{"id":"https://openalex.org/W2899558678","doi":"https://doi.org/10.1109/roman.2018.8525582","title":"Detecting and tracking objects in HRI: YOLO networks for the NAO \u201cI See You\u201d function","display_name":"Detecting and tracking objects in HRI: YOLO networks for the NAO \u201cI See You\u201d function","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2899558678","doi":"https://doi.org/10.1109/roman.2018.8525582","mag":"2899558678"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2018.8525582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2018.8525582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","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/A5055004003","display_name":"Jiahuan Zhou","orcid":"https://orcid.org/0000-0002-3301-747X"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahuan Zhou","raw_affiliation_strings":["College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China","institution_ids":["https://openalex.org/I134687103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038023964","display_name":"Lihang Feng","orcid":"https://orcid.org/0000-0002-5790-0478"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihang Feng","raw_affiliation_strings":["College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China","institution_ids":["https://openalex.org/I134687103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012302920","display_name":"Ryad Chellali","orcid":"https://orcid.org/0000-0003-3395-2254"},"institutions":[{"id":"https://openalex.org/I167027274","display_name":"Nanjing Forestry University","ror":"https://ror.org/03m96p165","country_code":"CN","type":"education","lineage":["https://openalex.org/I167027274"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ryad Chellali","raw_affiliation_strings":["Mechatronics College, Nanjing Forestry University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechatronics College, Nanjing Forestry University, Nanjing, China","institution_ids":["https://openalex.org/I167027274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101653886","display_name":"Haonan Zhu","orcid":"https://orcid.org/0009-0006-1492-2446"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Zhu","raw_affiliation_strings":["College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China","institution_ids":["https://openalex.org/I134687103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.636,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.75108298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9965000152587891,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8346608877182007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446761131286621},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7376419901847839},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6901023983955383},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6343767642974854},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.600621223449707},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.530831515789032},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4956907033920288},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.48541459441185},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4841190278530121},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4723944365978241},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47099679708480835},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4459022879600525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26723092794418335}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8346608877182007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446761131286621},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7376419901847839},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6901023983955383},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6343767642974854},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.600621223449707},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.530831515789032},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4956907033920288},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.48541459441185},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4841190278530121},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4723944365978241},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47099679708480835},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4459022879600525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26723092794418335},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/roman.2018.8525582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2018.8525582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","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":31,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W2051396567","https://openalex.org/W2059363354","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2130306094","https://openalex.org/W2163605009","https://openalex.org/W2183182206","https://openalex.org/W2194775991","https://openalex.org/W2570343428","https://openalex.org/W2585198391","https://openalex.org/W2613718673","https://openalex.org/W2749232325","https://openalex.org/W2755268668","https://openalex.org/W2769965474","https://openalex.org/W2773547303","https://openalex.org/W2783247274","https://openalex.org/W2962752334","https://openalex.org/W2962835968","https://openalex.org/W2963037989","https://openalex.org/W2963542991","https://openalex.org/W6620707391","https://openalex.org/W6629368666","https://openalex.org/W6637373629","https://openalex.org/W6679349572","https://openalex.org/W6684191040","https://openalex.org/W6743324380","https://openalex.org/W6746912294"],"related_works":["https://openalex.org/W2969228573","https://openalex.org/W2963690996","https://openalex.org/W4285271403","https://openalex.org/W2542007731","https://openalex.org/W2968379562","https://openalex.org/W2091015105","https://openalex.org/W4388689193","https://openalex.org/W2110899030","https://openalex.org/W29633852","https://openalex.org/W2985362983"],"abstract_inverted_index":{"Object":[0],"detection":[1,88,99],"and":[2,42,51,75,90,110,127,146,174,192],"tracking":[3,193],"is":[4,140,161,178],"a":[5,8,29,61,97,124,165],"basic":[6],"but":[7],"key":[9],"feature":[10],"in":[11,46,198],"many":[12],"robotics":[13],"tasks,":[14],"including":[15],"for":[16,22,134],"human-robots":[17],"interactions.":[18],"Handing":[19],"over":[20],"objects":[21,104,195],"instance":[23],"rely":[24],"almost":[25],"exclusively":[26],"on":[27,66,113,142,155],"such":[28],"capability:":[30],"robots":[31],"should":[32,108],"be":[33],"able":[34],"to":[35,48,84,101,164,181],"detect":[36,102,109],"the":[37,53,57,73,85,105,114,119,129,148,169],"object":[38,136],"of":[39,63,72,87,153,168,196],"interest,":[40],"localize":[41],"track":[43,111],"its":[44],"movements":[45],"order":[47],"synchronize":[49],"temporally":[50],"spatially":[52],"transition":[54],"phase.":[55],"In":[56,92],"past":[58],"few":[59],"years,":[60],"variety":[62],"architectures":[64],"based":[65,112],"convolutional":[67],"neural":[68],"networks,":[69],"especially":[70],"that":[71,187],"R-CNN":[74],"YOLO":[76,115,121],"(You":[77],"Only":[78],"Look":[79],"Once)":[80],"models,":[81],"largely":[82],"contribute":[83],"improvement":[86],"accuracy":[89],"efficiency.":[91],"this":[93],"paper,":[94],"we":[95],"design":[96],"visual":[98],"system":[100],"some":[103],"Nao":[106,170],"robot":[107],"architecture.":[116],"We":[117],"adopt":[118],"tiny":[120],"network":[122],"as":[123],"pretrained":[125],"model":[126,139,160],"modify":[128],"last":[130],"fully":[131],"connected":[132],"layer":[133],"three-class":[135],"detection.":[137],"The":[138,184],"trained":[141],"4322":[143],"training":[144],"images":[145],"achieves":[147],"mean":[149],"average":[150],"precision":[151],"(mAP)":[152],"44.3%":[154],"our":[156],"test":[157],"set.":[158],"This":[159],"then":[162],"applied":[163,180],"well-known":[166],"function":[167],"vision":[171],"system:":[172],"detecting":[173],"localizing":[175,191],"landmarks.":[176],"It":[177],"also":[179],"daily":[182],"objects.":[183],"results":[185],"demonstrate":[186],"it":[188],"could":[189],"help":[190],"accurately":[194],"interest":[197],"HRI":[199],"(human-robot":[200],"interaction).":[201]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}