{"id":"https://openalex.org/W4414404731","doi":"https://doi.org/10.1109/tcsvt.2025.3612499","title":"Multi-Stage Cross-Modality Feature Interaction for RGB-Thermal Multi-Object Tracking","display_name":"Multi-Stage Cross-Modality Feature Interaction for RGB-Thermal Multi-Object Tracking","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414404731","doi":"https://doi.org/10.1109/tcsvt.2025.3612499"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3612499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3612499","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/A5049734652","display_name":"Jianbo Ma","orcid":"https://orcid.org/0009-0007-9789-9591"},"institutions":[{"id":"https://openalex.org/I4210128284","display_name":"Institute of Optics and Electronics, Chinese Academy of Sciences","ror":"https://ror.org/02bn68w95","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128284"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbo Ma","raw_affiliation_strings":["State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0007-9789-9591","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]},{"raw_affiliation_string":"Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007665813","display_name":"Hui Luo","orcid":"https://orcid.org/0000-0001-6698-5576"},"institutions":[{"id":"https://openalex.org/I4210128284","display_name":"Institute of Optics and Electronics, Chinese Academy of Sciences","ror":"https://ror.org/02bn68w95","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128284"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Luo","raw_affiliation_strings":["State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-6698-5576","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]},{"raw_affiliation_string":"Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064880801","display_name":"Shuaicheng Niu","orcid":"https://orcid.org/0000-0001-8212-1831"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuaicheng Niu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015991234","display_name":"Peilin Zhao","orcid":"https://orcid.org/0000-0001-8543-3953"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peilin Zhao","raw_affiliation_strings":["Tencent AI Laboratory, Shenzhen, China","Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8543-3953","affiliations":[{"raw_affiliation_string":"Tencent AI Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357477","display_name":"Yunfeng Liu","orcid":"https://orcid.org/0000-0001-6635-6876"},"institutions":[{"id":"https://openalex.org/I4210128284","display_name":"Institute of Optics and Electronics, Chinese Academy of Sciences","ror":"https://ror.org/02bn68w95","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128284"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfeng Liu","raw_affiliation_strings":["State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]},{"raw_affiliation_string":"Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103012084","display_name":"Yuxing Wei","orcid":"https://orcid.org/0009-0005-2364-6693"},"institutions":[{"id":"https://openalex.org/I4210128284","display_name":"Institute of Optics and Electronics, Chinese Academy of Sciences","ror":"https://ror.org/02bn68w95","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128284"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Wei","raw_affiliation_strings":["State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0005-2364-6693","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]},{"raw_affiliation_string":"Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100747273","display_name":"Jianlin Zhang","orcid":"https://orcid.org/0000-0002-5284-2942"},"institutions":[{"id":"https://openalex.org/I4210128284","display_name":"Institute of Optics and Electronics, Chinese Academy of Sciences","ror":"https://ror.org/02bn68w95","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128284"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlin Zhang","raw_affiliation_strings":["State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5284-2942","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]},{"raw_affiliation_string":"Institute of Optics and Electronics, State Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China","institution_ids":["https://openalex.org/I4210128284"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8309,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92243242,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"2","first_page":"2449","last_page":"2463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9916999936103821,"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"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6301000118255615},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5831000208854675},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5587999820709229},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5091000199317932},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5073000192642212},{"id":"https://openalex.org/keywords/feature-tracking","display_name":"Feature tracking","score":0.4320000112056732},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.43070000410079956},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.421999990940094},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817000150680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7450000047683716},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6603999733924866},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6301000118255615},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5831000208854675},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5587999820709229},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C2987395694","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Feature