{"id":"https://openalex.org/W4372346764","doi":"https://doi.org/10.1109/icassp49357.2023.10096314","title":"DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-based Segmentation Networks","display_name":"DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-based Segmentation Networks","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346764","doi":"https://doi.org/10.1109/icassp49357.2023.10096314"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096314","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5068387663","display_name":"Francesco Barbato","orcid":"https://orcid.org/0000-0001-9893-5813"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Barbato","raw_affiliation_strings":["University of Padova,Department of Information Engineering,Padova,Italy","Department of Information Engineering, University of Padova, Padova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padova,Department of Information Engineering,Padova,Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070645069","display_name":"Giulia Rizzoli","orcid":"https://orcid.org/0000-0002-1390-8419"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulia Rizzoli","raw_affiliation_strings":["University of Padova,Department of Information Engineering,Padova,Italy","Department of Information Engineering, University of Padova, Padova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padova,Department of Information Engineering,Padova,Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070777118","display_name":"Pietro Zanuttigh","orcid":"https://orcid.org/0000-0002-9502-2389"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pietro Zanuttigh","raw_affiliation_strings":["University of Padova,Department of Information Engineering,Padova,Italy","Department of Information Engineering, University of Padova, Padova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padova,Department of Information Engineering,Padova,Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991999864578247,"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":0.8046441078186035},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.703691840171814},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6832754015922546},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6425654292106628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6370830535888672},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5694928169250488},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.549629271030426},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49527135491371155},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44225797057151794},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3831590712070465},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09391415119171143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046441078186035},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.703691840171814},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6832754015922546},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6425654292106628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6370830535888672},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5694928169250488},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.549629271030426},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49527135491371155},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44225797057151794},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3831590712070465},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09391415119171143},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096314","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.research.unipd.it:11577/3508084","is_oa":false,"landing_page_url":"https://hdl.handle.net/11577/3508084","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.8199999928474426,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2340897893","https://openalex.org/W2739253758","https://openalex.org/W2745846084","https://openalex.org/W2921749009","https://openalex.org/W2956887593","https://openalex.org/W2963038646","https://openalex.org/W2965380104","https://openalex.org/W2966669119","https://openalex.org/W3009257359","https://openalex.org/W3042346170","https://openalex.org/W3094502228","https://openalex.org/W3099155473","https://openalex.org/W3131500599","https://openalex.org/W3132397187","https://openalex.org/W3166016280","https://openalex.org/W3180638445","https://openalex.org/W3207537403","https://openalex.org/W3211490618","https://openalex.org/W4206573688","https://openalex.org/W4287879563","https://openalex.org/W4288348082","https://openalex.org/W4361029874","https://openalex.org/W4385245566","https://openalex.org/W4386179772","https://openalex.org/W6629098493","https://openalex.org/W6739901393","https://openalex.org/W6766273390","https://openalex.org/W6780728829","https://openalex.org/W6784333009","https://openalex.org/W6797399245","https://openalex.org/W6810281396","https://openalex.org/W6810856158"],"related_works":["https://openalex.org/W2517104666","https://openalex.org/W4223527717","https://openalex.org/W2005437358","https://openalex.org/W2790662084","https://openalex.org/W1669643531","https://openalex.org/W2008656436","https://openalex.org/W2134924024","https://openalex.org/W2023558673","https://openalex.org/W4313142172","https://openalex.org/W2110230079"],"abstract_inverted_index":{"Most":[0],"approaches":[1],"for":[2],"semantic":[3],"segmentation":[4,45],"use":[5],"only":[6],"information":[7,53],"from":[8],"color":[9,107],"cameras":[10],"to":[11,24,50,66],"parse":[12],"the":[13,44,58,64,80,89,96,100,104,115],"scenes,":[14],"yet":[15],"recent":[16],"advancements":[17],"show":[18],"that":[19,38,78],"using":[20],"depth":[21,52,105],"data":[22,68],"allows":[23],"further":[25],"improve":[26],"performances.":[27],"In":[28],"this":[29],"work,":[30],"we":[31,48,62],"focus":[32],"on":[33,43,114],"transformer-based":[34],"deep":[35],"learning":[36],"architectures,":[37],"have":[39],"achieved":[40],"state-of-the-art":[41],"performances":[42,113],"task,":[46],"and":[47,73,106],"propose":[49],"employ":[51],"by":[54],"embedding":[55],"it":[56],"in":[57,74],"positional":[59],"encoding.":[60],"Effectively,":[61],"extend":[63],"network":[65],"multimodal":[67],"without":[69],"adding":[70],"any":[71],"parameters":[72],"a":[75],"natural":[76],"way":[77],"exploits":[79],"strength":[81],"of":[82,91],"transformers\u2019":[83],"self-attention":[84],"modules.":[85],"We":[86],"also":[87],"investigate":[88],"idea":[90],"performing":[92],"cross-modality":[93],"operations":[94],"inside":[95],"attention":[97],"module,":[98],"swapping":[99],"key":[101],"inputs":[102],"between":[103],"branches.":[108],"Our":[109],"approach":[110],"consistently":[111],"improves":[112],"Cityscapes":[116],"benchmark.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}