{"id":"https://openalex.org/W4403780611","doi":"https://doi.org/10.1145/3664647.3681530","title":"GLATrack: Global and Local Awareness for Open-Vocabulary Multiple Object Tracking","display_name":"GLATrack: Global and Local Awareness for Open-Vocabulary Multiple Object Tracking","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780611","doi":"https://doi.org/10.1145/3664647.3681530"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681530","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681530","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681530?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681530?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Guangyao Li","orcid":"https://orcid.org/0009-0004-2510-6378"},"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":true,"raw_author_name":"Guangyao Li","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & 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/A5109692717","display_name":"Yajun Jian","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":"Yajun Jian","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & 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/A5109692717","display_name":"Yajun Jian","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":"Yajun Jian","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & 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/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"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":"Yan Yan","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & 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/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"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":"Yan Yan","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & 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":null,"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":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & 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":null,"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":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University & 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":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.3376,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67376034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2457","last_page":"2466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9567000269889832,"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":0.9567000269889832,"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/T10050","display_name":"Multi-Criteria Decision Making","score":0.9388999938964844,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9383999705314636,"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":0.7393450736999512},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.683375358581543},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6262744069099426},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5106144547462463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.471314013004303},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33828485012054443},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33631229400634766},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16437691450119019},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09238007664680481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7393450736999512},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.683375358581543},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6262744069099426},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5106144547462463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.471314013004303},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33828485012054443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33631229400634766},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16437691450119019},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09238007664680481},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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:10.1145/3664647.3681530","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681530","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681530?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681530","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681530","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681530?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2022121445","display_name":null,"funder_award_id":"U21A20514","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4782616423","display_name":null,"funder_award_id":"62372388","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5058181936","display_name":null,"funder_award_id":"207140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8055606312","display_name":null,"funder_award_id":"62071404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8565926968","display_name":null,"funder_award_id":"U21A2051","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403780611.pdf","grobid_xml":"https://content.openalex.org/works/W4403780611.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1566405224","https://openalex.org/W2138302688","https://openalex.org/W2142996775","https://openalex.org/W2252355370","https://openalex.org/W2603203130","https://openalex.org/W2609532991","https://openalex.org/W2613718673","https://openalex.org/W2920942303","https://openalex.org/W2928165649","https://openalex.org/W2963150697","https://openalex.org/W2981393651","https://openalex.org/W2982723417","https://openalex.org/W2983208726","https://openalex.org/W3035172746","https://openalex.org/W3035442500","https://openalex.org/W3035564946","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3093175170","https://openalex.org/W3093256682","https://openalex.org/W3095753995","https://openalex.org/W3097883757","https://openalex.org/W3097885906","https://openalex.org/W3104218139","https://openalex.org/W3104778224","https://openalex.org/W3116469262","https://openalex.org/W3119686997","https://openalex.org/W3173859428","https://openalex.org/W3174101598","https://openalex.org/W3205307530","https://openalex.org/W3207282964","https://openalex.org/W4284961860","https://openalex.org/W4286904999","https://openalex.org/W4304091839","https://openalex.org/W4312424618","https://openalex.org/W4312473433","https://openalex.org/W4312509508","https://openalex.org/W4312547276","https://openalex.org/W4312563428","https://openalex.org/W4312689495","https://openalex.org/W4312747482","https://openalex.org/W4312818263","https://openalex.org/W4312933868","https://openalex.org/W4312956471","https://openalex.org/W4313026212","https://openalex.org/W4382240079","https://openalex.org/W4385245566","https://openalex.org/W4385575022","https://openalex.org/W4386065383","https://openalex.org/W4386065398","https://openalex.org/W4386066010","https://openalex.org/W4386076029","https://openalex.org/W4386076116","https://openalex.org/W4386076204","https://openalex.org/W4386076331","https://openalex.org/W4386076396","https://openalex.org/W4386083103","https://openalex.org/W4387967948","https://openalex.org/W4387968137","https://openalex.org/W4390873612","https://openalex.org/W4390874237","https://openalex.org/W4390874578","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2084086966","https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W2158788032"],"abstract_inverted_index":{"Open-vocabulary":[0],"multi-object":[1],"tracking":[2],"(MOT)":[3],"aims":[4],"to":[5,64,85,120,140,157],"track":[6],"arbitrary":[7],"objects":[8],"encountered":[9],"in":[10,129,174,178],"the":[11,15,35,41,66,100,104,109,145,181],"real":[12],"world":[13],"beyond":[14],"training":[16],"set.":[17],"However,":[18],"recent":[19],"methods":[20],"rely":[21],"solely":[22],"on":[23,180],"instance-level":[24,75],"detection":[25],"and":[26,45,55,74,98,108,176],"association":[27],"of":[28,40,68,172],"novel":[29],"objects,":[30],"which":[31,62,94,132],"may":[32],"not":[33],"consider":[34],"valuable":[36,135],"fine-grained":[37],"semantic":[38,96,117,122],"representations":[39,160],"targets":[42,162],"within":[43,137],"key":[44,130],"reference":[46,138],"frames.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,78,150],"propose":[52,114],"a":[53,80,115],"Global":[54],"Local":[56],"Awareness":[57],"open-vocabulary":[58],"MOT":[59,70],"method":[60,168],"(GLATrack),":[61],"learns":[63],"tackle":[65],"task":[67],"real-world":[69],"from":[71,125],"both":[72],"global":[73,87],"perspectives.":[76],"Specifically,":[77],"introduce":[79,151],"region-aware":[81],"feature":[82,106],"enhancement":[83],"module":[84,156],"refine":[86],"knowledge":[88,146],"for":[89,161],"complementing":[90],"local":[91],"target":[92,127],"information,":[93],"enhances":[95],"representation":[97,143],"bridges":[99],"distribution":[101],"gap":[102],"between":[103],"image":[105],"map":[107],"pooled":[110],"regional":[111],"features.":[112],"We":[113],"bidirectional":[116],"complementarity":[118],"strategy":[119],"mitigate":[121],"misalignment":[123],"arising":[124],"missing":[126],"information":[128,136],"frames,":[131],"dynamically":[133],"selects":[134],"frames":[139],"enrich":[141],"object":[142],"during":[144],"distillation":[147],"process.":[148],"Furthermore,":[149],"an":[152,170],"appearance":[153],"richness":[154],"measurement":[155],"provide":[158],"appropriate":[159],"with":[163],"different":[164],"appearances.":[165],"The":[166],"proposed":[167],"gains":[169],"improvement":[171],"6.9%":[173],"TETA":[175],"5.6%":[177],"mAP":[179],"large-scale":[182],"TAO":[183],"benchmark.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}