{"id":"https://openalex.org/W3199612070","doi":"https://doi.org/10.1109/tip.2021.3113114","title":"Action Anticipation Using Pairwise Human-Object Interactions and Transformers","display_name":"Action Anticipation Using Pairwise Human-Object Interactions and Transformers","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3199612070","doi":"https://doi.org/10.1109/tip.2021.3113114","mag":"3199612070","pmid":"https://pubmed.ncbi.nlm.nih.gov/34550884"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3113114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3113114","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5060306211","display_name":"Debaditya Roy","orcid":"https://orcid.org/0000-0002-8779-1241"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Debaditya Roy","raw_affiliation_strings":["Institute of High-Performance Computing (IHPC), A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High-Performance Computing (IHPC), A*STAR, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090467618","display_name":"Basura Fernando","orcid":"https://orcid.org/0000-0002-6920-9916"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Basura Fernando","raw_affiliation_strings":["Institute of High-Performance Computing (IHPC), A*STAR, Singapore","Institute of High-Performance Computing (IHPC), A*STAR, 1 Fusionopolis Way #08-10 Connexis North, 138632, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High-Performance Computing (IHPC), A*STAR, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute of High-Performance Computing (IHPC), A*STAR, 1 Fusionopolis Way #08-10 Connexis North, 138632, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060306211"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"],"apc_list":null,"apc_paid":null,"fwci":2.4978,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.91160131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"8116","last_page":"8129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9955999851226807,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9950000047683716,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.7364377975463867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6663823127746582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6549307107925415},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.6399424076080322},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4970269501209259},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.4789365231990814},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4064747095108032},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36426371335983276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3218349814414978},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.2139931321144104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10077130794525146},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0987536609172821}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7364377975463867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6663823127746582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6549307107925415},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.6399424076080322},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4970269501209259},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.4789365231990814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4064747095108032},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36426371335983276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3218349814414978},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2139931321144104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10077130794525146},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0987536609172821},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2021.3113114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3113114","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:34550884","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34550884","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1457887009","display_name":null,"funder_award_id":"AISG-RP-2019-010","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G3917087662","display_name":null,"funder_award_id":"AISG2-RP-2020-016","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":99,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1483019628","https://openalex.org/W1485009520","https://openalex.org/W1861492603","https://openalex.org/W1892016050","https://openalex.org/W1899504021","https://openalex.org/W1983496390","https://openalex.org/W2048192550","https://openalex.org/W2099614498","https://openalex.org/W2104657103","https://openalex.org/W2109698606","https://openalex.org/W2114216982","https://openalex.org/W2116022929","https://openalex.org/W2124592697","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2147615062","https://openalex.org/W2156387975","https://openalex.org/W2193145675","https://openalex.org/W2202226326","https://openalex.org/W2204257188","https://openalex.org/W2235735853","https://openalex.org/W2339712187","https://openalex.org/W2402869773","https://openalex.org/W2422305492","https://openalex.org/W2550143307","https://openalex.org/W2592008540","https://openalex.org/W2605300166","https://openalex.org/W2746692960","https://openalex.org/W2770804203","https://openalex.org/W2786807178","https://openalex.org/W2808675313","https://openalex.org/W2883275382","https://openalex.org/W2885024018","https://openalex.org/W2888096830","https://openalex.org/W2894666173","https://openalex.org/W2913636123","https://openalex.org/W2936614765","https://openalex.org/W2945792291","https://openalex.org/W2951702519","https://openalex.org/W2960747818","https://openalex.org/W2962688385","https://openalex.org/W2962839378","https://openalex.org/W2962929176","https://openalex.org/W2963091558","https://openalex.org/W2963097937","https://openalex.org/W2963150697","https://openalex.org/W2963165299","https://openalex.org/W2963363102","https://openalex.org/W2963403868","https://openalex.org/W2963405520","https://openalex.org/W2963563276","https://openalex.org/W2963564348","https://openalex.org/W2963570630","https://openalex.org/W2963853051","https://openalex.org/W2964193299","https://openalex.org/W2964217160","https://openalex.org/W2964308564","https://openalex.org/W2964308810","https://openalex.org/W2989506443","https://openalex.org/W2989839235","https://openalex.org/W2993447238","https://openalex.org/W3009811369","https://openalex.org/W3020843970","https://openalex.org/W3021013305","https://openalex.org/W3021948998","https://openalex.org/W3022272795","https://openalex.org/W3034667697","https://openalex.org/W3034994895","https://openalex.org/W3035029089","https://openalex.org/W3037916678","https://openalex.org/W3085043532","https://openalex.org/W3096383329","https://openalex.org/W3106250896","https://openalex.org/W3109813419","https://openalex.org/W3161197088","https://openalex.org/W3175928291","https://openalex.org/W4287778673","https://openalex.org/W4288104375","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6639569935","https://openalex.org/W6677265961","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682889407","https://openalex.org/W6712886282","https://openalex.org/W6733956904","https://openalex.org/W6739901393","https://openalex.org/W6748310659","https://openalex.org/W6753596515","https://openalex.org/W6758736441","https://openalex.org/W6761549388","https://openalex.org/W6765991202","https://openalex.org/W6767337265","https://openalex.org/W6772408192","https://openalex.org/W6776598532","https://openalex.org/W6780677595","https://openalex.org/W6796429242"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W3049116993","https://openalex.org/W1541884709","https://openalex.org/W2589081601","https://openalex.org/W2226037301","https://openalex.org/W2026855223","https://openalex.org/W2070708245"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,62,78],"anticipate":[3],"future":[4],"actions":[5,29],"of":[6,33,94,104,110,144,188,210],"humans":[7],"is":[8,121,215],"useful":[9],"in":[10,51,86,107,149],"application":[11],"areas":[12],"such":[13],"as":[14],"automated":[15],"driving,":[16],"robot-assisted":[17],"manufacturing,":[18],"and":[19,26,129,181,196,198,213],"smart":[20],"homes.":[21],"These":[22],"applications":[23],"require":[24,43],"representing":[25],"anticipating":[27],"human":[28],"involving":[30],"the":[31,52,56,80,95,111,176,186,208],"use":[32,38,76],"objects.":[34],"Existing":[35],"methods":[36],"that":[37,54,97,116,136,174,207],"human-object":[39,66,84,105,211],"interactions":[40],"for":[41,47,124,141,162,218],"anticipation":[42,126,152],"object":[44,50],"affordance":[45],"labels":[46],"every":[48,64,108],"relevant":[49],"scene":[53],"match":[55],"ongoing":[57],"action.":[58],"Hence,":[59],"we":[60,75,134,158,205],"propose":[61,159],"represent":[63],"pairwise":[65],"(HO)":[67],"interaction":[68],"using":[69,137],"only":[70],"their":[71],"visual":[72],"features.":[73],"Next,":[74],"cross-correlation":[77,117],"capture":[79],"second-order":[81,131],"statistics":[82],"across":[83,178],"pairs":[85,106],"a":[87,91,101,138],"frame.":[88],"Cross-correlation":[89],"produces":[90],"holistic":[92],"representation":[93,120,212],"frame":[96,109,119],"can":[98],"also":[99],"handle":[100],"variable":[102],"number":[103],"observation":[112],"period.":[113],"We":[114,184],"show":[115,185],"based":[118],"more":[122],"suited":[123],"action":[125,151],"than":[127,153],"attention-based":[128],"other":[130,154],"approaches.":[132],"Furthermore,":[133],"observe":[135],"transformer":[139,168],"model":[140,173],"temporal":[142,155],"aggregation":[143],"frame-wise":[145],"HO":[146,182],"representations":[147],"results":[148],"better":[150],"networks.":[156],"So,":[157],"two":[160],"approaches":[161],"constructing":[163],"an":[164,199],"end-to-end":[165],"trainable":[166],"multi-modal":[167],"(MM-Transformer;":[169],"code":[170],"at":[171],"https://github.com/debadityaroy/MM-Transformer_ActAnt)":[172],"combines":[175],"evidence":[177],"spatio-temporal,":[179],"motion,":[180],"representations.":[183],"performance":[187],"MM-Transformer":[189],"on":[190],"procedural":[191],"datasets":[192],"like":[193,202],"50":[194],"Salads":[195],"Breakfast,":[197],"unscripted":[200],"dataset":[201],"EPIC-KITCHENS55.":[203],"Finally,":[204],"demonstrate":[206],"combination":[209],"MM-Transformers":[214],"effective":[216],"even":[217],"long-term":[219],"anticipation.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}