{"id":"https://openalex.org/W4401415307","doi":"https://doi.org/10.1109/icra57147.2024.10610979","title":"Multi-modal 3D Human Tracking for Robots in Complex Environment with Siamese Point-Video Transformer","display_name":"Multi-modal 3D Human Tracking for Robots in Complex Environment with Siamese Point-Video Transformer","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415307","doi":"https://doi.org/10.1109/icra57147.2024.10610979"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5111068042","display_name":"Shuo Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Xin","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390201","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0003-3031-3350"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Zhang","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429671","display_name":"Mengmeng Wang","orcid":"https://orcid.org/0000-0002-7380-1111"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengmeng Wang","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103156798","display_name":"Xiaojun Hou","orcid":"https://orcid.org/0000-0002-5344-8517"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Hou","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051556141","display_name":"Yaowei Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Guo","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333956","display_name":"Xiao Kang","orcid":"https://orcid.org/0009-0007-0491-4466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Kang","raw_affiliation_strings":["China North Vehicle Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China North Vehicle Research Institute,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113971784","display_name":"Liang Liu","orcid":"https://orcid.org/0009-0001-1203-3390"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Liu","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9940999746322632,"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":0.9915000200271606,"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/robot","display_name":"Robot","score":0.6737845540046692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6461017727851868},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6444501876831055},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6167532205581665},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48875951766967773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4627765119075775},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4599124789237976},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4271318316459656},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.333757221698761},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2016010284423828},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12358734011650085},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11525118350982666},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08003553748130798}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6737845540046692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6461017727851868},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6444501876831055},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6167532205581665},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48875951766967773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4627765119075775},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4599124789237976},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4271318316459656},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.333757221698761},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2016010284423828},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12358734011650085},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11525118350982666},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08003553748130798},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.5600000023841858,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W861352110","https://openalex.org/W1487560374","https://openalex.org/W1977081314","https://openalex.org/W2028683273","https://openalex.org/W2067528992","https://openalex.org/W2081793425","https://openalex.org/W2131072478","https://openalex.org/W2148725385","https://openalex.org/W2150066425","https://openalex.org/W2156924265","https://openalex.org/W2169172998","https://openalex.org/W2435777129","https://openalex.org/W2470394683","https://openalex.org/W2536519148","https://openalex.org/W2562105614","https://openalex.org/W2604178231","https://openalex.org/W2795166961","https://openalex.org/W2799058067","https://openalex.org/W2912429050","https://openalex.org/W2962922818","https://openalex.org/W2963121255","https://openalex.org/W2963854930","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W3035641096","https://openalex.org/W3093537218","https://openalex.org/W3094502228","https://openalex.org/W3111535274","https://openalex.org/W3129373298","https://openalex.org/W3153465022","https://openalex.org/W3164399840","https://openalex.org/W3190492058","https://openalex.org/W3194700450","https://openalex.org/W3199838280","https://openalex.org/W3206532678","https://openalex.org/W3208501016","https://openalex.org/W3214586131","https://openalex.org/W4200223523","https://openalex.org/W4214755140","https://openalex.org/W4283795368","https://openalex.org/W4312571097","https://openalex.org/W4312736325","https://openalex.org/W4312788538","https://openalex.org/W4312950653","https://openalex.org/W4313057812","https://openalex.org/W4383097653","https://openalex.org/W4383108173","https://openalex.org/W4385245566","https://openalex.org/W4385801295","https://openalex.org/W4390873121","https://openalex.org/W6603310463","https://openalex.org/W6739778489","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2084086966","https://openalex.org/W2023861399","https://openalex.org/W2730915376","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727"],"abstract_inverted_index":{"Tracking":[0,56],"a":[1,53,118,162],"specific":[2],"person":[3],"in":[4,15,33,37],"3D":[5,19,68],"scene":[6],"is":[7,59,64,123],"gaining":[8],"momentum":[9],"due":[10],"to":[11,80,94],"its":[12],"numerous":[13],"applications":[14],"robotics.":[16],"Currently,":[17],"most":[18],"trackers":[20],"focus":[21],"on":[22,41,113,157],"driving":[23],"scenarios":[24],"with":[25,77,126],"neglected":[26],"jitter":[27],"and":[28,115,161,168],"uncomplicated":[29],"surroundings,":[30],"which":[31,98],"results":[32],"their":[34],"severe":[35],"degeneration":[36],"complex":[38,138],"environments,":[39,97],"especially":[40],"jolting":[42],"robot":[43,147,164],"platforms":[44],"(only":[45],"20-60%":[46],"success":[47],"rate).":[48],"To":[49],"improve":[50],"the":[51,65,87,104,110,134,143,146],"accuracy,":[52],"Point-Video-based":[54],"Transformer":[55,90],"model":[57],"(PVTrack)":[58],"presented":[60],"for":[61,91,165],"robots.":[62],"It":[63,132],"first":[66],"multi-modal":[67],"human":[69],"tracking":[70],"work":[71],"that":[72,151],"incorporates":[73],"point":[74],"clouds":[75],"together":[76,125],"RGB":[78],"videos":[79],"achieve":[81],"information":[82,102],"complementarity.":[83],"Moreover,":[84],"PVTrack":[85],"proposes":[86],"Siamese":[88],"Point-Video":[89],"feature":[92],"aggregation":[93],"overcome":[95],"dynamic":[96],"captures":[99],"more":[100],"target-aware":[101],"through":[103],"hierarchical":[105],"attention":[106],"mechanism":[107],"adaptively.":[108],"Considering":[109],"violent":[111],"shaking":[112],"robots":[114],"rugged":[116],"terrains,":[117],"lateral":[119],"Human-ware":[120],"Proposal":[121,129],"Network":[122],"designed":[124],"an":[127],"Anti-shake":[128],"Compensation":[130],"module.":[131],"alleviates":[133],"disturbance":[135],"caused":[136],"by":[137],"scenes":[139],"as":[140,142],"well":[141],"particularity":[144],"of":[145],"platform.":[148],"Experiments":[149],"show":[150],"our":[152],"method":[153],"achieves":[154],"state-of-the-art":[155],"performance":[156],"both":[158],"KITTI/Waymo":[159],"datasets":[160],"quadruped":[163],"various":[166],"indoor":[167],"outdoor":[169],"scenes.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
