{"id":"https://openalex.org/W4414360660","doi":"https://doi.org/10.24963/ijcai.2025/153","title":"Exploring Efficient and Effective Sequence Learning for Visual Object Tracking","display_name":"Exploring Efficient and Effective Sequence Learning for Visual Object Tracking","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360660","doi":"https://doi.org/10.24963/ijcai.2025/153"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/153","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5103095710","display_name":"Dongdong Li","orcid":"https://orcid.org/0000-0003-3253-6099"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Li","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113362271","display_name":"Zhinan Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhinan Gao","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066941627","display_name":"Yangliu Kuai","orcid":"https://orcid.org/0000-0001-9357-8482"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangliu Kuai","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403661","display_name":"Rui Chen","orcid":"https://orcid.org/0000-0002-8003-4643"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Chen","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1368","last_page":"1376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9937000274658203,"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":0.9937000274658203,"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/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6525999903678894},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6466000080108643},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.5548999905586243},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5460000038146973},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5220000147819519},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5037999749183655},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5037999749183655},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.4918999969959259},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48420000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6575999855995178},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6525999903678894},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6466000080108643},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.5548999905586243},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5220000147819519},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.35569998621940613},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/153","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":[],"abstract_inverted_index":{"Sequence":[0],"learning":[1,53],"based":[2,54],"tracking":[3,9,44,66,89,148],"frameworks":[4],"are":[5,68,98,180],"popular":[6],"in":[7,56,75,105],"the":[8,76,82,88,103,112,118,123,140],"community.":[10],"In":[11,30,146],"practice,":[12],"its":[13],"auto-regressive":[14,119],"sequence":[15,52,62],"generation":[16,63],"manner":[17,108],"leads":[18],"to":[19,33,70,134],"inferior":[20],"performance":[21,173],"and":[22,41,61,73,109,155,170,178],"high":[23],"latency":[24],"compared":[25,91,116],"with":[26,92,117],"latest":[27],"advanced":[28],"trackers.":[29,176],"this":[31,35],"paper,":[32],"mitigate":[34],"issue,":[36],"we":[37,126],"propose":[38],"an":[39],"efficient":[40],"effective":[42],"sequence-to-sequence":[43],"framework":[45],"named":[46],"FastSeqTrack.":[47],"FastSeqTrack":[48,165],"differs":[49],"from":[50],"previous":[51],"trackers":[55],"terms":[57],"of":[58],"token":[59],"initialization":[60],"manner.":[64,120],"Four":[65],"tokens":[67,97],"appended":[69],"patch":[71],"embeddings":[72],"generated":[74],"encoder":[77],"as":[78],"initial":[79],"guesses":[80],"for":[81],"bounding":[83],"box":[84],"sequence,":[85],"which":[86],"improves":[87],"accuracy":[90],"randomly":[93],"initialized":[94],"tokens.":[95],"Tracking":[96],"then":[99],"parallelly":[100],"fed":[101],"into":[102],"decoder":[104,132],"a":[106],"one-pass":[107],"greatly":[110],"boost":[111],"forward":[113,137],"inference":[114,138],"speed":[115],"Inspired":[121],"by":[122],"early-exit":[124],"mechanism,":[125],"inject":[127],"internal":[128],"classifiers":[129],"after":[130],"each":[131],"layer":[133],"early":[135,150],"terminate":[136],"when":[139],"softmax":[141],"confidence":[142],"is":[143],"sufficiently":[144],"reliable.":[145],"easy":[147],"frames,":[149],"exits":[151],"avoid":[152],"network":[153],"overthinking":[154],"unnecessary":[156],"computation.":[157],"Extensive":[158],"experiments":[159],"on":[160],"multiple":[161],"benchmarks":[162],"demonstrate":[163],"that":[164],"runs":[166],"over":[167],"100":[168],"fps":[169],"showcases":[171],"superior":[172],"against":[174],"state-of-the-art":[175],"Codes":[177],"models":[179],"available":[181],"at":[182],"https://github.com/vision4drones/FastSeqTrack.":[183]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}