{"id":"https://openalex.org/W4385488625","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191977","title":"Efficient Multi-Task Scene Analysis with RGB-D Transformers","display_name":"Efficient Multi-Task Scene Analysis with RGB-D Transformers","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488625","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191977"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5019677916","display_name":"S\u00f6hnke Benedikt Fischedick","orcid":"https://orcid.org/0000-0001-8447-0584"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"S\u00f6hnke Benedikt Fischedick","raw_affiliation_strings":["Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684"],"raw_orcid":"https://orcid.org/0000-0001-8447-0584","affiliations":[{"raw_affiliation_string":"Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077353311","display_name":"Daniel Seichter","orcid":"https://orcid.org/0000-0002-3828-2926"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Seichter","raw_affiliation_strings":["Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065050142","display_name":"Robin Schmidt","orcid":"https://orcid.org/0000-0001-5613-8349"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robin Schmidt","raw_affiliation_strings":["Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092130769","display_name":"Leonard Rabes","orcid":null},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leonard Rabes","raw_affiliation_strings":["Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075114390","display_name":"Horst\u2013Michael Gro\u00df","orcid":"https://orcid.org/0000-0001-9712-0225"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Horst-Michael Gross","raw_affiliation_strings":["Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684","institution_ids":["https://openalex.org/I119449181"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019677916"],"corresponding_institution_ids":["https://openalex.org/I119449181"],"apc_list":null,"apc_paid":null,"fwci":2.0017,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88706899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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":0.8417191505432129},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.777909517288208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6585609912872314},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5923497676849365},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5660536885261536},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5645059943199158},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5187140107154846},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4796888530254364},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.47570571303367615},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4465055465698242},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42402949929237366},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4208759665489197},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4148673713207245},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0752088725566864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8417191505432129},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.777909517288208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6585609912872314},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5923497676849365},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5660536885261536},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5645059943199158},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5187140107154846},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4796888530254364},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.47570571303367615},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4465055465698242},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42402949929237366},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4208759665489197},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4148673713207245},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0752088725566864},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1923184257","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2275395544","https://openalex.org/W2489780108","https://openalex.org/W2560023338","https://openalex.org/W2560544142","https://openalex.org/W2587989515","https://openalex.org/W2594519801","https://openalex.org/W2630837129","https://openalex.org/W2774839435","https://openalex.org/W2775906317","https://openalex.org/W2781749584","https://openalex.org/W2805395174","https://openalex.org/W2896457183","https://openalex.org/W2910628332","https://openalex.org/W2911831070","https://openalex.org/W2924984885","https://openalex.org/W2955425717","https://openalex.org/W2963419596","https://openalex.org/W2963896186","https://openalex.org/W2964309882","https://openalex.org/W2965182628","https://openalex.org/W2969050719","https://openalex.org/W2970717207","https://openalex.org/W2971014764","https://openalex.org/W2971290066","https://openalex.org/W2971298073","https://openalex.org/W2999219213","https://openalex.org/W3003772167","https://openalex.org/W3034355852","https://openalex.org/W3085046840","https://openalex.org/W3097660860","https://openalex.org/W3099155473","https://openalex.org/W3108601100","https://openalex.org/W3110108516","https://openalex.org/W3124434019","https://openalex.org/W3131500599","https://openalex.org/W3133385195","https://openalex.org/W3138516171","https://openalex.org/W3168649818","https://openalex.org/W3176319743","https://openalex.org/W3194841206","https://openalex.org/W3207537403","https://openalex.org/W3211490618","https://openalex.org/W4292779060","https://openalex.org/W4295312788","https://openalex.org/W4302290282","https://openalex.org/W4312349930","https://openalex.org/W4312372834","https://openalex.org/W4312443924","https://openalex.org/W4312610896","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6748481559","https://openalex.org/W6762718338","https://openalex.org/W6766978945","https://openalex.org/W6778883912","https://openalex.org/W6785207073","https://openalex.org/W6797399245"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W3034529322","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W2115913271","https://openalex.org/W2113597336","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W2155505549"],"abstract_inverted_index":{"Scene":[0],"analysis":[1,63],"is":[2,51],"essential":[3],"for":[4,142],"enabling":[5,139,169],"autonomous":[6],"systems,":[7],"such":[8,29],"as":[9,30],"mobile":[10,49],"robots,":[11],"to":[12,73,173],"operate":[13],"in":[14,122],"real-world":[15],"environments.":[16],"However,":[17,87],"obtaining":[18],"a":[19,101,123,134],"comprehensive":[20],"understanding":[21],"of":[22,95],"the":[23,76,83,91,150],"scene":[24,37,62],"requires":[25],"solving":[26],"multiple":[27],"tasks,":[28],"panoptic":[31],"segmentation,":[32],"instance":[33],"orientation":[34],"estimation,":[35],"and":[36,45,115,157],"classification.":[38],"Solving":[39],"these":[40],"tasks":[41],"given":[42],"limited":[43],"computing":[44],"battery":[46],"capabilities":[47],"on":[48,129,149,176],"platforms":[50],"challenging.":[52],"To":[53,105,126],"address":[54],"this":[55],"challenge,":[56],"we":[57,88,108,132,159],"introduce":[58],"an":[59,69,177],"efficient":[60],"multi-task":[61],"approach,":[64],"called":[65],"EMSAFormer,":[66],"that":[67,90,161],"uses":[68],"RGB-D":[70],"Transformer-based":[71,103],"encoder":[72,94],"simultaneously":[74],"perform":[75],"aforementioned":[77],"tasks.":[78],"Our":[79],"approach":[80,163],"builds":[81],"upon":[82],"previously":[84],"published":[85],"EMSANet.":[86],"show":[89,160],"dual":[92],"CNN-based":[93],"EMSANet":[96],"can":[97,118],"be":[98,119],"replaced":[99],"with":[100,171],"single":[102,124],"encoder.":[104,125],"achieve":[106],"this,":[107],"investigate":[109],"how":[110],"information":[111],"from":[112],"both":[113],"RGB":[114],"depth":[116],"data":[117],"effectively":[120],"incorporated":[121],"accelerate":[127],"inference":[128,170],"robotic":[130],"hardware,":[131],"provide":[133],"custom":[135],"NVIDIA":[136,178],"TensorRT":[137],"extension":[138],"highly":[140],"optimization":[141],"our":[143,162],"EMSAFormer":[144],"approach.":[145],"Through":[146],"extensive":[147],"experiments":[148],"commonly":[151],"used":[152],"indoor":[153],"datasets":[154],"NYUv2,":[155],"SUNRGB-D,":[156],"ScanNet,":[158],"achieves":[164],"state-of-the-art":[165],"performance":[166],"while":[167],"still":[168],"up":[172],"39.1":[174],"FPS":[175],"Jetson":[179],"AGX":[180],"Orin":[181],"32":[182],"GB.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}