{"id":"https://openalex.org/W7131087677","doi":"https://doi.org/10.1109/robio66223.2025.11376009","title":"Real-Time Human-Object Interaction Recognition Using Minimal Keypoints and Bi-LSTM for Imitation Learning","display_name":"Real-Time Human-Object Interaction Recognition Using Minimal Keypoints and Bi-LSTM for Imitation Learning","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7131087677","doi":"https://doi.org/10.1109/robio66223.2025.11376009"},"language":null,"primary_location":{"id":"doi:10.1109/robio66223.2025.11376009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11376009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5099583371","display_name":"Jagannatha Charjee Pyaraka","orcid":"https://orcid.org/0000-0002-1067-8945"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jagannatha Charjee Pyaraka","raw_affiliation_strings":["Swinburne University of Technology,Department of Mechanical and Product Design Engineering,Hawthorn,VIC,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology,Department of Mechanical and Product Design Engineering,Hawthorn,VIC,Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033590604","display_name":"Mats Isaksson","orcid":"https://orcid.org/0000-0003-3047-6811"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mats Isaksson","raw_affiliation_strings":["Swinburne University of Technology,Department of Mechanical and Product Design Engineering,Hawthorn,VIC,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology,Department of Mechanical and Product Design Engineering,Hawthorn,VIC,Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083242794","display_name":"John McCormick","orcid":"https://orcid.org/0000-0002-5347-0378"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"John McCormick","raw_affiliation_strings":["Centre for Transformative Media Technologies, Swinburne University of Technology,Hawthorn,VIC,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Transformative Media Technologies, Swinburne University of Technology,Hawthorn,VIC,Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042792890","display_name":"Fouad Sukkar","orcid":"https://orcid.org/0000-0002-7041-5151"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fouad Sukkar","raw_affiliation_strings":["UTS Robotics Institute and Centre for Advanced Manufacturing, University of Technology Sydney,Ultimo,NSW,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UTS Robotics Institute and Centre for Advanced Manufacturing, University of Technology Sydney,Ultimo,NSW,Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031338128","display_name":"Sheila Sutjipto","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sheila Sutjipto","raw_affiliation_strings":["UTS Robotics Institute and Centre for Advanced Manufacturing, University of Technology Sydney,Ultimo,NSW,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UTS Robotics Institute and Centre for Advanced Manufacturing, University of Technology Sydney,Ultimo,NSW,Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"615","last_page":"620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.4359999895095825,"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":0.4359999895095825,"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":0.22529999911785126,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.05959999933838844,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5372999906539917},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.49160000681877136},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4357999861240387},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.430400013923645},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42739999294281006},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.4172999858856201},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.3856000006198883},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3711000084877014},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.36010000109672546}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.807200014591217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753000259399414},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5613999962806702},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.430400013923645},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.36010000109672546},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio66223.2025.11376009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11376009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":12,"referenced_works":["https://openalex.org/W2963076818","https://openalex.org/W3081268564","https://openalex.org/W3203092975","https://openalex.org/W4313176000","https://openalex.org/W4383709763","https://openalex.org/W4384436109","https://openalex.org/W4385767975","https://openalex.org/W4387501242","https://openalex.org/W4390142036","https://openalex.org/W4390872886","https://openalex.org/W4400911255","https://openalex.org/W4407467080"],"related_works":[],"abstract_inverted_index":{"Human-object":[0],"interaction":[1],"(HOI)":[2],"recognition":[3,53],"from":[4,63],"video":[5],"is":[6],"necessary":[7],"for":[8,37,148],"robotic":[9],"imitation":[10,149],"learning,":[11],"enabling":[12],"robots":[13],"to":[14],"effectively":[15],"interpret":[16],"and":[17,59,79,98,107,117,129,144,157],"replicate":[18],"human":[19],"actions.":[20],"Existing":[21],"approaches":[22],"typically":[23],"rely":[24],"on":[25,94],"computationally":[26],"intensive":[27],"models":[28],"or":[29],"require":[30],"extensive":[31],"annotated":[32],"datasets,":[33],"making":[34],"them":[35],"unsuitable":[36],"real-time":[38,51],"deployment":[39],"in":[40,151,155],"resource-constrained":[41],"environments.":[42],"To":[43],"address":[44],"these":[45],"limitations,":[46],"we":[47],"propose":[48],"a":[49,84,142],"lightweight,":[50],"HOI":[52],"framework":[54,140],"that":[55,111],"leverages":[56],"only":[57],"wrist":[58,70],"object":[60,73],"keypoints":[61],"extracted":[62],"2D":[64],"videos.":[65],"Our":[66],"method":[67],"integrates":[68],"MediaPipe-based":[69],"tracking":[71],"with":[72,91],"centroid":[74],"detection":[75],"via":[76],"color":[77],"segmentation":[78],"captures":[80],"temporal":[81,119],"interactions":[82],"using":[83],"Bidirectional":[85],"Long":[86],"Short-Term":[87],"Memory":[88],"(Bi-LSTM)":[89],"enhanced":[90],"attention.":[92],"Evaluations":[93],"the":[95,124,131],"GRAB":[96],"dataset":[97],"additional":[99],"real-world":[100],"videos":[101],"featuring":[102],"unseen":[103],"individuals,":[104],"diverse":[105],"objects,":[106],"challenging":[108],"backgrounds":[109],"demonstrate":[110],"our":[112],"model":[113],"maintains":[114],"consistent":[115],"accuracy":[116],"robust":[118],"segmentation.":[120],"Ablation":[121],"studies":[122],"validate":[123],"effectiveness":[125],"of":[126,134],"attention":[127],"mechanisms":[128],"assess":[130],"incremental":[132],"benefit":[133],"including":[135],"elbow":[136],"keypoints.":[137],"The":[138],"proposed":[139],"offers":[141],"practical":[143],"efficient":[145],"solution":[146],"suitable":[147],"learning":[150],"robotics":[152],"applications,":[153],"particularly":[154],"edge":[156],"low-resource":[158],"scenarios.":[159]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-24T00:00:00"}