{"id":"https://openalex.org/W4409129237","doi":"https://doi.org/10.1109/tmm.2025.3557710","title":"Visual-Linguistic Feature Alignment With Semantic and Kinematic Guidance for Referring Multi-Object Tracking","display_name":"Visual-Linguistic Feature Alignment With Semantic and Kinematic Guidance for Referring Multi-Object Tracking","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409129237","doi":"https://doi.org/10.1109/tmm.2025.3557710"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3557710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557710","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yizhe Li","orcid":"https://orcid.org/0009-0004-1193-7007"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhe Li","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi'an Jiaotong University, Xi'an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-1193-7007","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, 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":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanping Zhou","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi'an Jiaotong University, Xi'an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-4100-2304","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng Qin","orcid":"https://orcid.org/0009-0008-4301-8952"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Qin","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi'an Jiaotong University, Xi'an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0008-4301-8952","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Le Wang","orcid":"https://orcid.org/0000-0001-6636-6396"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Wang","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi'an Jiaotong University, Xi'an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-6636-6396","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":2.792,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9015453,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"3034","last_page":"3044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8863000273704529,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.8863000273704529,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13382","display_name":"Robotics and Automated Systems","score":0.8759999871253967,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8342000246047974,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8431724905967712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6316007375717163},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5423427820205688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5305628776550293},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5283874869346619},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5151838064193726},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46087485551834106},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4572370648384094},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2500112056732178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431724905967712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6316007375717163},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5423427820205688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5305628776550293},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5283874869346619},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5151838064193726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46087485551834106},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4572370648384094},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2500112056732178},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3557710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557710","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G1999039755","display_name":null,"funder_award_id":"2023ZD0121300","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"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"},{"id":"https://openalex.org/G524075158","display_name":null,"funder_award_id":"12326608","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7600037353","display_name":null,"funder_award_id":"XTR042021005","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8442236830","display_name":null,"funder_award_id":"U24A20325","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/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"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":53,"referenced_works":["https://openalex.org/W1786529921","https://openalex.org/W2138302688","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2252355370","https://openalex.org/W2603203130","https://openalex.org/W2940963663","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2969535679","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3092725515","https://openalex.org/W3094000868","https://openalex.org/W3106763294","https://openalex.org/W3119686997","https://openalex.org/W3164698655","https://openalex.org/W3215899623","https://openalex.org/W4214490042","https://openalex.org/W4214627427","https://openalex.org/W4224988000","https://openalex.org/W4226024706","https://openalex.org/W4283748233","https://openalex.org/W4286904999","https://openalex.org/W4312351586","https://openalex.org/W4312473433","https://openalex.org/W4313117614","https://openalex.org/W4318954130","https://openalex.org/W4319866011","https://openalex.org/W4385245566","https://openalex.org/W4386065416","https://openalex.org/W4386071948","https://openalex.org/W4386076180","https://openalex.org/W4386076204","https://openalex.org/W4386083103","https://openalex.org/W4386083136","https://openalex.org/W4390872868","https://openalex.org/W4392904092","https://openalex.org/W4393178550","https://openalex.org/W4396239517","https://openalex.org/W4401506914","https://openalex.org/W4402726924","https://openalex.org/W4402727808","https://openalex.org/W4409366257","https://openalex.org/W6684191040","https://openalex.org/W6757817989","https://openalex.org/W6766673545","https://openalex.org/W6780226713","https://openalex.org/W6784094891","https://openalex.org/W6788023325","https://openalex.org/W6850625674","https://openalex.org/W6868907939","https://openalex.org/W6869610258"],"related_works":["https://openalex.org/W2364155688","https://openalex.org/W2046522763","https://openalex.org/W2366916257","https://openalex.org/W2375847997","https://openalex.org/W2072836406","https://openalex.org/W2391772185","https://openalex.org/W2061641547","https://openalex.org/W2355099127","https://openalex.org/W2361892564","https://openalex.org/W1847280318"],"abstract_inverted_index":{"Referring":[0],"Multi-Object":[1],"Tracking":[2],"(RMOT)":[3],"aims":[4],"to":[5,19,44,49,75,84,135,155],"dynamically":[6],"track":[7],"an":[8],"arbitrary":[9],"number":[10],"of":[11,140,185],"referred":[12,57],"targets":[13,51,161],"in":[14,131],"a":[15,101,113,118,132],"video":[16],"sequence":[17],"according":[18],"the":[20,31,38,61,87,109,124,137,141,144,157,171,183],"language":[21,62,93,163],"expression.":[22],"Previous":[23],"methods":[24],"mainly":[25],"focus":[26],"on":[27,170],"cross-modal":[28],"fusion":[29,149],"at":[30],"feature":[32,148],"level":[33],"with":[34,64,79,90,112,165],"designed":[35],"structures.":[36],"However,":[37],"insufficient":[39],"visual-linguistic":[40,46,77],"alignment":[41,78,138,151,158],"is":[42],"prone":[43],"causing":[45],"mismatches,":[47],"leading":[48],"some":[50],"being":[52],"tracked":[53],"but":[54],"not":[55],"correctly":[56],"especially":[58],"when":[59],"facing":[60],"expression":[63,164],"complex":[65],"semantics":[66],"or":[67],"motion":[68,166],"descriptions.":[69,167],"To":[70],"this":[71,96],"end,":[72],"we":[73,98],"propose":[74],"conduct":[76],"semantic":[80,128],"and":[81,117,150,162,173,181,188],"kinematic":[82],"guidance":[83],"effectively":[85],"align":[86],"visual":[88,160],"features":[89],"more":[91],"diverse":[92],"expressions.":[94],"In":[95,122],"paper,":[97],"put":[99],"forward":[100],"novel":[102],"end-to-end":[103],"RMOT":[104],"framework":[105,187],"SKTrack,":[106],"which":[107],"follows":[108],"transformer-based":[110],"architecture":[111],"Language-Guided":[114],"Decoder":[115],"(LGD)":[116],"Motion-Aware":[119],"Aggregator":[120],"(MAA).":[121],"particular,":[123],"LGD":[125],"performs":[126],"deep":[127],"interaction":[129],"layer-by-layer":[130],"single":[133],"frame":[134],"enhance":[136],"ability":[139],"model,":[142],"while":[143],"MAA":[145],"conducts":[146],"temporal":[147],"across":[152],"multiple":[153],"frames":[154],"enable":[156],"between":[159],"Extensive":[168],"experiments":[169],"Refer-KITTI":[172],"Refer-KITTI-v2":[174],"demonstrate":[175],"that":[176],"SKTrack":[177],"achieves":[178],"state-of-the-art":[179],"performance":[180],"verify":[182],"effectiveness":[184],"our":[186],"its":[189],"components.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-04T07:04:00.330322","created_date":"2025-10-10T00:00:00"}