{"id":"https://openalex.org/W4210786150","doi":"https://doi.org/10.1109/tmm.2022.3146714","title":"Real-Time 3D Single Object Tracking With Transformer","display_name":"Real-Time 3D Single Object Tracking With Transformer","publication_year":2022,"publication_date":"2022-01-27","ids":{"openalex":"https://openalex.org/W4210786150","doi":"https://doi.org/10.1109/tmm.2022.3146714"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3146714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3146714","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.00860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091000644","display_name":"Jiayao Shan","orcid":"https://orcid.org/0000-0001-8840-877X"},"institutions":[{"id":"https://openalex.org/I4210140031","display_name":"Science and Technology on Surface Physics and Chemistry Laboratory","ror":"https://ror.org/0543q7s13","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140031"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayao Shan","raw_affiliation_strings":["Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China","Science and Technology on Near-Surface Detection Laboratory, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0001-8840-877X","affiliations":[{"raw_affiliation_string":"Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Science and Technology on Near-Surface Detection Laboratory, Wuxi, China","institution_ids":["https://openalex.org/I4210140031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103268513","display_name":"Sifan Zhou","orcid":"https://orcid.org/0000-0003-3602-7566"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Zhou","raw_affiliation_strings":["Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-3602-7566","affiliations":[{"raw_affiliation_string":"Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066263434","display_name":"Yubo Cui","orcid":"https://orcid.org/0000-0001-5302-0484"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yubo Cui","raw_affiliation_strings":["Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-5302-0484","affiliations":[{"raw_affiliation_string":"Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064687463","display_name":"Zheng Fang","orcid":"https://orcid.org/0000-0003-3887-3141"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Fang","raw_affiliation_strings":["Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-3887-3141","affiliations":[{"raw_affiliation_string":"Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8889,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.97300745,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"2339","last_page":"2353"},"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":0.9994000196456909,"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":0.9936000108718872,"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":0.8146710395812988},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.48184359073638916},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4356442987918854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4104694128036499},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.39047902822494507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37653493881225586},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08473023772239685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8146710395812988},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.48184359073638916},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4356442987918854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4104694128036499},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.39047902822494507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37653493881225586},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08473023772239685},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2022.3146714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3146714","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"},{"id":"pmh:oai:arXiv.org:2209.00860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.00860","pdf_url":"https://arxiv.org/pdf/2209.00860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.00860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.00860","pdf_url":"https://arxiv.org/pdf/2209.00860","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3585439895","display_name":null,"funder_award_id":"201941050001","funder_id":"https://openalex.org/F4320322857","funder_display_name":"Aeronautical Science Foundation of China"},{"id":"https://openalex.org/G6509363187","display_name":null,"funder_award_id":"62073066","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G836760401","display_name":null,"funder_award_id":"N182608003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8544294156","display_name":null,"funder_award_id":"U20A20197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1531069015","https://openalex.org/W1892578678","https://openalex.org/W1964846093","https://openalex.org/W2150066425","https://openalex.org/W2151295993","https://openalex.org/W2154889144","https://openalex.org/W2158827467","https://openalex.org/W2194775991","https://openalex.org/W2435777129","https://openalex.org/W2470394683","https://openalex.org/W2557641257","https://openalex.org/W2560609797","https://openalex.org/W2799058067","https://openalex.org/W2894176037","https://openalex.org/W2896457183","https://openalex.org/W2912429050","https://openalex.org/W2917353338","https://openalex.org/W2922625254","https://openalex.org/W2949708697","https://openalex.org