{"id":"https://openalex.org/W4392904092","doi":"https://doi.org/10.1109/icassp48485.2024.10447535","title":"Visual-Linguistic Representation Learning with Deep Cross-Modality Fusion for Referring Multi-Object Tracking","display_name":"Visual-Linguistic Representation Learning with Deep Cross-Modality Fusion for Referring Multi-Object Tracking","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904092","doi":"https://doi.org/10.1109/icassp48485.2024.10447535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102627972","display_name":"Wenyan He","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyan He","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042786745","display_name":"Yajun Jian","orcid":"https://orcid.org/0000-0003-3068-6771"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajun Jian","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,Xiamen,China","Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454257","display_name":"Lu Yang","orcid":"https://orcid.org/0000-0002-5428-7874"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Lu","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044594971","display_name":"Hanzi Wang","orcid":"https://orcid.org/0000-0002-6913-9786"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6310","last_page":"6314"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9977999925613403,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962000250816345,"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":0.7544276714324951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7102227807044983},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6952628493309021},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.6635373830795288},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.601649284362793},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5985541939735413},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5771546363830566},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5598313212394714},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5045510530471802},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49944519996643066},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47346559166908264},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.471913605928421},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32075685262680054},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.23727843165397644},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08912265300750732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544276714324951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7102227807044983},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6952628493309021},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6635373830795288},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.601649284362793},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5985541939735413},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5771546363830566},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5598313212394714},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5045510530471802},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49944519996643066},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47346559166908264},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.471913605928421},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32075685262680054},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.23727843165397644},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08912265300750732},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[],"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":27,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2603203130","https://openalex.org/W2963351448","https://openalex.org/W2965373594","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3091588028","https://openalex.org/W3094000868","https://openalex.org/W3104778224","https://openalex.org/W3115390238","https://openalex.org/W3122239467","https://openalex.org/W3159619744","https://openalex.org/W4225274309","https://openalex.org/W4286904999","https://openalex.org/W4312473433","https://openalex.org/W4312956471","https://openalex.org/W4372260587","https://openalex.org/W4372270322","https://openalex.org/W4386071476","https://openalex.org/W4386076180","https://openalex.org/W6766673545","https://openalex.org/W6784094891","https://openalex.org/W6787985011","https://openalex.org/W6788023325","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W2379407973","https://openalex.org/W2965594636"],"abstract_inverted_index":{"Referring":[0],"multi-object":[1,31],"tracking":[2,14,37,49,78],"is":[3,69],"a":[4,19,24,99,104],"new":[5],"rising":[6],"research":[7],"topic":[8],"that":[9],"aims":[10],"at":[11],"detecting":[12],"and":[13,47,75,84,103,113],"the":[15,117,124,127],"referred":[16],"objects":[17],"in":[18,51,60],"video":[20],"sequence":[21],"based":[22],"on":[23,123],"natural":[25],"language":[26,85],"expression.":[27],"Compared":[28],"with":[29,38,90],"traditional":[30],"tracking,":[32],"this":[33],"setting":[34],"guides":[35],"object":[36,111],"high-level":[39],"semantic":[40],"information,":[41],"which":[42],"may":[43],"bring":[44],"more":[45],"flexible":[46],"robust":[48],"performance":[50],"practical":[52],"scenarios.":[53],"However,":[54],"existing":[55],"methods":[56],"perform":[57],"cross-modal":[58],"fusion":[59],"only":[61],"one":[62],"phase.":[63],"The":[64],"limitation":[65],"of":[66,129],"visual-linguistic":[67,119],"representation":[68],"prone":[70],"to":[71],"causing":[72],"visionlanguage":[73],"mismatching":[74],"producing":[76],"poor":[77],"results.":[79],"To":[80],"effectively":[81],"fuse":[82],"vision":[83],"modalities,":[86],"we":[87],"propose":[88],"DeepRMOT":[89,108],"deep":[91],"cross-modality":[92,105],"fusion,":[93],"including":[94],"an":[95],"enhanced":[96,118],"early-fusion":[97],"module,":[98],"bidirectional":[100],"crossmodality":[101],"encoder,":[102],"decoder.":[106],"Therefore,":[107],"can":[109],"boost":[110],"detection":[112],"data":[114],"association":[115],"by":[116],"representation.":[120],"Extensive":[121],"experiments":[122],"Refer-KITTI":[125],"demonstrate":[126],"effectiveness":[128],"our":[130],"method.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}