{"id":"https://openalex.org/W4385477837","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191718","title":"TEMI-MOT: Towards Efficient Multi-Modality Instance-Aware Feature Learning for 3D Multi-Object Tracking","display_name":"TEMI-MOT: Towards Efficient Multi-Modality Instance-Aware Feature Learning for 3D Multi-Object Tracking","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385477837","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191718"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191718","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5043582125","display_name":"Yu\u2010Feng Hu","orcid":"https://orcid.org/0000-0001-5715-2070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufeng Hu","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications,Xi'an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113827261","display_name":"Sanping Zhou","orcid":"https://orcid.org/0000-0003-4100-2304"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanping Zhou","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications,Xi'an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004232422","display_name":"Jinpeng Dong","orcid":"https://orcid.org/0009-0006-6938-4315"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinpeng Dong","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications,Xi'an,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications,Xi'an,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38964677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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":0.9995999932289124,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9721999764442444,"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":0.8007318377494812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.785228967666626},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6929906606674194},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6544963121414185},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5817298889160156},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5658156275749207},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5154910683631897},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43995365500450134},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43127164244651794},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.422944039106369},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3869543969631195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007318377494812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.785228967666626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6929906606674194},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6544963121414185},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5817298889160156},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5658156275749207},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5154910683631897},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43995365500450134},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43127164244651794},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.422944039106369},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3869543969631195},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191718","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2560609797","https://openalex.org/W2798965597","https://openalex.org/W2798991696","https://openalex.org/W2897529137","https://openalex.org/W2899302124","https://openalex.org/W2908510526","https://openalex.org/W2920942303","https://openalex.org/W2962766617","https://openalex.org/W2963323244","https://openalex.org/W2963727135","https://openalex.org/W2964333437","https://openalex.org/W2967324759","https://openalex.org/W2968296999","https://openalex.org/W2981393651","https://openalex.org/W2983227562","https://openalex.org/W3034739212","https://openalex.org/W3034782805","https://openalex.org/W3035461736","https://openalex.org/W3035574168","https://openalex.org/W3056795521","https://openalex.org/W3084173793","https://openalex.org/W3094000868","https://openalex.org/W3095753995","https://openalex.org/W3108426750","https://openalex.org/W3114753236","https://openalex.org/W3136115421","https://openalex.org/W3167095230","https://openalex.org/W3167732492","https://openalex.org/W3170030651","https://openalex.org/W3181852566","https://openalex.org/W3206199195","https://openalex.org/W3207707490","https://openalex.org/W3214282487","https://openalex.org/W3216604356","https://openalex.org/W4200381380","https://openalex.org/W4221145330","https://openalex.org/W4226100504","https://openalex.org/W4286750441","https://openalex.org/W4312707458","https://openalex.org/W4312778480","https://openalex.org/W4312921534","https://openalex.org/W4382203297","https://openalex.org/W4386243204","https://openalex.org/W6755742144","https://openalex.org/W6757817989","https://openalex.org/W6763422710","https://openalex.org/W6782246188","https://openalex.org/W6791755159","https://openalex.org/W6804018845","https://openalex.org/W6804183503","https://openalex.org/W6839615101","https://openalex.org/W6839707091","https://openalex.org/W6843199799","https://openalex.org/W6844043141","https://openalex.org/W6848469397"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2012200063","https://openalex.org/W2965594636"],"abstract_inverted_index":{"3D":[0,34,104,208],"multi-object":[1,35,105,209],"tracking":[2,36,55,128,165],"is":[3,110],"one":[4],"of":[5,9,26,50,68,82,112],"the":[6,22,48,54,66,117,122,127,135,138,144,149,159,164,169,185,189,199],"key":[7],"technologies":[8],"autonomous":[10,17],"driving,":[11],"which":[12,109],"aims":[13],"to":[14,62,72,157],"ensure":[15],"that":[16,198],"driving":[18],"vehicles":[19],"accurately":[20],"perceive":[21],"movements":[23],"and":[24,80,126,141,163,175,205],"intentions":[25],"surrounding":[27],"traffic":[28],"participants.":[29],"In":[30],"recent":[31],"years,":[32],"some":[33],"methods":[37,46,58,190],"based":[38,171],"on":[39,172,184],"multimodality":[40],"have":[41],"been":[42],"proposed.":[43],"Although":[44],"these":[45,57,93],"improve":[47],"accuracy":[49],"object":[51],"association":[52],"in":[53,115],"process,":[56],"are":[59],"still":[60],"difficult":[61],"effectively":[63],"deal":[64],"with":[65,153],"problems":[67],"feature":[69,75,89,100,120,124,132,146],"ambiguity":[70],"due":[71],"occlusion,":[73],"incorrect":[74],"alignment":[76,136],"between":[77,137],"different":[78],"modalities,":[79],"confusion":[81],"adjacent":[83],"target":[84],"features":[85,152,174],"caused":[86],"by":[87],"coarse-grained":[88],"maps.":[90],"To":[91],"address":[92],"problems,":[94],"we":[95],"propose":[96],"a":[97],"new":[98],"multi-modality":[99],"learning":[101],"method":[102,201],"for":[103,207],"tracking,":[106],"named":[107],"TEMI-MOT,":[108],"composed":[111],"three":[113],"modules":[114],"series:":[116],"point-guided":[118,131],"image":[119,142,151],"sampler,":[121],"instance-aware":[123,145,161,173],"encoder,":[125],"pipeline.":[129],"The":[130,194],"sampler":[133],"realizes":[134],"point":[139],"cloud":[140],"features,":[143,162],"encoder":[147],"fuses":[148],"aligned":[150],"each":[154],"object's":[155],"points":[156],"generate":[158],"discriminative":[160],"pipeline":[166],"finally":[167],"outputs":[168],"results":[170,183,196],"G-IoU":[176],"geometric":[177],"similarities.":[178],"Our":[179],"approach":[180],"achieves":[181],"state-of-the-art":[182],"nuScenes":[186],"dataset":[187],"among":[188],"using":[191],"CenterPoint":[192],"detections.":[193],"experimental":[195],"show":[197],"proposed":[200],"has":[202],"better":[203],"robustness":[204],"effectiveness":[206],"tracking.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}