{"id":"https://openalex.org/W2976818183","doi":"https://doi.org/10.1109/tmm.2019.2943753","title":"Interact as You Intend: Intention-Driven Human-Object Interaction Detection","display_name":"Interact as You Intend: Intention-Driven Human-Object Interaction Detection","publication_year":2019,"publication_date":"2019-09-25","ids":{"openalex":"https://openalex.org/W2976818183","doi":"https://doi.org/10.1109/tmm.2019.2943753","mag":"2976818183"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2943753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2943753","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","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/A5101501572","display_name":"Bingjie Xu","orcid":"https://orcid.org/0000-0003-2957-8204"},"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":"Bingjie Xu","raw_affiliation_strings":["Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2957-8204","affiliations":[{"raw_affiliation_string":"Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100608759","display_name":"Junnan Li","orcid":"https://orcid.org/0000-0002-5217-9204"},"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":"Junnan Li","raw_affiliation_strings":["Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5217-9204","affiliations":[{"raw_affiliation_string":"Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020006712","display_name":"Yongkang Wong","orcid":"https://orcid.org/0000-0002-1239-4428"},"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":"Yongkang Wong","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1239-4428","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047419128","display_name":"Qi Zhao","orcid":"https://orcid.org/0000-0003-3054-8934"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota, Minneapolis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota, Minneapolis, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016415049","display_name":"Mohan Kankanhalli","orcid":"https://orcid.org/0000-0002-4846-2015"},"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":"Mohan S. Kankanhalli","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4846-2015","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101501572"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":8.1689,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.98040545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"22","issue":"6","first_page":"1423","last_page":"1432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9990000128746033,"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":0.9983999729156494,"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":0.8595724105834961},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6545288562774658},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6225178241729736},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6103461980819702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5859787464141846},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5635808706283569},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5583778023719788},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.5506576299667358},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5218293070793152},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.46205368638038635},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4488966763019562},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4294653534889221},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40260612964630127},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22154289484024048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595724105834961},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6545288562774658},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6225178241729736},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6103461980819702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5859787464141846},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5635808706283569},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5583778023719788},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.5506576299667358},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5218293070793152},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.46205368638038635},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4488966763019562},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4294653534889221},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40260612964630127},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22154289484024048},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2943753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2943753","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W874179280","https://openalex.org/W1514535095","https://openalex.org/W1536680647","https://openalex.org/W1551928752","https://openalex.org/W1861492603","https://openalex.org/W1896788142","https://openalex.org/W1976546217","https://openalex.org/W2074693532","https://openalex.org/W2102530345","https://openalex.org/W2127795553","https://openalex.org/W2143800813","https://openalex.org/W2153098120","https://openalex.org/W2156311465","https://openalex.org/W2159991108","https://openalex.org/W2169393274","https://openalex.org/W2184540135","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2212494831","https://openalex.org/W2214124602","https://openalex.org/W2479423890","https://openalex.org/W2530258459","https://openalex.org/W2559085405","https://openalex.org/W2565639579","https://openalex.org/W2591644541","https://openalex.org/W2613718673","https://openalex.org/W2732026016","https://openalex.org/W2737087486","https://openalex.org/W2737355296","https://openalex.org/W2780730359","https://openalex.org/W2789158025","https://openalex.org/W2795378892","https://openalex.org/W2798558457","https://openalex.org/W2798685833","https://openalex.org/W2801004733","https://openalex.org/W2808699053","https://openalex.org/W2888096830","https://openalex.org/W2888814092","https://openalex.org/W2896659472","https://openalex.org/W2962716332","https://openalex.org/W2962794823","https://openalex.org/W2963097937","https://openalex.org/W2963480047","https://openalex.org/W2963649796","https://openalex.org/W2964225075","https://openalex.org/W6630875275","https://openalex.org/W6632922691","https://openalex.org/W6639102338","https://openalex.org/W6678830454","https://openalex.org/W6686360814","https://openalex.org/W6748822025","https://openalex.org/W6754152559"],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W3014378845","https://openalex.org/W2378211422","https://openalex.org/W4240909707","https://openalex.org/W2059546927","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W4287991909","https://openalex.org/W4390721878"],"abstract_inverted_index":{"The":[0,160],"recent":[1],"advances":[2],"in":[3,28,42,49,92,129],"instance-level":[4],"detection":[5,101],"tasks":[6,62],"lay":[7],"strong":[8],"foundation":[9],"for":[10,56],"genuine":[11],"comprehension":[12],"of":[13,51,146,162],"the":[14,18,96,108,115,125,144],"visual":[15],"scenes.":[16],"However,":[17],"ability":[19],"to":[20,88,114,123,142],"fully":[21],"comprehend":[22],"a":[23,84,130,137],"social":[24,43,61],"scene":[25,44],"is":[26,47],"still":[27],"its":[29],"preliminary":[30],"stage.":[31],"In":[32,133],"this":[33,80],"work,":[34],"we":[35,82,135],"focus":[36],"on":[37,75,79,152],"detecting":[38],"human-object":[39],"interactions":[40],"(HOIs)":[41],"images,":[45],"which":[46],"demanding":[48],"terms":[50],"research":[52],"and":[53,70,158],"increasingly":[54],"useful":[55],"practical":[57],"applications.":[58],"To":[59],"undertake":[60],"interacting":[63],"with":[64,107],"objects,":[65],"humans":[66],"direct":[67],"their":[68,72,76],"attention":[69],"move":[71],"body":[73,112],"based":[74],"intention.":[77],"Based":[78],"observation,":[81],"provide":[83],"unique":[85],"computational":[86],"perspective":[87],"explore":[89],"human":[90,98,105,121],"intention":[91],"HOI":[93,100],"detection.":[94],"Specifically,":[95],"proposed":[97,164],"intention-driven":[99],"(iHOI)":[102],"framework":[103],"models":[104],"pose":[106],"relative":[109],"distances":[110],"from":[111],"joints":[113],"object":[116],"instances.":[117],"It":[118],"also":[119,167],"utilizes":[120],"gaze":[122],"guide":[124],"attended":[126],"contextual":[127],"regions":[128],"weakly-supervised":[131],"setting.":[132],"addition,":[134],"propose":[136],"hard":[138],"negative":[139],"sampling":[140],"strategy":[141],"address":[143],"problem":[145],"mis-grouping.":[147],"We":[148],"perform":[149],"extensive":[150],"experiments":[151],"two":[153],"benchmark":[154],"datasets,":[155],"namely":[156],"V-COCO":[157],"HICO-DET.":[159],"efficacy":[161],"each":[163],"component":[165],"has":[166],"been":[168],"validated.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}