{"id":"https://openalex.org/W4416137203","doi":"https://doi.org/10.1109/ipta66025.2025.11222061","title":"Curvature Dedicated Architecture Using Swin Transformers for RGB-D Object Recognition","display_name":"Curvature Dedicated Architecture Using Swin Transformers for RGB-D Object Recognition","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4416137203","doi":"https://doi.org/10.1109/ipta66025.2025.11222061"},"language":null,"primary_location":{"id":"doi:10.1109/ipta66025.2025.11222061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta66025.2025.11222061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools &amp;amp; Applications (IPTA)","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/A5103997554","display_name":"Maxime Morisset","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210157089","display_name":"Laboratoire de l'Int\u00e9gration du Mat\u00e9riau au Syst\u00e8me","ror":"https://ror.org/04nabhy78","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210091158","https://openalex.org/I4210095849","https://openalex.org/I4210157089","https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maxime Morisset","raw_affiliation_strings":["Univ. Bordeaux, CNRS, Bordeaux INP, IMS,Talence,France,F-33400"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Bordeaux, CNRS, Bordeaux INP, IMS,Talence,France,F-33400","institution_ids":["https://openalex.org/I4210157089","https://openalex.org/I4210160189","https://openalex.org/I1294671590","https://openalex.org/I15057530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074358807","display_name":"Marc Donias","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210157089","display_name":"Laboratoire de l'Int\u00e9gration du Mat\u00e9riau au Syst\u00e8me","ror":"https://ror.org/04nabhy78","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210091158","https://openalex.org/I4210095849","https://openalex.org/I4210157089","https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marc Donias","raw_affiliation_strings":["Univ. Bordeaux, CNRS, Bordeaux INP, IMS,Talence,France,F-33400"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Bordeaux, CNRS, Bordeaux INP, IMS,Talence,France,F-33400","institution_ids":["https://openalex.org/I4210157089","https://openalex.org/I4210160189","https://openalex.org/I1294671590","https://openalex.org/I15057530"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084906943","display_name":"Christian Germain","orcid":"https://orcid.org/0000-0002-3097-8283"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christian Germain","raw_affiliation_strings":["Univ. Bordeaux, CNRS, Bordeaux INP, Bordeaux Sciences Agro, IMS,Talence,France,F-33400"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Bordeaux, CNRS, Bordeaux INP, Bordeaux Sciences Agro, IMS,Talence,France,F-33400","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I4210160189","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.304965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7092000246047974,"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":0.7092000246047974,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.0674000009894371,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.04699999839067459,"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/rgb-color-model","display_name":"RGB color model","score":0.7159000039100647},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5177000164985657},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4839000105857849},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4596000015735626},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.4553999900817871},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.40860000252723694},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7297999858856201},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7159000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679099977016449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6536999940872192},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.40860000252723694},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2671000063419342}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipta66025.2025.11222061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta66025.2025.11222061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools &amp;amp; Applications (IPTA)","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":8,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2156222070","https://openalex.org/W2194775991","https://openalex.org/W2744698739","https://openalex.org/W2963956866","https://openalex.org/W3138516171","https://openalex.org/W4312349930"],"related_works":[],"abstract_inverted_index":{"Image":[0],"classification":[1,141,150],"using":[2,44,165],"RGB-D":[3,139],"data":[4],"has":[5,64],"become":[6],"increasingly":[7],"important":[8],"in":[9,14,176],"computer":[10],"vision":[11],"applications,":[12],"especially":[13],"environments":[15],"where":[16],"RGB":[17,26,62,104,133],"information":[18],"alone":[19],"proves":[20],"insufficient.":[21],"Late":[22],"fusion":[23],"approaches":[24],"process":[25],"and":[27,124],"depth":[28,52,69,87,94],"modalities":[29],"independently,":[30],"enabling":[31],"richer":[32],"feature":[33],"learning.":[34],"While":[35,168],"our":[36,143,185],"previous":[37],"works":[38],"have":[39],"demonstrated":[40],"the":[41,54,66,117,137,161,169,181,188],"relevance":[42],"of":[43,50,56,68,152,163,171,184],"curvature":[45,166],"as":[46,71,195],"input":[47],"features":[48,126],"instead":[49],"raw":[51],"values,":[53],"dependence":[55,130],"Convolutional":[57],"Neural":[58],"Networks":[59],"on":[60,92,131,136],"pre-trained":[61,132],"backbones":[63],"forced":[65],"usage":[67],"colorization":[70],"a":[72,77,109,149],"workaround.":[73],"This":[74,114],"work":[75],"proposes":[76],"novel":[78],"architecture":[79,115,186],"that":[80],"natively":[81],"processes":[82],"principal":[83],"curvatures":[84,173],"extracted":[85],"from":[86,127],"images,":[88],"rather":[89],"than":[90],"relying":[91],"colorized":[93],"representations.":[95],"Our":[96],"method":[97],"introduces":[98,174],"dual":[99],"curvature-dedicated":[100],"streams":[101],"alongside":[102],"an":[103],"stream,":[105],"all":[106],"integrated":[107],"within":[108],"Swin":[110],"Transformer":[111],"V2":[112],"framework.":[113],"leverages":[116],"transformer's":[118],"capacity":[119],"to":[120,190],"learn":[121],"both":[122],"local":[123],"global":[125],"scratch,":[128],"without":[129],"models.":[134],"Evaluated":[135],"Washington":[138],"object":[140,196],"dataset,":[142],"approach":[144],"achieves":[145],"state-of-the-art":[146],"performance":[147],"with":[148],"accuracy":[151],"<tex":[153],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{9":[155],"4.":[156],"5":[157],"6":[158],"\\%}$</tex>,":[159],"confirming":[160],"efficacy":[162],"directly":[164],"information.":[167],"use":[170],"logarithmic-scale":[172],"limitations":[175],"distinguishing":[177],"certain":[178],"surface":[179],"types,":[180],"modular":[182],"design":[183],"open":[187],"path":[189],"more":[191],"complex":[192],"tasks":[193],"such":[194],"detection":[197],"or":[198],"segmentation.":[199]},"counts_by_year":[],"updated_date":"2025-11-28T06:01:27.636517","created_date":"2025-11-10T00:00:00"}