/W2952809536","https://openalex.org/W2962922818","https://openalex.org/W2963121255","https://openalex.org/W2963227409","https://openalex.org/W2963400571","https://openalex.org/W2963534981","https://openalex.org/W2964071664","https://openalex.org/W2965376383","https://openalex.org/W2971306974","https://openalex.org/W2972392244","https://openalex.org/W2983446232","https://openalex.org/W2988715931","https://openalex.org/W2990211277","https://openalex.org/W2997941866","https://openalex.org/W3006754479","https://openalex.org/W3008681115","https://openalex.org/W3009294634","https://openalex.org/W3026441479","https://openalex.org/W3034885317","https://openalex.org/W3035346742","https://openalex.org/W3035574168","https://openalex.org/W3035641096","https://openalex.org/W3035672751","https://openalex.org/W3093537218","https://openalex.org/W3096609285","https://openalex.org/W3102817716","https://openalex.org/W3107400217","https://openalex.org/W3111535274","https://openalex.org/W3114753236","https://openalex.org/W3115390238","https://openalex.org/W3119686997","https://openalex.org/W3129373298","https://openalex.org/W3131716792","https://openalex.org/W3132607695","https://openalex.org/W3149936330","https://openalex.org/W3153465022","https://openalex.org/W3166470370","https://openalex.org/W3167536469","https://openalex.org/W3175891031","https://openalex.org/W3194700450","https://openalex.org/W3208501016","https://openalex.org/W3214586131","https://openalex.org/W4287557165","https://openalex.org/W4297780875","https://openalex.org/W4298395628","https://openalex.org/W4385245566","https://openalex.org/W4394652702","https://openalex.org/W6631884009","https://openalex.org/W6739778489","https://openalex.org/W6739901393","https://openalex.org/W6754654878","https://openalex.org/W6755207826","https://openalex.org/W6757585730","https://openalex.org/W6760655697","https://openalex.org/W6763367864","https://openalex.org/W6778485988","https://openalex.org/W6787985011","https://openalex.org/W6788023325","https://openalex.org/W6788305448","https://openalex.org/W6792915775","https://openalex.org/W6802372869"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"LiDAR-based":[0],"3D":[1,83,135],"single":[2,84],"object":[3,54,85,185],"tracking":[4,60,86,114,246],"is":[5,273],"a":[6,74,133,215,232],"challenging":[7],"issue":[8],"in":[9,116,156,174,223,236,263],"robotics":[10],"and":[11,55,72,111,131,149,186,194,205,245],"autonomous":[12],"driving.":[13],"Currently,":[14],"existing":[15],"approaches":[16],"usually":[17],"suffer":[18],"from":[19],"the":[20,37,41,52,68,101,105,109,113,128,146,157,162,175,181,200,206,212,224,241,276],"problem":[21],"that":[22],"objects":[23],"at":[24,265,279],"long":[25],"distance":[26],"often":[27],"have":[28],"very":[29],"sparse":[30,237],"or":[31],"partially-occluded":[32],"point":[33,81,165],"clouds,":[34],"which":[35,99,167,210],"makes":[36],"features":[38,45,94,107],"extracted":[39],"by":[40,95,214],"model":[42,161],"ambiguous.":[43],"Ambiguous":[44],"will":[46],"make":[47],"it":[48],"hard":[49],"to":[50,58,251],"locate":[51],"target":[53,110],"finally":[56],"lead":[57],"bad":[59],"results.":[61],"To":[62,119],"solve":[63],"this":[64],"problem,":[65],"we":[66,124,142],"utilize":[67],"powerful":[69],"Transformer":[70],"architecture":[71],"propose":[73],"<bold":[75],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[76,219,281],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Point-Track-Transformer":[77],"(PTT)</b>":[78],"module":[79,90,155,173,204],"for":[80,275],"cloud-based":[82],"task.":[87],"Specifically,":[88],"PTT":[89,122,126,144,154,172,203],"generates":[91],"fine-tuned":[92],"attention":[93,97],"computing":[96],"weights,":[98],"guides":[100],"tracker":[102,137],"focusing":[103],"on":[104,192,255,267],"important":[106],"of":[108,202,208,243],"improves":[112],"ability":[115],"complex":[117],"scenarios.":[118,238],"evaluate":[120,189],"our":[121,190,228,249],"module,":[123],"embed":[125,143],"into":[127,145],"dominant":[129],"method":[130,229],"construct":[132],"novel":[134],"SOT":[136],"named":[138],"PTT-Net.":[139],"In":[140,239],"PTT-Net,":[141,209],"voting":[147,158],"stage":[148,159,178],"proposal":[150,176],"generation":[151,177],"stage,":[152],"respectively.":[153],"could":[160,179,261],"interactions":[163],"among":[164],"patches,":[166],"learns":[168],"context-dependent":[169],"features.":[170],"Meanwhile,":[171,227],"capture":[180],"contextual":[182],"information":[183],"between":[184],"background.":[187],"We":[188],"PTT-Net":[191,250,260],"KITTI":[193],"NuScenes":[195],"datasets.":[196,258],"Experimental":[197],"results":[198],"demonstrate":[199],"effectiveness":[201],"superiority":[207],"surpasses":[211],"baseline":[213],"noticeable":[216],"margin,":[217],"<inline-formula":[218],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[220],"notation=\"LaTeX\">$\\sim$</tex-math></inline-formula>":[221],"10%":[222],"Car":[225],"category.":[226],"also":[230],"has":[231],"significant":[233],"performance":[234,254],"improvement":[235],"general,":[240],"combination":[242],"transformer":[244],"pipeline":[247],"enables":[248],"achieve":[252],"state-of-the-art":[253],"both":[256],"two":[257],"Additionally,":[259],"run":[262],"real-time":[264],"40FPS":[266],"NVIDIA":[268],"1080Ti":[269],"GPU.":[270],"Our":[271],"code":[272],"open-sourced":[274],"research":[277],"community":[278],"<uri":[280],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/shanjiayao/PTT</uri>":[282],".":[283]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}