{"id":"https://openalex.org/W4402981795","doi":"https://doi.org/10.1109/icme57554.2024.10688191","title":"Learning Motion Priors with DETR for Visual Tracking","display_name":"Learning Motion Priors with DETR for Visual Tracking","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981795","doi":"https://doi.org/10.1109/icme57554.2024.10688191"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688191","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5102677150","display_name":"Qingmao Wei","orcid":"https://orcid.org/0000-0001-9982-3119"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingmao Wei","raw_affiliation_strings":["GuangDong University of Technology"],"affiliations":[{"raw_affiliation_string":"GuangDong University of Technology","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073040865","display_name":"Bi Zeng","orcid":"https://orcid.org/0000-0001-8596-8333"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bi Zeng","raw_affiliation_strings":["GuangDong University of Technology"],"affiliations":[{"raw_affiliation_string":"GuangDong University of Technology","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103186689","display_name":"Guotian Zeng","orcid":"https://orcid.org/0000-0002-3435-7580"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guotian Zeng","raw_affiliation_strings":["GuangDong University of Technology"],"affiliations":[{"raw_affiliation_string":"GuangDong University of Technology","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102677150"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16878005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9947999715805054,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9947999715805054,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9794999957084656,"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":0.9391000270843506,"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/prior-probability","display_name":"Prior probability","score":0.7193572521209717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7015045881271362},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6758158206939697},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6702884435653687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6194865703582764},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5476773977279663},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11154496669769287}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7193572521209717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015045881271362},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6758158206939697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6702884435653687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6194865703582764},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5476773977279663},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11154496669769287},{"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/icme57554.2024.10688191","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Recent":[0],"transformer-based":[1],"visual":[2,37],"tracking":[3,39],"models":[4],"have":[5,12],"demonstrated":[6],"superior":[7],"performance.":[8],"However,":[9],"prior":[10],"works":[11],"been":[13],"resource-intensive,":[14],"requiring":[15],"massive":[16],"GPU":[17],"training":[18,69],"hours.":[19],"This":[20],"resource":[21],"demand":[22],"renders":[23],"them":[24],"unsuitable":[25],"for":[26],"real-world":[27],"applications.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"present":[33],"DETRack,":[34],"a":[35,62,67,103,117],"training-friendly":[36],"object":[38],"framework":[40,49],"that":[41],"can":[42],"integrate":[43],"motion":[44],"priors":[45],"by":[46],"learning.":[47],"Our":[48],"utilizes":[50],"an":[51],"efficient":[52],"encoder-decoder":[53],"structure,":[54],"with":[55],"the":[56,77,85],"deformable":[57],"transformer":[58],"decoder":[59],"serving":[60],"as":[61],"target":[63],"head.":[64],"We":[65],"introduce":[66],"denoising":[68],"strategy":[70],"to":[71,99,112],"simulate":[72],"historical":[73],"predictions":[74],"and":[75,87],"enrich":[76],"supervision":[78],"signal":[79],"during":[80],"training.":[81],"Comprehensive":[82],"experiments":[83],"confirm":[84],"effectiveness":[86],"efficiency":[88],"of":[89],"our":[90],"proposed":[91],"method.":[92],"Notably,":[93],"it":[94],"only":[95],"takes":[96],"11":[97],"hours":[98],"train":[100],"DETRack":[101],"on":[102,109],"single":[104],"RTX2080Ti,":[105],"achieving":[106],"comparable":[107],"performance":[108],"multiple":[110],"benchmarks":[111],"advanced":[113],"trackers":[114],"while":[115],"maintaining":[116],"high":[118],"running":[119],"speed.":[120]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}