{"id":"https://openalex.org/W7129382632","doi":"https://doi.org/10.1109/icipw68931.2025.11386296","title":"Multimodal Monocular 3D Object Localization for Human-Robot Interaction","display_name":"Multimodal Monocular 3D Object Localization for Human-Robot Interaction","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W7129382632","doi":"https://doi.org/10.1109/icipw68931.2025.11386296"},"language":"en","primary_location":{"id":"doi:10.1109/icipw68931.2025.11386296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386296","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 Image Processing Workshops (ICIPW)","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/A5126258522","display_name":"Ari Wahl","orcid":null},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ari Wahl","raw_affiliation_strings":["Fraunhofer HHI,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer HHI,Berlin,Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126205407","display_name":"Dorian Gawlinski","orcid":null},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorian Gawlinski","raw_affiliation_strings":["Fraunhofer HHI,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer HHI,Berlin,Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033414262","display_name":"David Przewozny","orcid":"https://orcid.org/0000-0002-8459-9182"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Przewozny","raw_affiliation_strings":["Fraunhofer HHI,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer HHI,Berlin,Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004283092","display_name":"Paul Chojecki","orcid":"https://orcid.org/0000-0002-8807-0008"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paul Chojecki","raw_affiliation_strings":["Fraunhofer HHI,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer HHI,Berlin,Germany","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126254026","display_name":"Felix Bie\u03b2mann","orcid":null},"institutions":[{"id":"https://openalex.org/I129643931","display_name":"Berliner Hochschule f\u00fcr Technik","ror":"https://ror.org/00w7whj55","country_code":"DE","type":"education","lineage":["https://openalex.org/I129643931"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Bie\u03b2mann","raw_affiliation_strings":["Berliner Hochschule fϋr Technik (BHT),Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berliner Hochschule fϋr Technik (BHT),Berlin,Germany","institution_ids":["https://openalex.org/I129643931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020506776","display_name":"Sebastian Bosse","orcid":"https://orcid.org/0000-0002-8104-3904"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Bosse","raw_affiliation_strings":["Fraunhofer HHI,Berlin,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer HHI,Berlin,Germany","institution_ids":["https://openalex.org/I2800274787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126258522"],"corresponding_institution_ids":["https://openalex.org/I2800274787"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69006238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"310","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8878999948501587,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8878999948501587,"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":0.052799999713897705,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.011699999682605267,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7074000239372253},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.588100016117096},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.569100022315979},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5623000264167786},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.524399995803833},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.47099998593330383},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45669999718666077},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3741999864578247}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8052999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736999988555908},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7343999743461609},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7074000239372253},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.588100016117096},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5623000264167786},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.524399995803833},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3741999864578247},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2800999879837036}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icipw68931.2025.11386296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386296","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 Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/514980","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/514980","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5925664901733398,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W3035254347","https://openalex.org/W3114509423","https://openalex.org/W4385430679","https://openalex.org/W4390480939","https://openalex.org/W4390872744","https://openalex.org/W4390873008","https://openalex.org/W4390873312","https://openalex.org/W4401416579","https://openalex.org/W4402353981","https://openalex.org/W4402354046","https://openalex.org/W4402890475","https://openalex.org/W4413147844","https://openalex.org/W4415797243"],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"general-purpose":[1],"Vision-Language":[2],"Models":[3],"(VLM)":[4],"hold":[5],"the":[6,121,138,148],"potential":[7],"to":[8,14,95,150],"enhance":[9],"intuitive":[10],"human-machine":[11],"interactions":[12],"due":[13],"their":[15],"rich":[16],"world":[17],"knowledge":[18],"and":[19,60,65,75,124],"2D":[20],"object":[21,46],"detection":[22,30],"capabilities":[23],"[1].":[24],"However,":[25],"VLMs":[26,42],"for":[27,147],"3D":[28,45,103],"coordinates":[29],"tasks":[31],"are":[32,141],"rare.":[33],"In":[34,134],"this":[35],"work,":[36],"we":[37],"investigate":[38],"interactive":[39],"abilities":[40],"of":[41,70,117,137],"by":[43],"returning":[44],"positions":[47],"given":[48],"a":[49,54,67,77,82,114,125,129,143],"monocular":[50],"RGB":[51],"image":[52],"from":[53],"wrist-mounted":[55],"camera,":[56],"natural":[57],"language":[58],"input,":[59],"robot":[61,149],"states.":[62],"We":[63],"collected":[64],"curated":[66],"heterogeneous":[68],"dataset":[69],"more":[71],"than":[72],"100,000":[73],"images":[74],"finetuned":[76],"VLM":[78],"using":[79],"QLoRA":[80],"with":[81,113,152],"custom":[83],"regression":[84],"head.":[85],"By":[86],"implementing":[87],"conditional":[88],"routing,":[89],"our":[90],"model":[91],"maintains":[92],"its":[93],"ability":[94],"process":[96],"general":[97],"visual":[98],"queries":[99],"while":[100],"adding":[101],"specialized":[102],"position":[104],"estimation":[105],"capabilities.":[106],"Our":[107],"results":[108],"demonstrate":[109],"robust":[110],"predictive":[111],"performance":[112],"median":[115],"MAE":[116],"13":[118],"mm":[119],"on":[120],"test":[122],"set":[123],"five-fold":[126],"improvement":[127],"over":[128],"simpler":[130],"baseline":[131],"without":[132],"finetuning.":[133],"about":[135],"25%":[136],"cases,":[139],"predictions":[140],"within":[142],"range":[144],"considered":[145],"acceptable":[146],"interact":[151],"objects.":[153]},"counts_by_year":[],"updated_date":"2026-04-26T08:31:28.666265","created_date":"2026-02-18T00:00:00"}