{"id":"https://openalex.org/W4413017586","doi":"https://doi.org/10.1109/access.2025.3596215","title":"Improving Token-Based Object Detection With Video","display_name":"Improving Token-Based Object Detection With Video","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413017586","doi":"https://doi.org/10.1109/access.2025.3596215"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3596215","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3596215","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3596215","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091387172","display_name":"Abhineet Singh","orcid":"https://orcid.org/0000-0002-5624-8377"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abhineet Singh","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada","Department of Computing Science, University of Alberta, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5624-8377","affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082800075","display_name":"Nilanjan Ray","orcid":"https://orcid.org/0000-0002-7588-5400"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nilanjan Ray","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada","Department of Computing Science, University of Alberta, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7588-5400","affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15364946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"138622","last_page":"138639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.992900013923645,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9746999740600586,"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":0.8176069259643555},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5793451070785522},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4560615122318268},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4389650821685791},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4293504059314728},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4253285229206085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40484219789505005},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23249691724777222},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.17175588011741638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176069259643555},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5793451070785522},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4560615122318268},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4389650821685791},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4293504059314728},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4253285229206085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40484219789505005},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23249691724777222},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.17175588011741638}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3596215","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3596215","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2506.22562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22562","pdf_url":"https://arxiv.org/pdf/2506.22562","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:fe90c646c0b04f6ea54d398a41869428","is_oa":true,"landing_page_url":"https://doaj.org/article/fe90c646c0b04f6ea54d398a41869428","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 138622-138639 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3596215","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3596215","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2194775991","https://openalex.org/W2252355370","https://openalex.org/W2335901184","https://openalex.org/W2570343428","https://openalex.org/W2618530766","https://openalex.org/W2766984662","https://openalex.org/W2806070179","https://openalex.org/W2911653429","https://openalex.org/W2950418233","https://openalex.org/W2962683745","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963516811","https://openalex.org/W2989676862","https://openalex.org/W2990503944","https://openalex.org/W3003490096","https://openalex.org/W3018757597","https://openalex.org/W3033613646","https://openalex.org/W3034467781","https://openalex.org/W3034971973","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3133275180","https://openalex.org/W3138516171","https://openalex.org/W3160833223","https://openalex.org/W3172752666","https://openalex.org/W3201476065","https://openalex.org/W3204023867","https://openalex.org/W4221166276","https://openalex.org/W4226476965","https://openalex.org/W4283795993","https://openalex.org/W4285110782","https://openalex.org/W4285203457","https://openalex.org/W4294167341","https://openalex.org/W4309181071","https://openalex.org/W4312604781","https://openalex.org/W4312713936","https://openalex.org/W4313068342","https://openalex.org/W4313183732","https://openalex.org/W4382469019","https://openalex.org/W4385245566","https://openalex.org/W4385569741","https://openalex.org/W4386066081","https://openalex.org/W4386075493","https://openalex.org/W4388585137","https://openalex.org/W4388823657","https://openalex.org/W4390872705","https://openalex.org/W4390873622","https://openalex.org/W4401393088","https://openalex.org/W4403770406","https://openalex.org/W6947681574"],"related_works":["https://openalex.org/W4389065903","https://openalex.org/W2385949326","https://openalex.org/W2623195638","https://openalex.org/W1966005655","https://openalex.org/W3135795035","https://openalex.org/W2789220062","https://openalex.org/W2811496562","https://openalex.org/W2094665863","https://openalex.org/W2071984725","https://openalex.org/W2185534064"],"abstract_inverted_index":{"This":[0,74,145],"paper":[1],"improves":[2,29],"upon":[3,30],"the":[4,15,71,76,80,93,111,136,158,161,165,176,180,189,230,234,238],"Pix2Seq":[5,191],"object":[6,26],"detector":[7,187,193],"[1]":[8],"by":[9,39,155,208],"extending":[10],"it":[11,17,107,147,216,226],"for":[12],"videos.":[13],"In":[14],"process,":[16],"introduces":[18],"a":[19],"new":[20],"way":[21],"to":[22,65,78,134,148,172,223],"perform":[23],"end-to-end":[24],"video":[25,32,56,112,137,162,186,219],"detection":[27],"that":[28,86,164,225],"existing":[31],"detectors":[33,89,220],"in":[34,70,141],"two":[35],"key":[36],"ways.":[37],"First,":[38],"representing":[40],"objects":[41,113],"as":[42,114,139,168],"variable-length":[43],"sequences":[44],"of":[45,55,82,96,124,160,205,233],"discrete":[46],"tokens,":[47],"we":[48],"can":[49,178],"succinctly":[50],"represent":[51],"widely":[52],"varying":[53],"numbers":[54],"objects,":[57],"with":[58,151,188,202,217,229,237],"diverse":[59],"shapes":[60],"and":[61,90,101,109,117,129,197,245],"locations,":[62],"without":[63],"having":[64],"inject":[66],"any":[67],"localization":[68],"cues":[69],"training":[72,100],"process.":[73],"eliminates":[75],"need":[77],"sample":[79],"space":[81],"all":[83],"possible":[84],"boxes":[85,120,128,132],"constrains":[87],"conventional":[88,143],"thus":[91],"solves":[92],"dual":[94],"problems":[95],"loss":[97],"sparsity":[98],"during":[99,104],"heuristics-based":[102],"postprocessing":[103],"inference.":[105],"Second,":[106],"conceptualizes":[108],"outputs":[110],"fully":[115],"integrated":[116],"indivisible":[118],"3D":[119],"or":[121],"tracklets":[122],"instead":[123],"generating":[125],"image-specific":[126],"2D":[127],"linking":[130],"these":[131],"together":[133],"construct":[135],"object,":[138],"done":[140],"most":[142],"detectors.":[144],"allows":[146],"scale":[149],"effortlessly":[150],"available":[152,248],"computational":[153,211,239],"resources":[154],"simply":[156],"increasing":[157],"length":[159],"subsequence":[163,177],"network":[166],"takes":[167],"input,":[169],"even":[170,236],"generalizing":[171],"multi-object":[173],"tracking":[174],"if":[175],"span":[179],"entire":[181],"video.":[182],"We":[183,213,241],"compare":[184,215],"our":[185,209,243],"baseline":[190],"static":[192],"on":[194,221],"several":[195,218],"datasets":[196],"demonstrate":[198],"consistent":[199],"improvement,":[200],"although":[201],"strong":[203],"signs":[204],"being":[206],"bottlenecked":[207],"limited":[210],"resources.":[212],"also":[214],"UA-DETRAC":[222],"show":[224],"is":[227],"competitive":[228],"current":[231],"state":[232],"art":[235],"bottleneck.":[240],"make":[242],"code":[244],"models":[246],"publicly":[247],"[66].":[249]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}