{"id":"https://openalex.org/W3106542916","doi":"https://doi.org/10.1109/tcsvt.2020.3038720","title":"Grounding-Tracking-Integration","display_name":"Grounding-Tracking-Integration","publication_year":2020,"publication_date":"2020-11-17","ids":{"openalex":"https://openalex.org/W3106542916","doi":"https://doi.org/10.1109/tcsvt.2020.3038720","mag":"3106542916"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2020.3038720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3038720","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/A5050209478","display_name":"Zhengyuan Yang","orcid":"https://orcid.org/0000-0002-5808-0889"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-5808-0889","affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069983647","display_name":"Tushar Kumar","orcid":"https://orcid.org/0000-0003-0978-9004"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Kumar","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-0978-9004","affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015882351","display_name":"Tianlang Chen","orcid":"https://orcid.org/0000-0002-6355-6474"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianlang Chen","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-6355-6474","affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112584233","display_name":"Jingsong Su","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingsong Su","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-5606-7122","affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"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":"Jiebo Luo","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-4516-9729","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.8599,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.86589673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"31","issue":"9","first_page":"3433","last_page":"3443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9997000098228455,"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":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9990000128746033,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9957000017166138,"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":0.5718380212783813},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4752117097377777},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4511326253414154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.412768691778183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5718380212783813},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4752117097377777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4511326253414154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.412768691778183},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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:10.1109/tcsvt.2020.3038720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3038720","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":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4283415030","display_name":"RI: Medium:  Collaborative Research: Understanding and Editing Visual Sentiments","funder_award_id":"1704337","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4319893781","display_name":"SCH: INT: Multispectral Panoramic 3-D Endoscopic Imaging","funder_award_id":"1722847","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5926384816","display_name":"RI: Small: Learning Dynamics and Evolution towards Cognitive Understanding of Videos","funder_award_id":"1813709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W182940129","https://openalex.org/W1536680647","https://openalex.org/W1857884451","https://openalex.org/W1955741794","https://openalex.org/W1995903777","https://openalex.org/W2044986361","https://openalex.org/W2089961441","https://openalex.org/W2117539524","https://openalex.org/W2154889144","https://openalex.org/W2158592639","https://openalex.org/W2158827467","https://openalex.org/W2214352687","https://openalex.org/W2251512949","https://openalex.org/W2335901184","https://openalex.org/W2470394683","https://openalex.org/W2489434015","https://openalex.org/W2557641257","https://openalex.org/W2565639579","https://openalex.org/W2568262903","https://openalex.org/W2571175805","https://openalex.org/W2606473278","https://openalex.org/W2747053578","https://openalex.org/W2769941643","https://openalex.org/W2796347433","https://openalex.org/W2799058067","https://openalex.org/W2806224701","https://openalex.org/W2886904239","https://openalex.org/W2891033863","https://openalex.org/W2900474539","https://openalex.org/W2904164128","https://openalex.org/W2920326761","https://openalex.org/W2963471260","https://openalex.org/W2963534981","https://openalex.org/W2963541336","https://openalex.org/W2963783181","https://openalex.org/W2963843782","https://openalex.org/W2964242925","https://openalex.org/W2964345792","https://openalex.org/W2966759264","https://openalex.org/W2971900262","https://openalex.org/W2982651953","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3001584168","https://openalex.org/W3010072143","https://openalex.org/W3034298080","https://openalex.org/W3035590142","https://openalex.org/W3100935401","https://openalex.org/W3102624093","https://openalex.org/W3110435696","https://openalex.org/W4289126595","https://openalex.org/W4293584584","https://openalex.org/W6750227808","https://openalex.org/W6753610190","https://openalex.org/W6756015008","https://openalex.org/W6757135208","https://openalex.org/W6772516908"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"this":[1,115],"paper,":[2],"we":[3,93,117,190],"study":[4],"tracking":[5,162,201],"by":[6,80,202],"language":[7,20,59,203],"that":[8,28,122],"localizes":[9,62],"the":[10,30,47,53,58,63,67,70,87,91,98,101,109,130,135,139,144,150,154,173,178],"target":[11,64],"box":[12,48],"sequence":[13,49],"in":[14,73,104,163],"a":[15,19,24,192],"video":[16],"based":[17,65],"on":[18,66,180],"query.":[21,60],"We":[22,166],"propose":[23,118],"framework":[25,179],"called":[26],"GTI":[27,170],"decomposes":[29],"problem":[31],"into":[32],"three":[33,40],"sub-tasks:":[34],"Grounding,":[35],"Tracking,":[36],"and":[37,45,84,107,124,146,176,182],"Integration.":[38],"The":[39],"sub-task":[41],"modules":[42],"operate":[43],"simultaneously":[44],"predict":[46],"frame-by-frame.":[50],"\u201cGrounding\u201d":[51],"predicts":[52,125],"referred":[54],"region":[55,155],"directly":[56],"from":[57],"\u201cTracking\u201d":[61],"history":[68],"of":[69,100,195],"grounded":[71,102],"regions":[72,103],"previous":[74],"frames.":[75,165],"\u201cIntegration\u201d":[76],"generates":[77],"final":[78],"predictions":[79],"synergistically":[81],"combining":[82],"grounding":[83,140],"tracking.":[85],"With":[86],"\u201cintegration\u201d":[88],"task":[89],"as":[90],"key,":[92],"explore":[94],"how":[95],"to":[96,128,160,198],"indicate":[97],"quality":[99,152],"each":[105],"frame":[106],"achieve":[108],"desired":[110],"mutually":[111],"beneficial":[112],"combination.":[113],"To":[114],"end,":[116],"an":[119],"\u201cRT-integration\u201d":[120],"method":[121],"defines":[123],"two":[126],"scores":[127],"guide":[129],"integration:":[131],"1)":[132],"R-score":[133],"represents":[134,149],"Region":[136],"correctness":[137],"whether":[138,153],"prediction":[141],"accurately":[142],"covers":[143],"target,":[145],"2)":[147],"T-score":[148],"Template":[151],"provides":[156],"informative":[157],"visual":[158],"cues":[159],"improve":[161],"future":[164,200],"present":[167],"our":[168],"real-time":[169],"implementation":[171],"with":[172,185],"proposed":[174],"RT-integration,":[175],"benchmark":[177],"LaSOT":[181,196],"Lingual":[183],"OTB99":[184],"highly":[186],"promising":[187],"results.":[188],"Moreover,":[189],"produce":[191],"disambiguated":[193],"version":[194],"queries":[197],"facilitate":[199],"studies.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}