{"id":"https://openalex.org/W7125960914","doi":"https://doi.org/10.1016/j.patcog.2026.113184","title":"MonoTDF: Temporal deep feature learning for generalizable monocular 3D object detection","display_name":"MonoTDF: Temporal deep feature learning for generalizable monocular 3D object detection","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125960914","doi":"https://doi.org/10.1016/j.patcog.2026.113184"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.113184","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113184","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Pattern Recognition","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patcog.2026.113184","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053133694","display_name":"Xiu-Zhi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]},{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]},{"id":"https://openalex.org/I49645291","display_name":"National Taipei University of Education","ror":"https://ror.org/02bzpph30","country_code":"TW","type":"education","lineage":["https://openalex.org/I49645291"]},{"id":"https://openalex.org/I99613584","display_name":"National Taipei University","ror":"https://ror.org/03e29r284","country_code":"TW","type":"education","lineage":["https://openalex.org/I99613584"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Xiu-Zhi Chen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, 10608, Taiwan, R.O.C"],"raw_orcid":"https://orcid.org/0009-0009-0327-6209","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, 10608, Taiwan, R.O.C","institution_ids":["https://openalex.org/I118292597","https://openalex.org/I154864474","https://openalex.org/I49645291","https://openalex.org/I99613584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102550992","display_name":"Yi-Kai Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801834177","display_name":"Taipei City Government","ror":"https://ror.org/02eqw3q87","country_code":"TW","type":"government","lineage":["https://openalex.org/I2801834177"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Kai Chiu","raw_affiliation_strings":["Y-WELL CO., LTD., New Taipei City, 22161, Taiwan, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Y-WELL CO., LTD., New Taipei City, 22161, Taiwan, R.O.C","institution_ids":["https://openalex.org/I2801834177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102836324","display_name":"Chih-Sheng Huang","orcid":"https://orcid.org/0000-0002-8836-4970"},"institutions":[{"id":"https://openalex.org/I4210159061","display_name":"ELAN Microelectronics (Taiwan)","ror":"https://ror.org/051d31036","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210159061"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Sheng Huang","raw_affiliation_strings":["ELAN Microelectronics Corp, Hsinchu 300092, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-8836-4970","affiliations":[{"raw_affiliation_string":"ELAN Microelectronics Corp, Hsinchu 300092, Taiwan","institution_ids":["https://openalex.org/I4210159061"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120960820","display_name":"Yen-Lin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]},{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]},{"id":"https://openalex.org/I49645291","display_name":"National Taipei University of Education","ror":"https://ror.org/02bzpph30","country_code":"TW","type":"education","lineage":["https://openalex.org/I49645291"]},{"id":"https://openalex.org/I99613584","display_name":"National Taipei University","ror":"https://ror.org/03e29r284","country_code":"TW","type":"education","lineage":["https://openalex.org/I99613584"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yen-Lin Chen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, 10608, Taiwan, R.O.C"],"raw_orcid":"https://orcid.org/0000-0001-7717-9393","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, 10608, Taiwan, R.O.C","institution_ids":["https://openalex.org/I118292597","https://openalex.org/I154864474","https://openalex.org/I49645291","https://openalex.org/I99613584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053133694","https://openalex.org/A5120960820"],"corresponding_institution_ids":["https://openalex.org/I118292597","https://openalex.org/I154864474","https://openalex.org/I49645291","https://openalex.org/I99613584"],"apc_list":{"value":2850,"currency":"USD","value_usd":2850},"apc_paid":{"value":2850,"currency":"USD","value_usd":2850},"fwci":7.2205,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93733376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"176","issue":null,"first_page":"113184","last_page":"113184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.33880001306533813,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.33880001306533813,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11810000240802765,"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":0.11110000312328339,"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/object-detection","display_name":"Object