{"id":"https://openalex.org/W4403488399","doi":"https://doi.org/10.3233/faia240500","title":"TP-GMOT: Tracking Generic Multiple Object by Textual Prompt with Motion-Appearance Cost (MAC) SORT","display_name":"TP-GMOT: Tracking Generic Multiple Object by Textual Prompt with Motion-Appearance Cost (MAC) SORT","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403488399","doi":"https://doi.org/10.3233/faia240500"},"language":"en","primary_location":{"id":"doi:10.3233/faia240500","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240500","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240500","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240500","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023296687","display_name":"Duy Anh","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]},{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US","VN"],"is_corresponding":true,"raw_author_name":"Duy Le Dinh Anh","raw_affiliation_strings":["Department of Computer Science, University of Arkansas, USA","FPT Software AI Center, Vietnam"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"FPT Software AI Center, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":null,"display_name":"DKim Hoang Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]},{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US","VN"],"is_corresponding":false,"raw_author_name":"DKim Hoang Tran","raw_affiliation_strings":["Department of Computer Science, University of Arkansas, USA","FPT Software AI Center, Vietnam"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"FPT Software AI Center, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081787982","display_name":"Dieu T Le","orcid":"https://orcid.org/0000-0002-8678-2503"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DNgan Hoang Le","raw_affiliation_strings":["Department of Computer Science, University of Arkansas, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023296687"],"corresponding_institution_ids":["https://openalex.org/I109689652","https://openalex.org/I78715868"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38596334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8801000118255615,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8801000118255615,"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/sort","display_name":"sort","score":0.8541563749313354},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6132001280784607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6035768389701843},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6020540595054626},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.48537909984588623},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45394259691238403},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.42362287640571594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37003397941589355},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1434791386127472},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.09551462531089783}],"concepts":[{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.8541563749313354},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6132001280784607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6035768389701843},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6020540595054626},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.48537909984588623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45394259691238403},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.42362287640571594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37003397941589355},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1434791386127472},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.09551462531089783},{"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:10.3233/faia240500","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240500","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240500","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240500","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240500","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240500","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403488399.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4285271403","https://openalex.org/W2542007731","https://openalex.org/W4205448459","https://openalex.org/W2968379562","https://openalex.org/W2091015105","https://openalex.org/W4388689193","https://openalex.org/W2110899030","https://openalex.org/W29633852","https://openalex.org/W2985362983","https://openalex.org/W4327670844"],"abstract_inverted_index":{"While":[0],"Multi-Object":[1],"Tracking":[2,27],"(MOT)":[3],"has":[4],"made":[5],"substantial":[6],"advancements,":[7],"it":[8],"is":[9],"limited":[10,18],"by":[11,69,111],"heavy":[12],"reliance":[13],"on":[14,158,185],"prior":[15,37],"knowledge":[16],"and":[17,51,137,175,188,198],"to":[19,141,166],"predefined":[20],"categories.":[21],"In":[22],"contrast,":[23],"Generic":[24],"Multiple":[25],"Object":[26],"(GMOT),":[28],"tracking":[29,147],"multiple":[30,148],"objects":[31,119,150],"with":[32,45,56,94,120,151],"similar":[33],"appearance,":[34],"requires":[35],"less":[36],"information":[38],"about":[39],"the":[40,57,60,143,159,168,171,176,186,192],"targets":[41],"but":[42],"faces":[43],"challenges":[44],"variants":[46],"like":[47],"viewpoint,":[48],"lighting,":[49],"occlusion,":[50],"resolution.":[52],"Our":[53,154,195],"contributions":[54,155],"commence":[55],"introduction":[58],"of":[59,65,73,146,170,178],"Refer-GMOT":[61,160],"dataset":[62,161],"a":[63,79,112,128],"collection":[64],"videos,":[66],"each":[67],"accompanied":[68],"fine-grained":[70],"textual":[71,113],"descriptions":[72],"their":[74],"attributes.":[75],"Subsequently,":[76],"we":[77,101,181],"introduce":[78,102],"novel":[80,104,129],"text":[81],"prompt-based":[82],"open-vocabulary":[83],"GMOT":[84,163],"framework,":[85,100],"called":[86],"TP-GMOT,":[87],"which":[88],"can":[89],"track":[90],"never-seen":[91],"object":[92,109,130],"categories":[93],"zero":[95],"training":[96],"examples.":[97],"Within":[98],"TP-GMOT":[99,173],"two":[103],"components:":[105],"(i)":[106],"TP-OD,":[107],"an":[108],"detection":[110],"prompt,":[114],"for":[115,162,191],"accurately":[116],"detecting":[117],"unseen":[118],"specific":[121],"characteristics.":[122],"(ii)":[123],"Motion-Appearance":[124],"Cost":[125],"SORT":[126],"MAC-SORT,":[127],"association":[131],"approach":[132],"that":[133],"adeptly":[134],"integrates":[135],"motion":[136],"appearance-based":[138],"matching":[139],"strategies":[140],"tackle":[142],"complex":[144],"task":[145],"generic":[149],"high":[152],"similarity.":[153],"are":[156],"benchmarked":[157],"task.":[164,194],"Additionally,":[165],"assess":[167],"generalizability":[169],"proposed":[172],"framework":[174],"effectiveness":[177],"MAC-SORT":[179],"tracker,":[180],"conduct":[182],"ablation":[183],"studies":[184],"DanceTrack":[187],"MOT20":[189],"datasets":[190],"MOT":[193],"dataset,":[196],"code,":[197],"models":[199],"will":[200],"be":[201],"publicly":[202],"available":[203],"at:":[204],"https://fsoft-aic.github.io/TP-GMOT":[205]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
