{"id":"https://openalex.org/W7125905547","doi":"https://doi.org/10.1109/smc58881.2025.11343042","title":"DUO-Net: Joint End-to-End 2D Object Detection and Depth Estimation via Uncertainty-Aware Multitask Learning","display_name":"DUO-Net: Joint End-to-End 2D Object Detection and Depth Estimation via Uncertainty-Aware Multitask Learning","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125905547","doi":"https://doi.org/10.1109/smc58881.2025.11343042"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5034912950","display_name":"Fazal Ghaffar","orcid":"https://orcid.org/0009-0005-2262-3609"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Fazal Ghaffar","raw_affiliation_strings":["Deakin University,Institute for Intelligent Systems Research and Innovation (IISRI),Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University,Institute for Intelligent Systems Research and Innovation (IISRI),Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101427304","display_name":"Burhan Khan","orcid":"https://orcid.org/0000-0002-1765-935X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Burhan Khan","raw_affiliation_strings":["Deakin University,Institute for Intelligent Systems Research and Innovation (IISRI),Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University,Institute for Intelligent Systems Research and Innovation (IISRI),Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124059310","display_name":"Seyed Mohammad J. Jalali","orcid":null},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Seyed Mohammad J. Jalali","raw_affiliation_strings":["Edith Cowan University,School of Science,Joondalup,WA,Australia"],"affiliations":[{"raw_affiliation_string":"Edith Cowan University,School of Science,Joondalup,WA,Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072923302","display_name":"Chee Peng Lim","orcid":"https://orcid.org/0000-0003-4191-9083"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chee Peng Lim","raw_affiliation_strings":["Swinburne University of Technology,Department of Computing Tech-Nologies,Melbourne,Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology,Department of Computing Tech-Nologies,Melbourne,Australia","institution_ids":["https://openalex.org/I57093077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034912950"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7159397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4377","last_page":"4384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7146999835968018,"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":0.7146999835968018,"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":0.0754999965429306,"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":0.07199999690055847,"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/task","display_name":"Task (project management)","score":0.7184000015258789},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7099000215530396},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.6953999996185303},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6859999895095825},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5719000101089478},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5630000233650208},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5511999726295471},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5365999937057495},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4778999984264374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809000015258789},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7184000015258789},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7099000215530396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7055000066757202},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6953999996185303},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6859999895095825},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5376999974250793},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5365999937057495},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4778999984264374},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.3278999924659729},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":39,"referenced_works":["https://openalex.org/W607748843","https://openalex.org/W639708223","https://openalex.org/W2085805060","https://openalex.org/W2100912617","https://openalex.org/W2147347517","https://openalex.org/W2150066425","https://openalex.org/W2278156142","https://openalex.org/W2342242867","https://openalex.org/W2490270993","https://openalex.org/W2521788491","https://openalex.org/W2562137921","https://openalex.org/W2622634896","https://openalex.org/W2746763587","https://openalex.org/W2795812085","https://openalex.org/W2798441115","https://openalex.org/W2892087253","https://openalex.org/W2895387432","https://openalex.org/W2904300946","https://openalex.org/W2955639361","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963430933","https://openalex.org/W2963677766","https://openalex.org/W2963749150","https://openalex.org/W2963877604","https://openalex.org/W2964185501","https://openalex.org/W2964247799","https://openalex.org/W2966182616","https://openalex.org/W2973041079","https://openalex.org/W3009086519","https://openalex.org/W3085046840","https://openalex.org/W3096609285","https://openalex.org/W3097571420","https://openalex.org/W3120061487","https://openalex.org/W3144974485","https://openalex.org/W3176584633","https://openalex.org/W3186334775","https://openalex.org/W4214520160","https://openalex.org/W4414463394"],"related_works":[],"abstract_inverted_index":{"DUO-Net":[0,92],"is":[1,43],"proposed,":[2],"a":[3,19],"unified":[4],"multi-task":[5],"learning":[6],"framework":[7],"for":[8],"joint":[9,55],"2D":[10],"object":[11],"detection":[12],"and":[13,26,35,50,60,67,89,102],"depth":[14,37],"estimation.":[15],"The":[16],"architecture":[17],"employs":[18],"shared":[20],"ResNet-based":[21],"backbone":[22],"with":[23],"attention":[24],"modules":[25],"task-specific":[27],"heads":[28],"to":[29,45,78],"simultaneously":[30],"perform":[31],"bounding":[32],"box":[33],"localisation":[34],"dense":[36],"prediction.":[38],"A":[39],"two-stage":[40],"training":[41],"method":[42],"adopted":[44],"sequentially":[46],"pretrain":[47],"each":[48],"task":[49,65,81],"subsequently":[51],"refine":[52],"them":[53],"through":[54],"learning,":[56],"enhancing":[57],"both":[58,97],"features":[59],"convergence":[61],"reliability.":[62],"To":[63],"address":[64],"imbalance":[66],"noisy":[68],"supervision,":[69],"we":[70],"incorporate":[71],"uncertainty-aware":[72],"loss":[73],"weighting,":[74],"enabling":[75],"the":[76,87],"model":[77],"dynamically":[79],"adjust":[80],"contributions":[82],"during":[83],"training.":[84],"Evaluated":[85],"on":[86],"KITTI":[88],"JRDB":[90],"datasets,":[91],"demonstrates":[93],"robust":[94],"performance":[95],"across":[96],"tasks":[98],"while":[99],"maintaining":[100],"efficiency":[101],"scalability.":[103]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}