tracking","level":3,"score":0.4320000112056732},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.3905999958515167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.334199994802475},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3612499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3612499","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W2124781496","https://openalex.org/W2765667535","https://openalex.org/W2911488577","https://openalex.org/W2913269858","https://openalex.org/W2921749009","https://openalex.org/W2963323244","https://openalex.org/W2963351448","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3095753995","https://openalex.org/W3096609285","https://openalex.org/W3166092877","https://openalex.org/W3167949052","https://openalex.org/W3177211876","https://openalex.org/W3182674219","https://openalex.org/W3207919963","https://openalex.org/W4214516362","https://openalex.org/W4285244413","https://openalex.org/W4286904999","https://openalex.org/W4295832202","https://openalex.org/W4312473433","https://openalex.org/W4312504688","https://openalex.org/W4312567319","https://openalex.org/W4312612915","https://openalex.org/W4312668764","https://openalex.org/W4312906297","https://openalex.org/W4317794944","https://openalex.org/W4319879007","https://openalex.org/W4323022579","https://openalex.org/W4367663172","https://openalex.org/W4376126900","https://openalex.org/W4379528676","https://openalex.org/W4381300351","https://openalex.org/W4385245566","https://openalex.org/W4386071948","https://openalex.org/W4386076204","https://openalex.org/W4386083103","https://openalex.org/W4387092360","https://openalex.org/W4389352686","https://openalex.org/W4392188075","https://openalex.org/W4392551959","https://openalex.org/W4392796741","https://openalex.org/W4393148493","https://openalex.org/W4393153514","https://openalex.org/W4393171245","https://openalex.org/W4394596409","https://openalex.org/W4396941327","https://openalex.org/W4400314703","https://openalex.org/W4400447303","https://openalex.org/W4400810524","https://openalex.org/W4401806723","https://openalex.org/W4401908179","https://openalex.org/W4402315045","https://openalex.org/W4403331577","https://openalex.org/W4405942126","https://openalex.org/W4405974723","https://openalex.org/W4409152826"],"related_works":[],"abstract_inverted_index":{"RGB-Thermal":[0],"multi-object":[1],"tracking":[2,7,64,121,158,162],"(RGB-T":[3],"MOT)":[4],"focuses":[5],"on":[6,201],"multiple":[8,151],"objects":[9,113],"in":[10,41,62,160],"complex":[11],"scenarios,":[12],"such":[13],"as":[14],"nighttime":[15],"and":[16,28,56,87,147,191,206],"low-light":[17],"conditions,":[18],"which":[19,80,103,136,173],"is":[20,212],"crucial":[21],"for":[22],"various":[23],"applications,":[24],"including":[25],"video":[26,116],"surveillance":[27],"unmanned":[29],"aerial":[30],"vehicle":[31],"monitoring.":[32],"Existing":[33],"RGB-T":[34,115,208],"MOT":[35],"studies":[36],"typically":[37],"merge":[38],"multi-source":[39],"features":[40,143],"a":[42,71],"single":[43],"stage":[44],"before":[45],"the":[46,96,130,167,183],"backbone":[47],"network.":[48],"These":[49],"works":[50],"fail":[51],"to":[52,140,178,181],"preserve":[53],"fine-grained":[54],"details":[55],"struggle":[57],"with":[58],"context-dependent":[59],"fusion,":[60],"resulting":[61],"suboptimal":[63],"performance.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,94,128,165],"propose":[70,129,166],"novel":[72],"multi-stage":[73],"cross-modality":[74,88,125,138,168,186],"spatial-temporal":[75],"feature":[76,99,154,179,187],"interaction":[77,100,133],"network":[78],"(MCTrack),":[79],"emphasizes":[81],"two":[82],"main":[83],"aspects:":[84],"temporal-aware":[85,92],"learning":[86],"information":[89,126],"interaction.":[90,188],"For":[91,124],"learning,":[93],"introduce":[95],"temporal":[97],"salient":[98],"(TSFI)":[101],"module,":[102,135],"ensures":[104],"trajectory":[105],"continuity":[106],"by":[107],"capturing":[108],"dynamic":[109],"spatial":[110],"variation":[111],"of":[112,153,185],"across":[114],"pairs,":[117],"enabling":[118],"consistent":[119],"object":[120],"over":[122],"time.":[123],"interaction,":[127],"bidirectional":[131],"modality":[132],"(Bi-MI)":[134],"employs":[137],"transformers":[139],"extract":[141],"complementary":[142,169],"from":[144],"both":[145,202],"RGB":[146],"thermal":[148],"modalities":[149],"at":[150,214],"stages":[152],"extraction,":[155],"thereby":[156],"improving":[157],"adaptability":[159],"diverse":[161],"scenarios.":[163],"Additionally,":[164],"mask":[170],"(CCM)":[171],"strategy,":[172],"applies":[174],"non-overlapping":[175],"random":[176],"masks":[177],"maps":[180],"improve":[182],"robustness":[184],"Extensive":[189],"experiments":[190],"comparative":[192],"analyses":[193],"demonstrate":[194],"that":[195],"our":[196],"MCTrack":[197],"surpasses":[198],"state-of-the-art":[199],"trackers":[200],"publicly":[203],"available":[204,213],"VT-MOT":[205],"UniRTL-MOT":[207],"datasets.":[209],"The":[210],"code":[211],"https://github.com/ydhcg-BoBo/RGB-T-MOT.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
