{"id":"https://openalex.org/W4411446748","doi":"https://doi.org/10.1109/tpami.2025.3581381","title":"Revisiting Siamese-Based 3D Single Object Tracking With a Versatile Transformer","display_name":"Revisiting Siamese-Based 3D Single Object Tracking With a Versatile Transformer","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411446748","doi":"https://doi.org/10.1109/tpami.2025.3581381","pmid":"https://pubmed.ncbi.nlm.nih.gov/40536838"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3581381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3581381","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100440985","display_name":"Jiaming Liu","orcid":"https://orcid.org/0009-0003-9699-1987"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaming Liu","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Wu","orcid":"https://orcid.org/0000-0002-3459-5079"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an, China","School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103213763","display_name":"Qiguang Miao","orcid":"https://orcid.org/0000-0001-6766-8310"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiguang Miao","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an, China","School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091227928","display_name":"Maoguo Gong","orcid":"https://orcid.org/0000-0002-0415-8556"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoguo Gong","raw_affiliation_strings":["School of Electronic Engineering, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an, China","School of Electronic Engineering, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Electronic Engineering, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072308822","display_name":"Linghe Kong","orcid":"https://orcid.org/0000-0001-9266-3044"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghe Kong","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100440985"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80130204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"47","issue":"9","first_page":"8148","last_page":"8164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9994999766349792,"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":0.9994999766349792,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9675999879837036,"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":0.939300000667572,"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":0.8305873870849609},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6934459805488586},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6788589954376221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6219356656074524},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5306101441383362},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4958439767360687},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4482116401195526},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.29175060987472534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305873870849609},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6934459805488586},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6788589954376221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6219356656074524},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5306101441383362},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4958439767360687},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4482116401195526},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.29175060987472534},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3581381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3581381","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40536838","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40536838","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1949608614","display_name":null,"funder_award_id":"62036006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G731801172","display_name":null,"funder_award_id":"62276200","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2158827467","https://openalex.org/W2408241409","https://openalex.org/W2470394683","https://openalex.org/W2799058067","https://openalex.org/W2886910176","https://openalex.org/W2955747520","https://openalex.org/W2962922818","https://openalex.org/W2979750740","https://openalex.org/W2988715931","https://openalex.org/W2990613095","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W3035641096","https://openalex.org/W3134380005","https://openalex.org/W3194700450","https://openalex.org/W3199838280","https://openalex.org/W3208501016","https://openalex.org/W4213402071","https://openalex.org/W4292088557","https://openalex.org/W4312571097","https://openalex.org/W4312950653","https://openalex.org/W4313057812","https://openalex.org/W4313152844","https://openalex.org/W4313644299","https://openalex.org/W4317515510","https://openalex.org/W4321617995","https://openalex.org/W4323057526","https://openalex.org/W4376166839","https://openalex.org/W4380079737","https://openalex.org/W4386066081","https://openalex.org/W4386072382","https://openalex.org/W4386076400","https://openalex.org/W4386472903","https://openalex.org/W4386634677","https://openalex.org/W4387010603","https://openalex.org/W4387623730","https://openalex.org/W4387693309","https://openalex.org/W4387969843","https://openalex.org/W4390872484","https://openalex.org/W4391807613","https://openalex.org/W4392450285","https://openalex.org/W4392975673","https://openalex.org/W4393154549","https://openalex.org/W4402727527","https://openalex.org/W4402944020","https://openalex.org/W4407900019","https://openalex.org/W4408280824","https://openalex.org/W4411244793","https://openalex.org/W6739778489","https://openalex.org/W6780226713","https://openalex.org/W6801512601","https://openalex.org/W6803042736","https://openalex.org/W6838719481"],"related_works":["https://openalex.org/W4389065903","https://openalex.org/W2385949326","https://openalex.org/W2623195638","https://openalex.org/W1966005655","https://openalex.org/W3135795035","https://openalex.org/W2789220062","https://openalex.org/W2811496562","https://openalex.org/W2094665863","https://openalex.org/W2071984725","https://openalex.org/W2185534064"],"abstract_inverted_index":{"3D":[0,23,60,180,194],"Single":[1],"Object":[2],"Tracking":[3,55],"(SOT)":[4],"plays":[5],"an":[6],"important":[7],"role":[8],"in":[9,95],"real-world":[10],"visual":[11],"applications":[12],"such":[13],"as":[14],"autonomous":[15],"driving":[16],"and":[17,36,85,89,131,159,203],"planning.":[18],"How":[19],"to":[20,31,70,103,136,150,172],"realize":[21],"effective":[22],"SOT":[24,195],"is":[25,188],"still":[26],"a":[27,52,110,166,184,189],"valuable":[28],"challenge":[29],"due":[30],"its":[32,37],"carrier-sparse":[33],"point":[34,68,74],"clouds":[35],"role-complex":[38],"influencing":[39],"factors.":[40],"Inspired":[41],"by":[42],"the":[43,66,71,77,97,105,140,174,193],"remote":[44],"modeling":[45],"of":[46,100,115],"popular":[47],"transformers,":[48],"we":[49],"further":[50,147],"propose":[51],"Versatile":[53],"Point":[54],"Transformer":[56],"(VPTT)":[57],"method":[58],"for":[59,179,192],"SOT,":[61],"with":[62],"object":[63],"guidance":[64],"from":[65,134],"template":[67],"cloud":[69,75],"search":[72],"area":[73],"under":[76],"siamese-based":[78,213],"tracking":[79,106,141,181,210,214],"paradigm.":[80],"Specifically,":[81],"VPTT":[82,146,171,207],"employs":[83],"self-":[84],"cross-":[86],"attention":[87],"mechanisms":[88],"extends":[90],"four":[91,116],"matching":[92,122],"operations,":[93],"resulting":[94],"leveraging":[96],"contextual":[98],"information":[99],"consecutive":[101],"frames":[102],"improve":[104],"results.":[107],"By":[108],"constructing":[109],"deep":[111],"network":[112],"VerFormer":[113],"consisting":[114],"successive":[117],"transformer":[118,186],"layers,":[119],"which":[120],"performs":[121],"operations":[123],"involving":[124],"fusional":[125],"transformation,":[126],"separative":[127],"discrimination,":[128],"intersectional":[129],"interaction,":[130],"unidirectional":[132],"propagation":[133],"shallow":[135],"deep.":[137],"Considering":[138],"that":[139,187,206],"task":[142],"involves":[143],"multiple":[144],"processes,":[145],"learns":[148],"how":[149],"forecast":[151],"intermediate":[152],"outputs":[153],"including":[154],"mask":[155],"probability,":[156],"trailing":[157],"distance,":[158],"heading":[160],"angle":[161],"at":[162,216],"each":[163],"stage.":[164],"Such":[165],"specialized":[167],"design":[168],"allows":[169],"our":[170],"revisit":[173],"end-to-end":[175],"training":[176],"paradigm":[177],"used":[178],"while":[182],"developing":[183],"versatile":[185],"perfect":[190],"fit":[191],"task.":[196],"Experiments":[197],"on":[198,212],"three":[199],"benchmarks,":[200],"KITTI,":[201],"nuScenes,":[202],"Waymo,":[204],"show":[205],"achieves":[208],"state-of-the-art":[209],"performance":[211],"running":[215],"$\\sim$\u223c62":[217],"FPS.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}