{"id":"https://openalex.org/W7125920636","doi":"https://doi.org/10.1109/smc58881.2025.11343249","title":"M <sup>2</sup> ST-Net: Human-Object Interaction Recognition Using A Multi-stream Multi-feature Spatial-Temporal Network","display_name":"M <sup>2</sup> ST-Net: Human-Object Interaction Recognition Using A Multi-stream Multi-feature Spatial-Temporal Network","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125920636","doi":"https://doi.org/10.1109/smc58881.2025.11343249"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343249","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 Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5124075758","display_name":"Bohong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bohong Wu","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124075027","display_name":"Qing Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Gao","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124078988","display_name":"Yuanchuan Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchuan Lai","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124092024","display_name":"Huiwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104064","display_name":"Shenzhen Academy of Robotics","ror":"https://ror.org/01h027j09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210104064"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiwen Zhang","raw_affiliation_strings":["Pudu Robotics,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Pudu Robotics,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210104064"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124075758"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72751859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7434","last_page":"7440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.3418999910354614,"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":0.3418999910354614,"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":0.3156000077724457,"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":0.13750000298023224,"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/encoder","display_name":"Encoder","score":0.558899998664856},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5580000281333923},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4611000120639801},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.43389999866485596},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42890000343322754},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.38940000534057617},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.37369999289512634},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723000049591064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6202999949455261},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4878999888896942},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4611000120639801},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.43389999866485596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43149998784065247},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.29030001163482666},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343249","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 Systems, Man, and Cybernetics (SMC)","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":36,"referenced_works":["https://openalex.org/W1984170749","https://openalex.org/W2146055337","https://openalex.org/W2479423890","https://openalex.org/W2550143307","https://openalex.org/W2963097937","https://openalex.org/W2963853051","https://openalex.org/W2964225075","https://openalex.org/W2981773282","https://openalex.org/W2982232158","https://openalex.org/W3009916215","https://openalex.org/W3035598501","https://openalex.org/W3164894587","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3176070213","https://openalex.org/W3181762391","https://openalex.org/W3202241806","https://openalex.org/W3207158043","https://openalex.org/W3213438563","https://openalex.org/W4205518878","https://openalex.org/W4205564931","https://openalex.org/W4214607465","https://openalex.org/W4226334913","https://openalex.org/W4297094621","https://openalex.org/W4309344476","https://openalex.org/W4309345936","https://openalex.org/W4313034743","https://openalex.org/W4323338510","https://openalex.org/W4383109283","https://openalex.org/W4385245566","https://openalex.org/W4389666031","https://openalex.org/W4389666141","https://openalex.org/W4401415888","https://openalex.org/W4402772602","https://openalex.org/W4402968873","https://openalex.org/W4406613284"],"related_works":[],"abstract_inverted_index":{"Human-robot":[0],"interaction":[1,7],"(HRI)":[2],"relies":[3],"on":[4,83,97],"accurate":[5],"human-object":[6,75],"(HOI)":[8],"recognition":[9,16],"to":[10],"enable":[11],"collaborative":[12],"behaviors.":[13],"While":[14],"HOI":[15],"has":[17],"been":[18],"considered":[19],"for":[20,64],"enabling":[21],"intuitive":[22],"robot":[23],"interactions,":[24],"video-based":[25],"implementations":[26],"face":[27],"challenges":[28],"in":[29],"handling":[30],"complex":[31],"object-pose":[32],"variations":[33],"and":[34,53,70,78,86],"temporal":[35],"dynamics.":[36],"This":[37],"work":[38],"proposes":[39],"a":[40],"Multi-stream":[41],"Multi-feature":[42],"Spatial-Temporal":[43],"Network":[44],"(M<sup":[45],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[46],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>ST-Net)":[47],"that":[48],"synergistically":[49],"integrates":[50],"visual,":[51],"geometric,":[52],"global":[54,71],"relational":[55],"features.":[56],"The":[57],"framework":[58],"leverages":[59],"Faster":[60],"R-CNN-extracted":[61],"ROI":[62],"features":[63],"visual":[65],"perception,":[66],"while":[67],"dedicated":[68],"geometric":[69],"encoders":[72],"respectively":[73],"capture":[74],"spatial":[76],"dynamics":[77],"entity":[79],"positional":[80],"relationships.":[81],"Evaluations":[82],"MPHOI-72,":[84],"CAD-120,":[85],"Bimanual":[87],"Actions":[88],"demonstrate":[89],"superior":[90],"performance":[91],"over":[92],"existing":[93],"methods.":[94,105],"HRI":[95],"validation":[96],"dual-arm":[98],"robots":[99],"confirms":[100],"practical":[101],"applicability":[102],"of":[103],"our":[104],"Code":[106],"is":[107],"available":[108],"at":[109],"https://github.com/Cyber-BoBo/M2ST-Net.git.":[110]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-29T00:00:00"}