org\/W3105177947","https:\/\/openalex.org\/W3106988096","https:\/\/openalex.org\/W3112282513","https:\/\/openalex.org\/W4251247712","https:\/\/openalex.org\/W4306979059"],"related_works":["https:\/\/openalex.org\/W2383111961","https:\/\/openalex.org\/W2365952365","https:\/\/openalex.org\/W2352448290","https:\/\/openalex.org\/W2380820513","https:\/\/openalex.org\/W2913146933","https:\/\/openalex.org\/W2372385138","https:\/\/openalex.org\/W4296359239","https:\/\/openalex.org\/W2101155126","https:\/\/openalex.org\/W2043093291","https:\/\/openalex.org\/W2363545964"],"abstract_inverted_index":{"Detecting":[0],"human-object":[1],"interactions":[2],"(HOI)":[3],"is":[4,27,30,73],"an":[5,53],"important":[6],"step":[7],"toward":[8],"a":[9,22,41,44,104,109,122,128,157,170],"comprehensive":[10],"visual":[11,148],"understanding":[12],"of":[13,108],"machines.":[14],"While":[15],"detecting":[16,93],"non-temporal":[17],"HOIs":[18,38,95,119],"(e.g.,":[19,39],"sitting":[20],"on":[21,61,117],"chair)":[23],"from":[24,43],"static":[25,63],"images":[26,64],"feasible,":[28],"it":[29],"unlikely":[31],"even":[32],"for":[33],"humans":[34],"to":[35,68,82,121],"guess":[36],"temporal-related":[37,70],"opening\/closing":[40],"door)":[42],"single":[45],"video":[46,159],"frame,":[47],"where":[48,164],"the":[49],"neighboring":[50],"frames":[51],"play":[52],"essential":[54],"role.":[55],"However,":[56],"conventional":[57],"HOI":[58,135,160],"methods":[59],"operating":[60],"only":[62],"have":[65],"been":[66],"used":[67],"predict":[69],"interactions,":[71],"which":[72],"essentially":[74],"guessing":[75],"without":[76],"temporal":[77,98,139],"contexts":[78],"and":[79,144,150],"may":[80],"lead":[81],"sub-optimal":[83],"performance.":[84],"In":[85],"this":[86,90],"paper,":[87],"we":[88],"bridge":[89],"gap":[91],"by":[92],"video-based":[94,118],"with":[96],"explicit":[97],"information.":[99],"We":[100,125,155],"first":[101],"show":[102],"that":[103],"naive":[105],"temporal-aware":[106],"variant":[107],"common":[110],"action":[111],"detection":[112],"baseline":[113],"does":[114],"not":[115],"work":[116],"due":[120],"feature-inconsistency":[123],"issue.":[124],"then":[126],"propose":[127],"simple":[129],"yet":[130],"effective":[131],"architecture":[132],"named":[133],"Spatial-Temporal":[134],"Detection":[136],"(ST-HOI)":[137],"utilizing":[138],"information":[140],"such":[141],"as":[142,169],"human":[143],"object":[145],"trajectories,":[146],"correctly-localized":[147],"features,":[149],"spatial-temporal":[151],"masking":[152],"pose":[153],"features.":[154],"construct":[156],"new":[158],"benchmark":[161],"dubbed":[162],"VidHOI":[163],"our":[165],"proposed":[166],"approach":[167],"serves":[168],"solid":[171],"baseline.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}