{"id":"https://openalex.org/W4412939518","doi":"https://doi.org/10.1109/tcsvt.2025.3595760","title":"USVTrack: A Benchmark for Multi-Object Tracking in Complex Water Surface Scenes","display_name":"USVTrack: A Benchmark for Multi-Object Tracking in Complex Water Surface Scenes","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4412939518","doi":"https://doi.org/10.1109/tcsvt.2025.3595760"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3595760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3595760","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5046368743","display_name":"Bin Xue","orcid":"https://orcid.org/0000-0003-3664-9410"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Xue","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3664-9410","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074480992","display_name":"Yuwei Cheng","orcid":"https://orcid.org/0000-0002-6819-2075"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Cheng","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6819-2075","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664456","display_name":"Kun Ding","orcid":"https://orcid.org/0000-0002-2256-8815"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Ding","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2256-8815","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435212","display_name":"Chunhong Pan","orcid":"https://orcid.org/0000-0001-7433-4474"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhong Pan","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7433-4474","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040673285","display_name":"Shiming Xiang","orcid":"https://orcid.org/0000-0002-2089-9733"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Xiang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2089-9733","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86769541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"36","issue":"1","first_page":"1029","last_page":"1044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.954200029373169,"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":0.954200029373169,"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/T12316","display_name":"Oil Spill Detection and Mitigation","score":0.9347000122070312,"subfield":{"id":"https://openalex.org/subfields/2310","display_name":"Pollution"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9286999702453613,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7115835547447205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6938358545303345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6822283267974854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6690521240234375},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5294508337974548},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4768047034740448},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4716167747974396},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.431369423866272},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3483548164367676},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3092086613178253},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08550316095352173},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0771639347076416}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7115835547447205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6938358545303345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822283267974854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6690521240234375},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5294508337974548},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4768047034740448},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4716167747974396},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.431369423866272},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3483548164367676},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3092086613178253},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08550316095352173},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0771639347076416},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3595760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3595760","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/6","display_name":"Clean water and sanitation","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G3767319995","display_name":null,"funder_award_id":"62433003","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G7040694932","display_name":null,"funder_award_id":"62306310","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G709307851","display_name":null,"funder_award_id":"62306310","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2124781496","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2252355370","https://openalex.org/W2511791013","https://openalex.org/W2552331162","https://openalex.org/W2603203130","https://openalex.org/W2769653316","https://openalex.org/W2787889241","https://openalex.org/W2885291434","https://openalex.org/W2920942303","https://openalex.org/W2962777203","https://openalex.org/W2963323244","https://openalex.org/W2963351448","https://openalex.org/W2963855133","https://openalex.org/W2963857746","https://openalex.org/W2989604896","https://openalex.org/W2991460783","https://openalex.org/W2997242810","https://openalex.org/W3035564946","https://openalex.org/W3035574168","https://openalex.org/W3042011474","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3094000868","https://openalex.org/W3095753995","https://openalex.org/W3106763294","https://openalex.org/W3116469262","https://openalex.org/W3118212025","https://openalex.org/W3120048558","https://openalex.org/W3204885083","https://openalex.org/W3205100603","https://openalex.org/W3205307530","https://openalex.org/W4212841652","https://openalex.org/W4233618835","https://openalex.org/W4286904999","https://openalex.org/W4310467366","https://openalex.org/W4312473433","https://openalex.org/W4313072323","https://openalex.org/W4319300181","https://openalex.org/W4319866011","https://openalex.org/W4322576511","https://openalex.org/W4362501010","https://openalex.org/W4377231617","https://openalex.org/W4385245566","https://openalex.org/W4385575022","https://openalex.org/W4386076204","https://openalex.org/W4386083103","https://openalex.org/W4389352686","https://openalex.org/W4389554109","https://openalex.org/W4390874237","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4391428214","https://openalex.org/W4391852066","https://openalex.org/W4392452358","https://openalex.org/W4393149283","https://openalex.org/W4400035744","https://openalex.org/W4402727760","https://openalex.org/W4402753781","https://openalex.org/W4403724263","https://openalex.org/W4405127308","https://openalex.org/W4405232313","https://openalex.org/W4405974723"],"related_works":["https://openalex.org/W4390721878","https://openalex.org/W4285271403","https://openalex.org/W2542007731","https://openalex.org/W4292830139","https://openalex.org/W2968379562","https://openalex.org/W4319309705","https://openalex.org/W2091015105","https://openalex.org/W4388689193","https://openalex.org/W2110899030","https://openalex.org/W29633852"],"abstract_inverted_index":{"Multi-object":[0],"tracking":[1,111,177],"(MOT)":[2],"in":[3,101,142,203],"water":[4,31,76,103,205],"surface":[5,32,77,104,206],"scenes":[6,207],"is":[7],"crucial":[8],"for":[9,99,213],"the":[10,28,135,156,176,189,211],"autonomous":[11,61],"navigation":[12,54],"of":[13,84],"Unmanned":[14],"Surface":[15],"Vehicles":[16],"(USVs).":[17],"However,":[18],"existing":[19,196],"MOT":[20,33,69,100,144,202],"datasets":[21,34],"rarely":[22],"focus":[23],"on":[24,43,59,155,188],"these":[25],"scenes.":[26],"Moreover,":[27],"few":[29],"available":[30],"contain":[35],"limited":[36],"data":[37],"shot":[38],"onboard":[39],"and":[40,74,87,139,166,183],"concentrate":[41],"narrowly":[42],"specific":[44],"marine":[45],"scenes,":[46,78,105],"creating":[47],"a":[48,66,81],"significant":[49],"gap":[50],"from":[51],"real-world":[52],"USV":[53,60],"applications.":[55],"To":[56],"promote":[57],"research":[58],"navigation,":[62],"we":[63,91],"introduce":[64],"USVTrack,":[65],"fully":[67],"onboard-shot":[68],"benchmark":[70,191],"that":[71,161,173,193,201],"covers":[72],"diverse":[73],"complex":[75,102,204],"characterized":[79],"by":[80],"high":[82],"proportion":[83],"small":[85],"objects":[86],"varied":[88],"backgrounds.":[89],"Then,":[90],"propose":[92],"an":[93,148,169],"innovative":[94],"end-to-end":[95,143],"method":[96,172],"specifically":[97],"designed":[98],"termed":[106],"as":[107],"USVMOT.":[108],"It":[109],"improves":[110],"performance":[112],"through":[113],"four":[114],"key":[115],"contributions:":[116],"1)":[117],"integrating":[118],"mask":[119,151],"information":[120],"via":[121],"knowledge":[122],"distillation":[123],"to":[124,133,180],"boost":[125],"feature":[126],"discriminability;":[127],"2)":[128],"deploying":[129],"task-specific":[130],"auxiliary":[131],"pathways":[132],"alleviate":[134],"competition":[136],"between":[137],"detection":[138],"re-identification":[140],"(ReID)":[141],"methods;":[145],"3)":[146],"employing":[147],"adaptive":[149],"high-quality":[150],"generation":[152],"strategy":[153,178],"based":[154],"Segment":[157],"Anything":[158],"Model":[159],"(SAM)":[160],"obviates":[162],"extensive":[163],"manual":[164],"annotation;":[165],"4)":[167],"introducing":[168],"object-aware":[170],"association":[171],"dynamically":[174],"tailors":[175],"according":[179],"object":[181],"size":[182],"motion":[184],"speed.":[185],"Extensive":[186],"experiments":[187],"USVTrack":[190],"demonstrate":[192],"USVMOT":[194],"outperforms":[195],"methods.":[197],"Our":[198],"analysis":[199],"reveals":[200],"remains":[208],"challenging,":[209],"highlighting":[210],"need":[212],"further":[214],"advancements.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}