{"id":"https://openalex.org/W4405785381","doi":"https://doi.org/10.1109/iros58592.2024.10802239","title":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images","display_name":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785381","doi":"https://doi.org/10.1109/iros58592.2024.10802239"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5094196412","display_name":"Pardis Taghavi","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pardis Taghavi","raw_affiliation_strings":["Texas A&M University,Department of Mechanical Engineering,College Station,TX,USA,77840"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University,Department of Mechanical Engineering,College Station,TX,USA,77840","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017696249","display_name":"Reza Langari","orcid":"https://orcid.org/0000-0001-7900-5186"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reza Langari","raw_affiliation_strings":["Texas A&M University,Department of Mechanical Engineering,College Station,TX,USA,77840"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University,Department of Mechanical Engineering,College Station,TX,USA,77840","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101429750","display_name":"Gaurav Pandey","orcid":"https://orcid.org/0000-0002-4838-802X"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Pandey","raw_affiliation_strings":["Texas A&M University,Department of Engineering Technology & Industrial Distribution,College Station,TX,USA,77840"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University,Department of Engineering Technology & Industrial Distribution,College Station,TX,USA,77840","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4957","last_page":"4964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9660999774932861,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9660999774932861,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9635000228881836,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9308000206947327,"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":0.7685418725013733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7534076571464539},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.715950071811676},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7026848793029785},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6164150834083557},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5258206129074097},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4793687164783478},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4253835380077362},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11732685565948486},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05857139825820923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685418725013733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7534076571464539},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.715950071811676},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7026848793029785},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6164150834083557},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5258206129074097},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4793687164783478},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4253835380077362},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11732685565948486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05857139825820923},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":46,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2124907686","https://openalex.org/W2340897893","https://openalex.org/W2343077198","https://openalex.org/W2412782625","https://openalex.org/W2562137921","https://openalex.org/W2798441115","https://openalex.org/W2891374529","https://openalex.org/W2895387432","https://openalex.org/W2913340405","https://openalex.org/W2949208911","https://openalex.org/W2963430933","https://openalex.org/W2963488291","https://openalex.org/W2963652981","https://openalex.org/W2963677766","https://openalex.org/W2963877604","https://openalex.org/W2969365860","https://openalex.org/W3048775510","https://openalex.org/W3085046840","https://openalex.org/W3097571420","https://openalex.org/W3103908142","https://openalex.org/W3138516171","https://openalex.org/W3160809918","https://openalex.org/W3173727695","https://openalex.org/W3176063055","https://openalex.org/W3180638445","https://openalex.org/W3203073814","https://openalex.org/W3204786153","https://openalex.org/W3204819834","https://openalex.org/W4221152259","https://openalex.org/W4303645333","https://openalex.org/W4312253171","https://openalex.org/W4312871721","https://openalex.org/W4385391093","https://openalex.org/W4386065386","https://openalex.org/W6685261749","https://openalex.org/W6735913928","https://openalex.org/W6741832134","https://openalex.org/W6745995898","https://openalex.org/W6754005058","https://openalex.org/W6757817989","https://openalex.org/W6784333009","https://openalex.org/W6785345353","https://openalex.org/W6859305255"],"related_works":["https://openalex.org/W200819717","https://openalex.org/W2032269556","https://openalex.org/W1991834176","https://openalex.org/W2944448661","https://openalex.org/W2064421702","https://openalex.org/W4253756925","https://openalex.org/W2805523177","https://openalex.org/W2131956013","https://openalex.org/W2036566443","https://openalex.org/W1522196789"],"abstract_inverted_index":{"This":[0],"research":[1],"paper":[2,53],"presents":[3],"an":[4,55],"innovative":[5],"multitask":[6],"learning":[7],"framework":[8,63,73],"that":[9],"allows":[10],"concurrent":[11],"depth":[12,41,103,129],"estimation":[13,42,104],"and":[14,43,85,93,102,131],"semantic":[15,44],"segmentation":[16,45,101],"using":[17],"a":[18,27,60,65,137],"single":[19],"camera.":[20],"The":[21,72,144],"proposed":[22,142],"approach":[23],"is":[24,74,148],"based":[25],"on":[26,77],"shared":[28],"encoder-decoder":[29],"architecture,":[30],"which":[31],"integrates":[32],"various":[33],"techniques":[34],"to":[35,68,111,135],"improve":[36],"the":[37,40,52,81,86,113,121,125,141],"accuracy":[38],"of":[39,115,123,127,140],"task":[46],"without":[47],"compromising":[48],"computational":[49],"efficiency.":[50],"Additionally,":[51],"incorporates":[54],"adversarial":[56],"training":[57],"component,":[58],"employing":[59],"Wasserstein":[61],"GAN":[62],"with":[64],"critic":[66],"network,":[67],"refine":[69],"model\u2019s":[70],"predictions.":[71],"thoroughly":[75],"evaluated":[76],"two":[78],"datasets":[79],"-":[80,92],"outdoor":[82],"Cityscapes":[83],"dataset":[84,91],"indoor":[87],"NYU":[88],"Depth":[89],"V2":[90],"it":[94],"outperforms":[95],"existing":[96],"state-of-the-art":[97],"methods":[98],"in":[99],"both":[100],"tasks.":[105],"We":[106],"also":[107],"conducted":[108],"ablation":[109],"studies":[110],"analyze":[112],"contributions":[114],"different":[116],"components,":[117],"including":[118],"pre-training":[119],"strategies,":[120],"inclusion":[122],"critics,":[124],"use":[126],"logarithmic":[128],"scaling,":[130],"advanced":[132],"image":[133],"augmentations,":[134],"provide":[136],"better":[138],"understanding":[139],"framework.":[143],"accompanying":[145],"source":[146],"code":[147],"accessible":[149],"at":[150],"https://github.com/PardisTaghavi/SwinMTL.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}