detection","score":0.6877999901771545},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5408999919891357},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5320000052452087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49540001153945923},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4325000047683716},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3246000111103058}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8197000026702881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271000146865845},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6877999901771545},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6730999946594238},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5408999919891357},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.32440000772476196},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.29840001463890076},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2646999955177307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.patcog.2026.113184","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113184","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Pattern Recognition","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.patcog.2026.113184","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113184","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Pattern Recognition","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1362823181","display_name":null,"funder_award_id":"NSTC-113-2622-8-027-009","funder_id":"https://openalex.org/F2461203286","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G5598053226","display_name":null,"funder_award_id":"NSTC-113-2218-E-027-002","funder_id":"https://openalex.org/F2461203286","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G5674089340","display_name":null,"funder_award_id":"1140400220","funder_id":"https://openalex.org/F4320311687","funder_display_name":"Ministry of Education"}],"funders":[{"id":"https://openalex.org/F2461203286","display_name":"National Science and Technology Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2113015548","https://openalex.org/W2115579991","https://openalex.org/W2177274842","https://openalex.org/W2741850495","https://openalex.org/W3000171824","https://openalex.org/W3128100939","https://openalex.org/W3176287975","https://openalex.org/W4210477486","https://openalex.org/W4292488293","https://openalex.org/W4316021899","https://openalex.org/W4385453546","https://openalex.org/W4387092319","https://openalex.org/W4393184775","https://openalex.org/W4406909014","https://openalex.org/W4408076713","https://openalex.org/W4409370893"],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1,49,106],"object":[2,50,107],"detection":[3,51,82,98,108],"has":[4],"gained":[5],"significant":[6],"attention":[7],"due":[8],"to":[9,77],"its":[10],"cost-effectiveness":[11],"and":[12,26,81,89,127],"practicality":[13],"in":[14,32,115],"real-world":[15,139],"applications.":[16],"However,":[17],"existing":[18,96],"monocular":[19,48,97,105],"methods":[20],"often":[21],"struggle":[22],"with":[23],"depth":[24,79],"estimation":[25],"spatial":[27],"consistency,":[28],"limiting":[29],"their":[30],"accuracy":[31],"complex":[33],"environments.":[34],"In":[35],"this":[36,147],"work,":[37],"we":[38],"introduce":[39],"a":[40,62,135],"Temporal":[41],"Deep":[42],"Feature":[43],"Learning":[44],"framework,":[45],"which":[46],"enhances":[47],"by":[52],"integrating":[53],"temporal":[54],"features":[55],"across":[56,102],"sequential":[57],"frames.":[58],"Our":[59,122],"approach":[60],"leverages":[61],"novel":[63],"deep":[64],"feature":[65],"auxiliary":[66],"module":[67,86],"based":[68],"on":[69],"convolutional":[70],"recurrent":[71],"structures,":[72],"effectively":[73],"capturing":[74],"spatiotemporal":[75],"information":[76],"improve":[78],"perception":[80,141],"robustness.":[83],"The":[84,143],"proposed":[85,131],"is":[87,149],"model-agnostic":[88],"can":[90],"be":[91],"seamlessly":[92],"integrated":[93],"into":[94],"various":[95],"frameworks.":[99],"Extensive":[100],"experiments":[101],"multiple":[103],"state-of-the-art":[104],"models":[109],"demonstrate":[110],"consistent":[111],"performance":[112],"improvements,":[113],"particularly":[114],"detecting":[116],"small":[117],"or":[118],"partially":[119],"occluded":[120],"objects.":[121],"results":[123],"highlight":[124],"the":[125,130],"effectiveness":[126],"generalizability":[128],"of":[129,146],"approach,":[132],"making":[133],"it":[134],"promising":[136],"solution":[137],"for":[138],"autonomous":[140],"systems.":[142],"source":[144],"code":[145],"work":[148],"at:":[150],"https://github.com/Shuray36/MonoTDF-Temporal-Deep-Feature-Learning-for-Generalizable-Monocular-3D-Object-Detection":[151],".":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-01-29T00:00:00"}